Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore
index 67ebd30..d71179d 100644
--- a/arch/powerpc/kernel/.gitignore
+++ b/arch/powerpc/kernel/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
prom_init_check
vmlinux.lds
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index afbd47b..376104c 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -3,8 +3,6 @@
# Makefile for the linux kernel.
#
-CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
ifdef CONFIG_PPC64
CFLAGS_prom_init.o += $(NO_MINIMAL_TOC)
endif
@@ -13,13 +11,15 @@
CFLAGS_btext.o += -fPIC
endif
+CFLAGS_early_32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
+CFLAGS_prom_init.o += -fno-stack-protector
CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_prom_init.o += -ffreestanding
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
@@ -40,16 +40,18 @@
CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
endif
-obj-y := cputable.o ptrace.o syscalls.o \
- irq.o align.o signal_32.o pmc.o vdso.o \
+obj-y := cputable.o syscalls.o \
+ irq.o align.o signal_$(BITS).o pmc.o vdso.o \
process.o systbl.o idle.o \
signal.o sysfs.o cacheinfo.o time.o \
prom.o traps.o setup-common.o \
udbg.o misc.o io.o misc_$(BITS).o \
- of_platform.o prom_parse.o
-obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
- signal_64.o ptrace32.o \
- paca.o nvram_64.o firmware.o note.o
+ of_platform.o prom_parse.o firmware.o \
+ hw_breakpoint_constraints.o
+obj-y += ptrace/
+obj-$(CONFIG_PPC64) += setup_64.o \
+ paca.o nvram_64.o note.o syscall_64.o
+obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o
obj-$(CONFIG_VDSO32) += vdso32/
obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
@@ -61,8 +63,7 @@
obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
-obj-$(CONFIG_PPC_970_NAP) += idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP) += idle_book3s.o
+obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o
procfs-y := proc_powerpc.o
obj-$(CONFIG_PROC_FS) += $(procfs-y)
rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o
@@ -71,13 +72,12 @@
obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o
obj-$(CONFIG_RTAS_PROC) += rtas-proc.o
obj-$(CONFIG_PPC_DT_CPU_FTRS) += dt_cpu_ftrs.o
-obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
+obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_cache.o \
eeh_driver.o eeh_event.o eeh_sysfs.o
obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
-ifneq ($(CONFIG_FA_DUMP)$(CONFIG_PRESERVE_FA_DUMP),)
-obj-y += fadump.o
-endif
+obj-$(CONFIG_FA_DUMP) += fadump.o
+obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o
ifdef CONFIG_PPC32
obj-$(CONFIG_E500) += idle_e500.o
endif
@@ -96,7 +96,8 @@
obj-$(CONFIG_PPC_DOORBELL) += dbell.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
-extra-y := head_$(BITS).o
+extra-$(CONFIG_PPC64) := head_64.o
+extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o
extra-$(CONFIG_40x) := head_40x.o
extra-$(CONFIG_44x) := head_44x.o
extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o
@@ -123,14 +124,6 @@
obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \
pci-common.o pci_of_scan.o
obj-$(CONFIG_PCI_MSI) += msi.o
-obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o crash.o \
- machine_kexec_$(BITS).o
-obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o
-ifdef CONFIG_HAVE_IMA_KEXEC
-ifdef CONFIG_IMA
-obj-y += ima_kexec.o
-endif
-endif
obj-$(CONFIG_AUDIT) += audit.o
obj64-$(CONFIG_AUDIT) += compat_audit.o
@@ -158,22 +151,22 @@
obj-y += ucall.o
endif
+obj-$(CONFIG_PPC_SECURE_BOOT) += secure_boot.o ima_arch.o secvar-ops.o
+obj-$(CONFIG_PPC_SECVAR_SYSFS) += secvar-sysfs.o
+
# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
KCOV_INSTRUMENT_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
-GCOV_PROFILE_machine_kexec_64.o := n
-KCOV_INSTRUMENT_machine_kexec_64.o := n
-UBSAN_SANITIZE_machine_kexec_64.o := n
-GCOV_PROFILE_machine_kexec_32.o := n
-KCOV_INSTRUMENT_machine_kexec_32.o := n
-UBSAN_SANITIZE_machine_kexec_32.o := n
GCOV_PROFILE_kprobes.o := n
KCOV_INSTRUMENT_kprobes.o := n
UBSAN_SANITIZE_kprobes.o := n
GCOV_PROFILE_kprobes-ftrace.o := n
KCOV_INSTRUMENT_kprobes-ftrace.o := n
UBSAN_SANITIZE_kprobes-ftrace.o := n
+GCOV_PROFILE_syscall_64.o := n
+KCOV_INSTRUMENT_syscall_64.o := n
+UBSAN_SANITIZE_syscall_64.o := n
UBSAN_SANITIZE_vdso.o := n
# Necessary for booting with kcov enabled on book3e machines
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 92045ed..c7797eb 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -24,6 +24,7 @@
#include <asm/disassemble.h>
#include <asm/cpu_has_feature.h>
#include <asm/sstep.h>
+#include <asm/inst.h>
struct aligninfo {
unsigned char len;
@@ -104,7 +105,7 @@
* so we don't need the address swizzling.
*/
static int emulate_spe(struct pt_regs *regs, unsigned int reg,
- unsigned int instr)
+ struct ppc_inst ppc_instr)
{
int ret;
union {
@@ -115,8 +116,9 @@
} data, temp;
unsigned char __user *p, *addr;
unsigned long *evr = ¤t->thread.evr[reg];
- unsigned int nb, flags;
+ unsigned int nb, flags, instr;
+ instr = ppc_inst_val(ppc_instr);
instr = (instr >> 1) & 0x1f;
/* DAR has the operand effective address */
@@ -176,11 +178,11 @@
ret |= __get_user_inatomic(temp.v[1], p++);
ret |= __get_user_inatomic(temp.v[2], p++);
ret |= __get_user_inatomic(temp.v[3], p++);
- /* fall through */
+ fallthrough;
case 4:
ret |= __get_user_inatomic(temp.v[4], p++);
ret |= __get_user_inatomic(temp.v[5], p++);
- /* fall through */
+ fallthrough;
case 2:
ret |= __get_user_inatomic(temp.v[6], p++);
ret |= __get_user_inatomic(temp.v[7], p++);
@@ -261,11 +263,11 @@
ret |= __put_user_inatomic(data.v[1], p++);
ret |= __put_user_inatomic(data.v[2], p++);
ret |= __put_user_inatomic(data.v[3], p++);
- /* fall through */
+ fallthrough;
case 4:
ret |= __put_user_inatomic(data.v[4], p++);
ret |= __put_user_inatomic(data.v[5], p++);
- /* fall through */
+ fallthrough;
case 2:
ret |= __put_user_inatomic(data.v[6], p++);
ret |= __put_user_inatomic(data.v[7], p++);
@@ -293,7 +295,7 @@
int fix_alignment(struct pt_regs *regs)
{
- unsigned int instr;
+ struct ppc_inst instr;
struct instruction_op op;
int r, type;
@@ -303,18 +305,18 @@
*/
CHECK_FULL_REGS(regs);
- if (unlikely(__get_user(instr, (unsigned int __user *)regs->nip)))
+ if (unlikely(__get_user_instr(instr, (void __user *)regs->nip)))
return -EFAULT;
if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
/* We don't handle PPC little-endian any more... */
if (cpu_has_feature(CPU_FTR_PPC_LE))
return -EIO;
- instr = swab32(instr);
+ instr = ppc_inst_swab(instr);
}
#ifdef CONFIG_SPE
- if ((instr >> 26) == 0x4) {
- int reg = (instr >> 21) & 0x1f;
+ if (ppc_inst_primary_opcode(instr) == 0x4) {
+ int reg = (ppc_inst_val(instr) >> 21) & 0x1f;
PPC_WARN_ALIGNMENT(spe, regs);
return emulate_spe(regs, reg, instr);
}
@@ -331,7 +333,7 @@
* when pasting to a co-processor. Furthermore, paste_last is the
* synchronisation point for preceding copy/paste sequences.
*/
- if ((instr & 0xfc0006fe) == (PPC_INST_COPY & 0xfc0006fe))
+ if ((ppc_inst_val(instr) & 0xfc0006fe) == (PPC_INST_COPY & 0xfc0006fe))
return -EIO;
r = analyse_instr(&op, regs, instr);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index af39967..5c12525 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -30,7 +30,6 @@
#include <asm/io.h>
#include <asm/page.h>
-#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
@@ -70,6 +69,10 @@
#include <asm/fixmap.h>
#endif
+#ifdef CONFIG_XMON
+#include "../xmon/xmon_bpts.h"
+#endif
+
#define STACK_PT_REGS_OFFSET(sym, val) \
DEFINE(sym, STACK_FRAME_OVERHEAD + offsetof(struct pt_regs, val))
@@ -127,6 +130,24 @@
OFFSET(KSP_VSID, thread_struct, ksp_vsid);
#else /* CONFIG_PPC64 */
OFFSET(PGDIR, thread_struct, pgdir);
+#ifdef CONFIG_VMAP_STACK
+ OFFSET(SRR0, thread_struct, srr0);
+ OFFSET(SRR1, thread_struct, srr1);
+ OFFSET(DAR, thread_struct, dar);
+ OFFSET(DSISR, thread_struct, dsisr);
+#ifdef CONFIG_PPC_BOOK3S_32
+ OFFSET(THR0, thread_struct, r0);
+ OFFSET(THR3, thread_struct, r3);
+ OFFSET(THR4, thread_struct, r4);
+ OFFSET(THR5, thread_struct, r5);
+ OFFSET(THR6, thread_struct, r6);
+ OFFSET(THR8, thread_struct, r8);
+ OFFSET(THR9, thread_struct, r9);
+ OFFSET(THR11, thread_struct, r11);
+ OFFSET(THLR, thread_struct, lr);
+ OFFSET(THCTR, thread_struct, ctr);
+#endif
+#endif
#ifdef CONFIG_SPE
OFFSET(THREAD_EVR0, thread_struct, evr[0]);
OFFSET(THREAD_ACC, thread_struct, acc);
@@ -155,6 +176,7 @@
OFFSET(THREAD_TM_TAR, thread_struct, tm_tar);
OFFSET(THREAD_TM_PPR, thread_struct, tm_ppr);
OFFSET(THREAD_TM_DSCR, thread_struct, tm_dscr);
+ OFFSET(THREAD_TM_AMR, thread_struct, tm_amr);
OFFSET(PT_CKPT_REGS, thread_struct, ckpt_regs);
OFFSET(THREAD_CKVRSTATE, thread_struct, ckvr_state.vr);
OFFSET(THREAD_CKVRSAVE, thread_struct, ckvrsave);
@@ -385,29 +407,25 @@
OFFSET(CFG_SYSCALL_MAP32, vdso_data, syscall_map_32);
OFFSET(WTOM_CLOCK_SEC, vdso_data, wtom_clock_sec);
OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec);
- OFFSET(STAMP_XTIME, vdso_data, stamp_xtime);
+ OFFSET(STAMP_XTIME_SEC, vdso_data, stamp_xtime_sec);
+ OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
+#ifdef CONFIG_PPC64
OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
-#ifdef CONFIG_PPC64
OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
- OFFSET(TVAL64_TV_SEC, timeval, tv_sec);
- OFFSET(TVAL64_TV_USEC, timeval, tv_usec);
+ OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
+ OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
+#endif
+ OFFSET(TSPC64_TV_SEC, __kernel_timespec, tv_sec);
+ OFFSET(TSPC64_TV_NSEC, __kernel_timespec, tv_nsec);
OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec);
OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec);
- OFFSET(TSPC64_TV_SEC, timespec, tv_sec);
- OFFSET(TSPC64_TV_NSEC, timespec, tv_nsec);
OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec);
OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec);
-#else
- OFFSET(TVAL32_TV_SEC, timeval, tv_sec);
- OFFSET(TVAL32_TV_USEC, timeval, tv_usec);
- OFFSET(TSPC32_TV_SEC, timespec, tv_sec);
- OFFSET(TSPC32_TV_NSEC, timespec, tv_nsec);
-#endif
/* timeval/timezone offsets for use by vdso */
OFFSET(TZONE_TZ_MINWEST, timezone, tz_minuteswest);
OFFSET(TZONE_TZ_DSTTIME, timezone, tz_dsttime);
@@ -417,7 +435,10 @@
DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
+ DEFINE(CLOCK_MAX, CLOCK_TAI);
DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
+ DEFINE(EINVAL, EINVAL);
+ DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
#ifdef CONFIG_BUG
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
@@ -539,6 +560,8 @@
OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending);
OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request);
OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr);
+ OFFSET(VCPU_MMCRA, kvm_vcpu, arch.mmcra);
+ OFFSET(VCPU_MMCRS, kvm_vcpu, arch.mmcrs);
OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc);
OFFSET(VCPU_SPMC, kvm_vcpu, arch.spmc);
OFFSET(VCPU_SIAR, kvm_vcpu, arch.siar);
@@ -676,6 +699,9 @@
HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
+ HSTATE_FIELD(HSTATE_MMCR3, host_mmcr[7]);
+ HSTATE_FIELD(HSTATE_SIER2, host_mmcr[8]);
+ HSTATE_FIELD(HSTATE_SIER3, host_mmcr[9]);
HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
@@ -778,5 +804,9 @@
DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
#endif
+#ifdef CONFIG_XMON
+ DEFINE(BPT_SIZE, BPT_SIZE);
+#endif
+
return 0;
}
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 6dfceaa..1cffb5e 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -9,13 +9,13 @@
#include <linux/init.h>
#include <linux/export.h>
#include <linux/memblock.h>
+#include <linux/pgtable.h>
#include <asm/sections.h>
#include <asm/prom.h>
#include <asm/btext.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/udbg.h>
@@ -26,7 +26,7 @@
static void scrollscreen(void);
#endif
-#define __force_data __attribute__((__section__(".data")))
+#define __force_data __section(".data")
static int g_loc_X __force_data;
static int g_loc_Y __force_data;
@@ -95,19 +95,10 @@
boot_text_mapped = 0;
return;
}
- if (PVR_VER(mfspr(SPRN_PVR)) != 1) {
- /* 603, 604, G3, G4, ... */
- lowbits = addr & ~0xFF000000UL;
- addr &= 0xFF000000UL;
- disp_BAT[0] = vaddr | (BL_16M<<2) | 2;
- disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW);
- } else {
- /* 601 */
- lowbits = addr & ~0xFF800000UL;
- addr &= 0xFF800000UL;
- disp_BAT[0] = vaddr | (_PAGE_NO_CACHE | PP_RWXX) | 4;
- disp_BAT[1] = addr | BL_8M | 0x40;
- }
+ lowbits = addr & ~0xFF000000UL;
+ addr &= 0xFF000000UL;
+ disp_BAT[0] = vaddr | (BL_16M<<2) | 2;
+ disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW);
logicalDisplayBase = (void *) (vaddr + lowbits);
}
#endif
@@ -250,8 +241,10 @@
rc = btext_initialize(np);
printk("result: %d\n", rc);
}
- if (rc == 0)
+ if (rc == 0) {
+ of_node_put(np);
break;
+ }
}
return rc;
}
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 4703362..65ab9fc 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -7,6 +7,8 @@
* Author: Nathan Lynch
*/
+#define pr_fmt(fmt) "cacheinfo: " fmt
+
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/kernel.h>
@@ -166,7 +168,7 @@
list_for_each_entry(iter, &cache_list, list)
WARN_ONCE(iter->next_local == cache,
- "cache for %pOF(%s) refers to cache for %pOF(%s)\n",
+ "cache for %pOFP(%s) refers to cache for %pOFP(%s)\n",
iter->ofnode,
cache_type_string(iter),
cache->ofnode,
@@ -178,7 +180,7 @@
if (!cache)
return;
- pr_debug("freeing L%d %s cache for %pOF\n", cache->level,
+ pr_debug("freeing L%d %s cache for %pOFP\n", cache->level,
cache_type_string(cache), cache->ofnode);
release_cache_debugcheck(cache);
@@ -193,7 +195,7 @@
while (next) {
WARN_ONCE(cpumask_test_cpu(cpu, &next->shared_cpu_map),
- "CPU %i already accounted in %pOF(%s)\n",
+ "CPU %i already accounted in %pOFP(%s)\n",
cpu, next->ofnode,
cache_type_string(next));
cpumask_set_cpu(cpu, &next->shared_cpu_map);
@@ -352,7 +354,7 @@
static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
{
- pr_debug("creating L%d ucache for %pOF\n", level, node);
+ pr_debug("creating L%d ucache for %pOFP\n", level, node);
return new_cache(cache_is_unified_d(node), level, node);
}
@@ -362,7 +364,7 @@
{
struct cache *dcache, *icache;
- pr_debug("creating L%d dcache and icache for %pOF\n", level,
+ pr_debug("creating L%d dcache and icache for %pOFP\n", level,
node);
dcache = new_cache(CACHE_TYPE_DATA, level, node);
@@ -418,12 +420,27 @@
}
smaller->next_local = bigger;
+
+ /*
+ * The cache->next_local list sorts by level ascending:
+ * L1d -> L1i -> L2 -> L3 ...
+ */
+ WARN_ONCE((smaller->level == 1 && bigger->level > 2) ||
+ (smaller->level > 1 && bigger->level != smaller->level + 1),
+ "linking L%i cache %pOFP to L%i cache %pOFP; skipped a level?\n",
+ smaller->level, smaller->ofnode, bigger->level, bigger->ofnode);
}
static void do_subsidiary_caches_debugcheck(struct cache *cache)
{
- WARN_ON_ONCE(cache->level != 1);
- WARN_ON_ONCE(!of_node_is_type(cache->ofnode, "cpu"));
+ WARN_ONCE(cache->level != 1,
+ "instantiating cache chain from L%d %s cache for "
+ "%pOFP instead of an L1\n", cache->level,
+ cache_type_string(cache), cache->ofnode);
+ WARN_ONCE(!of_node_is_type(cache->ofnode, "cpu"),
+ "instantiating cache chain from node %pOFP of type '%s' "
+ "instead of a cpu node\n", cache->ofnode,
+ of_node_get_device_type(cache->ofnode));
}
static void do_subsidiary_caches(struct cache *cache)
@@ -647,12 +664,13 @@
return &cache->shared_cpu_map;
}
-static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+static ssize_t
+show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
{
struct cache_index_dir *index;
struct cache *cache;
const struct cpumask *mask;
- int ret, cpu;
+ int cpu;
index = kobj_to_cache_index_dir(k);
cache = index->cache;
@@ -664,16 +682,25 @@
mask = &cache->shared_cpu_map;
}
- ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n",
- cpumask_pr_args(mask));
- buf[ret++] = '\n';
- buf[ret] = '\0';
- return ret;
+ return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, false);
+}
+
+static ssize_t shared_cpu_list_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, true);
}
static struct kobj_attribute cache_shared_cpu_map_attr =
__ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL);
+static struct kobj_attribute cache_shared_cpu_list_attr =
+ __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL);
+
/* Attributes which should always be created -- the kobject/sysfs core
* does this automatically via kobj_type->default_attrs. This is the
* minimum data required to uniquely identify a cache.
@@ -682,6 +709,7 @@
&cache_type_attr.attr,
&cache_level_attr.attr,
&cache_shared_cpu_map_attr.attr,
+ &cache_shared_cpu_list_attr.attr,
NULL,
};
@@ -733,13 +761,13 @@
rc = attr->show(&dir->kobj, attr, buf);
if (rc <= 0) {
pr_debug("not creating %s attribute for "
- "%pOF(%s) (rc = %zd)\n",
+ "%pOFP(%s) (rc = %zd)\n",
attr->attr.name, cache->ofnode,
cache_type, rc);
continue;
}
if (sysfs_create_file(&dir->kobj, &attr->attr))
- pr_debug("could not create %s attribute for %pOF(%s)\n",
+ pr_debug("could not create %s attribute for %pOFP(%s)\n",
attr->attr.name, cache->ofnode, cache_type);
}
@@ -855,7 +883,7 @@
struct cache *next = cache->next_local;
WARN_ONCE(!cpumask_test_cpu(cpu, &cache->shared_cpu_map),
- "CPU %i not accounted in %pOF(%s)\n",
+ "CPU %i not accounted in %pOFP(%s)\n",
cpu, cache->ofnode,
cache_type_string(cache));
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f6517f6..f8b5ff6 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -288,6 +288,7 @@
mtmsr r10
isync
blr
+_ASM_NOKPROBE_SYMBOL(__init_fpu_registers)
/* Definitions for the table use to save CPU states */
@@ -483,4 +484,5 @@
1:
mtcr r7
blr
+_ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 2b4f3ec..1d30878 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -231,7 +231,7 @@
blr
#endif
-/* flush L1 date cache, it can apply to e500v2, e500mc and e5500 */
+/* flush L1 data cache, it can apply to e500v2, e500mc and e5500 */
_GLOBAL(flush_dcache_L1)
mfmsr r10
wrteei 0
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
deleted file mode 100644
index f91ecb1..0000000
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ /dev/null
@@ -1,219 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This file contains low level CPU setup functions.
- * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- */
-
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cache.h>
-#include <asm/book3s/64/mmu-hash.h>
-
-/* Entry: r3 = crap, r4 = ptr to cputable entry
- *
- * Note that we can be called twice for pseudo-PVRs
- */
-_GLOBAL(__setup_cpu_power7)
- mflr r11
- bl __init_hvmode_206
- mtlr r11
- beqlr
- li r0,0
- mtspr SPRN_LPID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
- bl __init_LPCR_ISA206
- mtlr r11
- blr
-
-_GLOBAL(__restore_cpu_power7)
- mflr r11
- mfmsr r3
- rldicl. r0,r3,4,63
- beqlr
- li r0,0
- mtspr SPRN_LPID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
- bl __init_LPCR_ISA206
- mtlr r11
- blr
-
-_GLOBAL(__setup_cpu_power8)
- mflr r11
- bl __init_FSCR
- bl __init_PMU
- bl __init_PMU_ISA207
- bl __init_hvmode_206
- mtlr r11
- beqlr
- li r0,0
- mtspr SPRN_LPID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- ori r3, r3, LPCR_PECEDH
- li r4,0 /* LPES = 0 */
- bl __init_LPCR_ISA206
- bl __init_HFSCR
- bl __init_PMU_HV
- bl __init_PMU_HV_ISA207
- mtlr r11
- blr
-
-_GLOBAL(__restore_cpu_power8)
- mflr r11
- bl __init_FSCR
- bl __init_PMU
- bl __init_PMU_ISA207
- mfmsr r3
- rldicl. r0,r3,4,63
- mtlr r11
- beqlr
- li r0,0
- mtspr SPRN_LPID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- ori r3, r3, LPCR_PECEDH
- li r4,0 /* LPES = 0 */
- bl __init_LPCR_ISA206
- bl __init_HFSCR
- bl __init_PMU_HV
- bl __init_PMU_HV_ISA207
- mtlr r11
- blr
-
-_GLOBAL(__setup_cpu_power9)
- mflr r11
- bl __init_FSCR
- bl __init_PMU
- bl __init_hvmode_206
- mtlr r11
- beqlr
- li r0,0
- mtspr SPRN_PSSCR,r0
- mtspr SPRN_LPID,r0
- mtspr SPRN_PID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
- or r3, r3, r4
- LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
- andc r3, r3, r4
- li r4,0 /* LPES = 0 */
- bl __init_LPCR_ISA300
- bl __init_HFSCR
- bl __init_PMU_HV
- mtlr r11
- blr
-
-_GLOBAL(__restore_cpu_power9)
- mflr r11
- bl __init_FSCR
- bl __init_PMU
- mfmsr r3
- rldicl. r0,r3,4,63
- mtlr r11
- beqlr
- li r0,0
- mtspr SPRN_PSSCR,r0
- mtspr SPRN_LPID,r0
- mtspr SPRN_PID,r0
- LOAD_REG_IMMEDIATE(r0, PCR_MASK)
- mtspr SPRN_PCR,r0
- mfspr r3,SPRN_LPCR
- LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
- or r3, r3, r4
- LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
- andc r3, r3, r4
- li r4,0 /* LPES = 0 */
- bl __init_LPCR_ISA300
- bl __init_HFSCR
- bl __init_PMU_HV
- mtlr r11
- blr
-
-__init_hvmode_206:
- /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */
- mfmsr r3
- rldicl. r0,r3,4,63
- bnelr
- ld r5,CPU_SPEC_FEATURES(r4)
- LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST)
- andc r5,r5,r6
- std r5,CPU_SPEC_FEATURES(r4)
- blr
-
-__init_LPCR_ISA206:
- /* Setup a sane LPCR:
- * Called with initial LPCR in R3 and desired LPES 2-bit value in R4
- *
- * LPES = 0b01 (HSRR0/1 used for 0x500)
- * PECE = 0b111
- * DPFD = 4
- * HDICE = 0
- * VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
- * VRMASD = 0b10000 (L=1, LP=00)
- *
- * Other bits untouched for now
- */
- li r5,0x10
- rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
-
- /* POWER9 has no VRMASD */
-__init_LPCR_ISA300:
- rldimi r3,r4, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
- ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
- li r5,4
- rldimi r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3
- clrrdi r3,r3,1 /* clear HDICE */
- li r5,4
- rldimi r3,r5, LPCR_VC_SH, 0
- mtspr SPRN_LPCR,r3
- isync
- blr
-
-__init_FSCR:
- mfspr r3,SPRN_FSCR
- ori r3,r3,FSCR_TAR|FSCR_EBB
- mtspr SPRN_FSCR,r3
- blr
-
-__init_HFSCR:
- mfspr r3,SPRN_HFSCR
- ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\
- HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP
- mtspr SPRN_HFSCR,r3
- blr
-
-__init_PMU_HV:
- li r5,0
- mtspr SPRN_MMCRC,r5
- blr
-
-__init_PMU_HV_ISA207:
- li r5,0
- mtspr SPRN_MMCRH,r5
- blr
-
-__init_PMU:
- li r5,0
- mtspr SPRN_MMCRA,r5
- mtspr SPRN_MMCR0,r5
- mtspr SPRN_MMCR1,r5
- mtspr SPRN_MMCR2,r5
- blr
-
-__init_PMU_ISA207:
- li r5,0
- mtspr SPRN_MMCRS,r5
- blr
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
new file mode 100644
index 0000000..3cca88e
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2020, Jordan Niethe, IBM Corporation.
+ *
+ * This file contains low level CPU setup functions.
+ * Originally written in assembly by Benjamin Herrenschmidt & various other
+ * authors.
+ */
+
+#include <asm/reg.h>
+#include <asm/synch.h>
+#include <linux/bitops.h>
+#include <asm/cputable.h>
+#include <asm/cpu_setup_power.h>
+
+/* Disable CPU_FTR_HVMODE and return false if MSR:HV is not set */
+static bool init_hvmode_206(struct cpu_spec *t)
+{
+ u64 msr;
+
+ msr = mfmsr();
+ if (msr & MSR_HV)
+ return true;
+
+ t->cpu_features &= ~(CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST);
+ return false;
+}
+
+static void init_LPCR_ISA300(u64 lpcr, u64 lpes)
+{
+ /* POWER9 has no VRMASD */
+ lpcr |= (lpes << LPCR_LPES_SH) & LPCR_LPES;
+ lpcr |= LPCR_PECE0|LPCR_PECE1|LPCR_PECE2;
+ lpcr |= (4ull << LPCR_DPFD_SH) & LPCR_DPFD;
+ lpcr &= ~LPCR_HDICE; /* clear HDICE */
+ lpcr |= (4ull << LPCR_VC_SH);
+ mtspr(SPRN_LPCR, lpcr);
+ isync();
+}
+
+/*
+ * Setup a sane LPCR:
+ * Called with initial LPCR and desired LPES 2-bit value
+ *
+ * LPES = 0b01 (HSRR0/1 used for 0x500)
+ * PECE = 0b111
+ * DPFD = 4
+ * HDICE = 0
+ * VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
+ * VRMASD = 0b10000 (L=1, LP=00)
+ *
+ * Other bits untouched for now
+ */
+static void init_LPCR_ISA206(u64 lpcr, u64 lpes)
+{
+ lpcr |= (0x10ull << LPCR_VRMASD_SH) & LPCR_VRMASD;
+ init_LPCR_ISA300(lpcr, lpes);
+}
+
+static void init_FSCR(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_TAR|FSCR_EBB;
+ mtspr(SPRN_FSCR, fscr);
+}
+
+static void init_FSCR_power9(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_SCV;
+ mtspr(SPRN_FSCR, fscr);
+ init_FSCR();
+}
+
+static void init_FSCR_power10(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_PREFIX;
+ mtspr(SPRN_FSCR, fscr);
+ init_FSCR_power9();
+}
+
+static void init_HFSCR(void)
+{
+ u64 hfscr;
+
+ hfscr = mfspr(SPRN_HFSCR);
+ hfscr |= HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|HFSCR_DSCR|\
+ HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP;
+ mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_PMU_HV(void)
+{
+ mtspr(SPRN_MMCRC, 0);
+}
+
+static void init_PMU_HV_ISA207(void)
+{
+ mtspr(SPRN_MMCRH, 0);
+}
+
+static void init_PMU(void)
+{
+ mtspr(SPRN_MMCRA, 0);
+ mtspr(SPRN_MMCR0, 0);
+ mtspr(SPRN_MMCR1, 0);
+ mtspr(SPRN_MMCR2, 0);
+}
+
+static void init_PMU_ISA207(void)
+{
+ mtspr(SPRN_MMCRS, 0);
+}
+
+static void init_PMU_ISA31(void)
+{
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+}
+
+/*
+ * Note that we can be called twice of pseudo-PVRs.
+ * The parameter offset is not used.
+ */
+
+void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t)
+{
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
+}
+
+void __restore_cpu_power7(void)
+{
+ u64 msr;
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
+}
+
+void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR();
+ init_PMU();
+ init_PMU_ISA207();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
+ init_HFSCR();
+ init_PMU_HV();
+ init_PMU_HV_ISA207();
+}
+
+void __restore_cpu_power8(void)
+{
+ u64 msr;
+
+ init_FSCR();
+ init_PMU();
+ init_PMU_ISA207();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
+ init_HFSCR();
+ init_PMU_HV();
+ init_PMU_HV_ISA207();
+}
+
+void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR_power9();
+ init_PMU();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __restore_cpu_power9(void)
+{
+ u64 msr;
+
+ init_FSCR_power9();
+ init_PMU();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR_power10();
+ init_PMU();
+ init_PMU_ISA31();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __restore_cpu_power10(void)
+{
+ u64 msr;
+
+ init_FSCR_power10();
+ init_PMU();
+ init_PMU_ISA31();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 245be4f..8fdb40e 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -16,6 +16,7 @@
#include <asm/oprofile_impl.h>
#include <asm/cputable.h>
#include <asm/prom.h> /* for PTRRELOC on ARCH=ppc */
+#include <asm/mce.h>
#include <asm/mmu.h>
#include <asm/setup.h>
@@ -59,17 +60,12 @@
extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec);
#endif /* CONFIG_PPC32 */
#ifdef CONFIG_PPC64
+#include <asm/cpu_setup_power.h>
extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec);
extern void __restore_cpu_pa6t(void);
extern void __restore_cpu_ppc970(void);
-extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec);
-extern void __restore_cpu_power7(void);
-extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
-extern void __restore_cpu_power8(void);
-extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec);
-extern void __restore_cpu_power9(void);
extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
@@ -118,7 +114,19 @@
#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
PPC_FEATURE2_ARCH_3_00 | \
PPC_FEATURE2_HAS_IEEE128 | \
- PPC_FEATURE2_DARN )
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV)
+#define COMMON_USER_POWER10 COMMON_USER_POWER9
+#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \
+ PPC_FEATURE2_MMA | \
+ PPC_FEATURE2_ARCH_3_00 | \
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV | \
+ PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
#ifdef CONFIG_PPC_BOOK3E_64
#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
@@ -367,6 +375,22 @@
.cpu_restore = __restore_cpu_power9,
.platform = "power9",
},
+ { /* 3.1-compliant processor, i.e. Power10 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000006,
+ .cpu_name = "POWER10 (architected)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .oprofile_cpu_type = "ppc64/ibm-compat-v1",
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .platform = "power10",
+ },
{ /* Power7 */
.pvr_mask = 0xffff0000,
.pvr_value = 0x003f0000,
@@ -519,6 +543,25 @@
.machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
+ { /* Power10 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00800000,
+ .cpu_name = "POWER10 (raw)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .oprofile_cpu_type = "ppc64/power10",
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .machine_check_early = __machine_check_early_realmode_p10,
+ .platform = "power10",
+ },
{ /* Cell Broadband Engine */
.pvr_mask = 0xffff0000,
.pvr_value = 0x00700000,
@@ -569,21 +612,6 @@
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_PPC32
-#ifdef CONFIG_PPC_BOOK3S_601
- { /* 601 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00010000,
- .cpu_name = "601",
- .cpu_features = CPU_FTRS_PPC601,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR |
- PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_generic,
- .platform = "ppc601",
- },
-#endif /* CONFIG_PPC_BOOK3S_601 */
#ifdef CONFIG_PPC_BOOK3S_6xx
{ /* 603 */
.pvr_mask = 0xffff0000,
@@ -1232,69 +1260,6 @@
},
#endif /* CONFIG_PPC_8xx */
#ifdef CONFIG_40x
- { /* 403GC */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x00200200,
- .cpu_name = "403GC",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 16,
- .dcache_bsize = 16,
- .machine_check = machine_check_4xx,
- .platform = "ppc403",
- },
- { /* 403GCX */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x00201400,
- .cpu_name = "403GCX",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 16,
- .dcache_bsize = 16,
- .machine_check = machine_check_4xx,
- .platform = "ppc403",
- },
- { /* 403G ?? */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00200000,
- .cpu_name = "403G ??",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 16,
- .dcache_bsize = 16,
- .machine_check = machine_check_4xx,
- .platform = "ppc403",
- },
- { /* 405GP */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x40110000,
- .cpu_name = "405GP",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* STB 03xxx */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x40130000,
- .cpu_name = "STB03xxx",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
{ /* STB 04xxx */
.pvr_mask = 0xffff0000,
.pvr_value = 0x41810000,
@@ -1385,32 +1350,6 @@
.machine_check = machine_check_4xx,
.platform = "ppc405",
},
- { /* Xilinx Virtex-II Pro */
- .pvr_mask = 0xfffff000,
- .pvr_value = 0x20010000,
- .cpu_name = "Virtex-II Pro",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* Xilinx Virtex-4 FX */
- .pvr_mask = 0xfffff000,
- .pvr_value = 0x20011000,
- .cpu_name = "Virtex-4 FX",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
{ /* 405EP */
.pvr_mask = 0xffff0000,
.pvr_value = 0x51210000,
@@ -1800,19 +1739,6 @@
.machine_check = machine_check_440A,
.platform = "ppc440",
},
- { /* 440 in Xilinx Virtex-5 FXT */
- .pvr_mask = 0xfffffff0,
- .pvr_value = 0x7ff21910,
- .cpu_name = "440 in Virtex-5 FXT",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440x5,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
{ /* 460EX */
.pvr_mask = 0xffff0006,
.pvr_value = 0x13020002,
@@ -2198,7 +2124,6 @@
*/
if (old.oprofile_cpu_type != NULL) {
t->oprofile_cpu_type = old.oprofile_cpu_type;
- t->oprofile_type = old.oprofile_type;
t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
}
}
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
deleted file mode 100644
index d488311..0000000
--- a/arch/powerpc/kernel/crash.c
+++ /dev/null
@@ -1,374 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Architecture specific (PPC64) functions for kexec based crash dumps.
- *
- * Copyright (C) 2005, IBM Corp.
- *
- * Created by: Haren Myneni
- */
-
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/reboot.h>
-#include <linux/kexec.h>
-#include <linux/export.h>
-#include <linux/crash_dump.h>
-#include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/types.h>
-
-#include <asm/processor.h>
-#include <asm/machdep.h>
-#include <asm/kexec.h>
-#include <asm/prom.h>
-#include <asm/smp.h>
-#include <asm/setjmp.h>
-#include <asm/debug.h>
-
-/*
- * The primary CPU waits a while for all secondary CPUs to enter. This is to
- * avoid sending an IPI if the secondary CPUs are entering
- * crash_kexec_secondary on their own (eg via a system reset).
- *
- * The secondary timeout has to be longer than the primary. Both timeouts are
- * in milliseconds.
- */
-#define PRIMARY_TIMEOUT 500
-#define SECONDARY_TIMEOUT 1000
-
-#define IPI_TIMEOUT 10000
-#define REAL_MODE_TIMEOUT 10000
-
-static int time_to_dump;
-/*
- * crash_wake_offline should be set to 1 by platforms that intend to wake
- * up offline cpus prior to jumping to a kdump kernel. Currently powernv
- * sets it to 1, since we want to avoid things from happening when an
- * offline CPU wakes up due to something like an HMI (malfunction error),
- * which propagates to all threads.
- */
-int crash_wake_offline;
-
-#define CRASH_HANDLER_MAX 3
-/* List of shutdown handles */
-static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX];
-static DEFINE_SPINLOCK(crash_handlers_lock);
-
-static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
-static int crash_shutdown_cpu = -1;
-
-static int handle_fault(struct pt_regs *regs)
-{
- if (crash_shutdown_cpu == smp_processor_id())
- longjmp(crash_shutdown_buf, 1);
- return 0;
-}
-
-#ifdef CONFIG_SMP
-
-static atomic_t cpus_in_crash;
-void crash_ipi_callback(struct pt_regs *regs)
-{
- static cpumask_t cpus_state_saved = CPU_MASK_NONE;
-
- int cpu = smp_processor_id();
-
- hard_irq_disable();
- if (!cpumask_test_cpu(cpu, &cpus_state_saved)) {
- crash_save_cpu(regs, cpu);
- cpumask_set_cpu(cpu, &cpus_state_saved);
- }
-
- atomic_inc(&cpus_in_crash);
- smp_mb__after_atomic();
-
- /*
- * Starting the kdump boot.
- * This barrier is needed to make sure that all CPUs are stopped.
- */
- while (!time_to_dump)
- cpu_relax();
-
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(1, 1);
-
-#ifdef CONFIG_PPC64
- kexec_smp_wait();
-#else
- for (;;); /* FIXME */
-#endif
-
- /* NOTREACHED */
-}
-
-static void crash_kexec_prepare_cpus(int cpu)
-{
- unsigned int msecs;
- unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
- int tries = 0;
- int (*old_handler)(struct pt_regs *regs);
-
- printk(KERN_EMERG "Sending IPI to other CPUs\n");
-
- if (crash_wake_offline)
- ncpus = num_present_cpus() - 1;
-
- crash_send_ipi(crash_ipi_callback);
- smp_wmb();
-
-again:
- /*
- * FIXME: Until we will have the way to stop other CPUs reliably,
- * the crash CPU will send an IPI and wait for other CPUs to
- * respond.
- */
- msecs = IPI_TIMEOUT;
- while ((atomic_read(&cpus_in_crash) < ncpus) && (--msecs > 0))
- mdelay(1);
-
- /* Would it be better to replace the trap vector here? */
-
- if (atomic_read(&cpus_in_crash) >= ncpus) {
- printk(KERN_EMERG "IPI complete\n");
- return;
- }
-
- printk(KERN_EMERG "ERROR: %d cpu(s) not responding\n",
- ncpus - atomic_read(&cpus_in_crash));
-
- /*
- * If we have a panic timeout set then we can't wait indefinitely
- * for someone to activate system reset. We also give up on the
- * second time through if system reset fail to work.
- */
- if ((panic_timeout > 0) || (tries > 0))
- return;
-
- /*
- * A system reset will cause all CPUs to take an 0x100 exception.
- * The primary CPU returns here via setjmp, and the secondary
- * CPUs reexecute the crash_kexec_secondary path.
- */
- old_handler = __debugger;
- __debugger = handle_fault;
- crash_shutdown_cpu = smp_processor_id();
-
- if (setjmp(crash_shutdown_buf) == 0) {
- printk(KERN_EMERG "Activate system reset (dumprestart) "
- "to stop other cpu(s)\n");
-
- /*
- * A system reset will force all CPUs to execute the
- * crash code again. We need to reset cpus_in_crash so we
- * wait for everyone to do this.
- */
- atomic_set(&cpus_in_crash, 0);
- smp_mb();
-
- while (atomic_read(&cpus_in_crash) < ncpus)
- cpu_relax();
- }
-
- crash_shutdown_cpu = -1;
- __debugger = old_handler;
-
- tries++;
- goto again;
-}
-
-/*
- * This function will be called by secondary cpus.
- */
-void crash_kexec_secondary(struct pt_regs *regs)
-{
- unsigned long flags;
- int msecs = SECONDARY_TIMEOUT;
-
- local_irq_save(flags);
-
- /* Wait for the primary crash CPU to signal its progress */
- while (crashing_cpu < 0) {
- if (--msecs < 0) {
- /* No response, kdump image may not have been loaded */
- local_irq_restore(flags);
- return;
- }
-
- mdelay(1);
- }
-
- crash_ipi_callback(regs);
-}
-
-#else /* ! CONFIG_SMP */
-
-static void crash_kexec_prepare_cpus(int cpu)
-{
- /*
- * move the secondaries to us so that we can copy
- * the new kernel 0-0x100 safely
- *
- * do this if kexec in setup.c ?
- */
-#ifdef CONFIG_PPC64
- smp_release_cpus();
-#else
- /* FIXME */
-#endif
-}
-
-void crash_kexec_secondary(struct pt_regs *regs)
-{
-}
-#endif /* CONFIG_SMP */
-
-/* wait for all the CPUs to hit real mode but timeout if they don't come in */
-#if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
-static void __maybe_unused crash_kexec_wait_realmode(int cpu)
-{
- unsigned int msecs;
- int i;
-
- msecs = REAL_MODE_TIMEOUT;
- for (i=0; i < nr_cpu_ids && msecs > 0; i++) {
- if (i == cpu)
- continue;
-
- while (paca_ptrs[i]->kexec_state < KEXEC_STATE_REAL_MODE) {
- barrier();
- if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0))
- break;
- msecs--;
- mdelay(1);
- }
- }
- mb();
-}
-#else
-static inline void crash_kexec_wait_realmode(int cpu) {}
-#endif /* CONFIG_SMP && CONFIG_PPC64 */
-
-/*
- * Register a function to be called on shutdown. Only use this if you
- * can't reset your device in the second kernel.
- */
-int crash_shutdown_register(crash_shutdown_t handler)
-{
- unsigned int i, rc;
-
- spin_lock(&crash_handlers_lock);
- for (i = 0 ; i < CRASH_HANDLER_MAX; i++)
- if (!crash_shutdown_handles[i]) {
- /* Insert handle at first empty entry */
- crash_shutdown_handles[i] = handler;
- rc = 0;
- break;
- }
-
- if (i == CRASH_HANDLER_MAX) {
- printk(KERN_ERR "Crash shutdown handles full, "
- "not registered.\n");
- rc = 1;
- }
-
- spin_unlock(&crash_handlers_lock);
- return rc;
-}
-EXPORT_SYMBOL(crash_shutdown_register);
-
-int crash_shutdown_unregister(crash_shutdown_t handler)
-{
- unsigned int i, rc;
-
- spin_lock(&crash_handlers_lock);
- for (i = 0 ; i < CRASH_HANDLER_MAX; i++)
- if (crash_shutdown_handles[i] == handler)
- break;
-
- if (i == CRASH_HANDLER_MAX) {
- printk(KERN_ERR "Crash shutdown handle not found\n");
- rc = 1;
- } else {
- /* Shift handles down */
- for (; i < (CRASH_HANDLER_MAX - 1); i++)
- crash_shutdown_handles[i] =
- crash_shutdown_handles[i+1];
- /*
- * Reset last entry to NULL now that it has been shifted down,
- * this will allow new handles to be added here.
- */
- crash_shutdown_handles[i] = NULL;
- rc = 0;
- }
-
- spin_unlock(&crash_handlers_lock);
- return rc;
-}
-EXPORT_SYMBOL(crash_shutdown_unregister);
-
-void default_machine_crash_shutdown(struct pt_regs *regs)
-{
- unsigned int i;
- int (*old_handler)(struct pt_regs *regs);
-
- /*
- * This function is only called after the system
- * has panicked or is otherwise in a critical state.
- * The minimum amount of code to allow a kexec'd kernel
- * to run successfully needs to happen here.
- *
- * In practice this means stopping other cpus in
- * an SMP system.
- * The kernel is broken so disable interrupts.
- */
- hard_irq_disable();
-
- /*
- * Make a note of crashing cpu. Will be used in machine_kexec
- * such that another IPI will not be sent.
- */
- crashing_cpu = smp_processor_id();
-
- /*
- * If we came in via system reset, wait a while for the secondary
- * CPUs to enter.
- */
- if (TRAP(regs) == 0x100)
- mdelay(PRIMARY_TIMEOUT);
-
- crash_kexec_prepare_cpus(crashing_cpu);
-
- crash_save_cpu(regs, crashing_cpu);
-
- time_to_dump = 1;
-
- crash_kexec_wait_realmode(crashing_cpu);
-
- machine_kexec_mask_interrupts();
-
- /*
- * Call registered shutdown routines safely. Swap out
- * __debugger_fault_handler, and replace on exit.
- */
- old_handler = __debugger_fault_handler;
- __debugger_fault_handler = handle_fault;
- crash_shutdown_cpu = smp_processor_id();
- for (i = 0; i < CRASH_HANDLER_MAX && crash_shutdown_handles[i]; i++) {
- if (setjmp(crash_shutdown_buf) == 0) {
- /*
- * Insert syncs and delay to ensure
- * instructions in the dangerous region don't
- * leak away from this protected region.
- */
- asm volatile("sync; isync");
- /* dangerous region */
- crash_shutdown_handles[i]();
- asm volatile("sync; isync");
- }
- }
- crash_shutdown_cpu = -1;
- __debugger_fault_handler = old_handler;
-
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(1, 0);
-}
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 05745dd..735e893 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -18,6 +18,7 @@
#include <asm/firmware.h>
#include <linux/uaccess.h>
#include <asm/rtas.h>
+#include <asm/inst.h>
#ifdef DEBUG
#include <asm/udbg.h>
@@ -34,7 +35,7 @@
static void __init create_trampoline(unsigned long addr)
{
- unsigned int *p = (unsigned int *)addr;
+ struct ppc_inst *p = (struct ppc_inst *)addr;
/* The maximum range of a single instruction branch, is the current
* instruction's address + (32 MB - 4) bytes. For the trampoline we
@@ -44,8 +45,8 @@
* branch to "addr" we jump to ("addr" + 32 MB). Although it requires
* two instructions it doesn't require any registers.
*/
- patch_instruction(p, PPC_INST_NOP);
- patch_branch(++p, addr + PHYSICAL_START, 0);
+ patch_instruction(p, ppc_inst(PPC_INST_NOP));
+ patch_branch((void *)p + 4, addr + PHYSICAL_START, 0);
}
void __init setup_kdump_trampoline(void)
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
index 5f66b95..cdc2dcc 100644
--- a/arch/powerpc/kernel/dawr.c
+++ b/arch/powerpc/kernel/dawr.c
@@ -16,7 +16,7 @@
bool dawr_force_enable;
EXPORT_SYMBOL_GPL(dawr_force_enable);
-int set_dawr(struct arch_hw_breakpoint *brk)
+int set_dawr(int nr, struct arch_hw_breakpoint *brk)
{
unsigned long dawr, dawrx, mrd;
@@ -30,37 +30,46 @@
* DAWR length is stored in field MDR bits 48:53. Matches range in
* doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
* 0b111111=64DW.
- * brk->len is in bytes.
+ * brk->hw_len is in bytes.
* This aligns up to double word size, shifts and does the bias.
*/
- mrd = ((brk->len + 7) >> 3) - 1;
+ mrd = ((brk->hw_len + 7) >> 3) - 1;
dawrx |= (mrd & 0x3f) << (63 - 53);
if (ppc_md.set_dawr)
- return ppc_md.set_dawr(dawr, dawrx);
+ return ppc_md.set_dawr(nr, dawr, dawrx);
- mtspr(SPRN_DAWR, dawr);
- mtspr(SPRN_DAWRX, dawrx);
+ if (nr == 0) {
+ mtspr(SPRN_DAWR0, dawr);
+ mtspr(SPRN_DAWRX0, dawrx);
+ } else {
+ mtspr(SPRN_DAWR1, dawr);
+ mtspr(SPRN_DAWRX1, dawrx);
+ }
return 0;
}
-static void set_dawr_cb(void *info)
+static void disable_dawrs_cb(void *info)
{
- set_dawr(info);
+ struct arch_hw_breakpoint null_brk = {0};
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_dawr(i, &null_brk);
}
static ssize_t dawr_write_file_bool(struct file *file,
const char __user *user_buf,
size_t count, loff_t *ppos)
{
- struct arch_hw_breakpoint null_brk = {0, 0, 0};
+ struct arch_hw_breakpoint null_brk = {0};
size_t rc;
/* Send error to user if they hypervisor won't allow us to write DAWR */
if (!dawr_force_enable &&
firmware_has_feature(FW_FEATURE_LPAR) &&
- set_dawr(&null_brk) != H_SUCCESS)
+ set_dawr(0, &null_brk) != H_SUCCESS)
return -ENODEV;
rc = debugfs_write_file_bool(file, user_buf, count, ppos);
@@ -69,7 +78,7 @@
/* If we are clearing, make sure all CPUs have the DAWR cleared */
if (!dawr_force_enable)
- smp_call_function(set_dawr_cb, &null_brk, 0);
+ smp_call_function(disable_dawrs_cb, NULL, 0);
return rc;
}
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f17ff12..52680cf 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -18,61 +18,6 @@
#ifdef CONFIG_SMP
-/*
- * Doorbells must only be used if CPU_FTR_DBELL is available.
- * msgsnd is used in HV, and msgsndp is used in !HV.
- *
- * These should be used by platform code that is aware of restrictions.
- * Other arch code should use ->cause_ipi.
- *
- * doorbell_global_ipi() sends a dbell to any target CPU.
- * Must be used only by architectures that address msgsnd target
- * by PIR/get_hard_smp_processor_id.
- */
-void doorbell_global_ipi(int cpu)
-{
- u32 tag = get_hard_smp_processor_id(cpu);
-
- kvmppc_set_host_ipi(cpu);
- /* Order previous accesses vs. msgsnd, which is treated as a store */
- ppc_msgsnd_sync();
- ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
-}
-
-/*
- * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
- * Must be used only by architectures that address msgsnd target
- * by TIR/cpu_thread_in_core.
- */
-void doorbell_core_ipi(int cpu)
-{
- u32 tag = cpu_thread_in_core(cpu);
-
- kvmppc_set_host_ipi(cpu);
- /* Order previous accesses vs. msgsnd, which is treated as a store */
- ppc_msgsnd_sync();
- ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
-}
-
-/*
- * Attempt to cause a core doorbell if destination is on the same core.
- * Returns 1 on success, 0 on failure.
- */
-int doorbell_try_core_ipi(int cpu)
-{
- int this_cpu = get_cpu();
- int ret = 0;
-
- if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
- doorbell_core_ipi(cpu);
- ret = 1;
- }
-
- put_cpu();
-
- return ret;
-}
-
void doorbell_exception(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index f4cb2c5..9ac0651 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -14,23 +14,6 @@
* Generic iommu implementation
*/
-/*
- * The coherent mask may be smaller than the real mask, check if we can
- * really use a direct window.
- */
-static inline bool dma_iommu_alloc_bypass(struct device *dev)
-{
- return dev->archdata.iommu_bypass && !iommu_fixed_is_weak &&
- dma_direct_supported(dev, dev->coherent_dma_mask);
-}
-
-static inline bool dma_iommu_map_bypass(struct device *dev,
- unsigned long attrs)
-{
- return dev->archdata.iommu_bypass &&
- (!iommu_fixed_is_weak || (attrs & DMA_ATTR_WEAK_ORDERING));
-}
-
/* Allocates a contiguous real buffer and creates mappings over it.
* Returns the virtual address of the buffer and sets dma_handle
* to the dma address (mapping) of the first page.
@@ -39,8 +22,6 @@
dma_addr_t *dma_handle, gfp_t flag,
unsigned long attrs)
{
- if (dma_iommu_alloc_bypass(dev))
- return dma_direct_alloc(dev, size, dma_handle, flag, attrs);
return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
dma_handle, dev->coherent_dma_mask, flag,
dev_to_node(dev));
@@ -50,11 +31,7 @@
void *vaddr, dma_addr_t dma_handle,
unsigned long attrs)
{
- if (dma_iommu_alloc_bypass(dev))
- dma_direct_free(dev, size, vaddr, dma_handle, attrs);
- else
- iommu_free_coherent(get_iommu_table_base(dev), size, vaddr,
- dma_handle);
+ iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
}
/* Creates TCEs for a user provided buffer. The user buffer must be
@@ -67,9 +44,6 @@
enum dma_data_direction direction,
unsigned long attrs)
{
- if (dma_iommu_map_bypass(dev, attrs))
- return dma_direct_map_page(dev, page, offset, size, direction,
- attrs);
return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
size, dma_get_mask(dev), direction, attrs);
}
@@ -79,11 +53,8 @@
size_t size, enum dma_data_direction direction,
unsigned long attrs)
{
- if (!dma_iommu_map_bypass(dev, attrs))
- iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
- direction, attrs);
- else
- dma_direct_unmap_page(dev, dma_handle, size, direction, attrs);
+ iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
+ attrs);
}
@@ -91,8 +62,6 @@
int nelems, enum dma_data_direction direction,
unsigned long attrs)
{
- if (dma_iommu_map_bypass(dev, attrs))
- return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
dma_get_mask(dev), direction, attrs);
}
@@ -101,11 +70,8 @@
int nelems, enum dma_data_direction direction,
unsigned long attrs)
{
- if (!dma_iommu_map_bypass(dev, attrs))
- ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+ ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
direction, attrs);
- else
- dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs);
}
static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
@@ -113,8 +79,9 @@
struct pci_dev *pdev = to_pci_dev(dev);
struct pci_controller *phb = pci_bus_to_host(pdev->bus);
- return phb->controller_ops.iommu_bypass_supported &&
- phb->controller_ops.iommu_bypass_supported(pdev, mask);
+ if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+ return false;
+ return phb->controller_ops.iommu_bypass_supported(pdev, mask);
}
/* We support DMA to/from any memory page via the iommu */
@@ -123,7 +90,7 @@
struct iommu_table *tbl = get_iommu_table_base(dev);
if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
- dev->archdata.iommu_bypass = true;
+ dev->dma_ops_bypass = true;
dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
return 1;
}
@@ -141,7 +108,7 @@
}
dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
- dev->archdata.iommu_bypass = false;
+ dev->dma_ops_bypass = false;
return 1;
}
@@ -150,16 +117,18 @@
struct iommu_table *tbl = get_iommu_table_base(dev);
u64 mask;
- if (!tbl)
- return 0;
-
if (dev_is_pci(dev)) {
u64 bypass_mask = dma_direct_get_required_mask(dev);
- if (dma_iommu_bypass_supported(dev, bypass_mask))
+ if (dma_iommu_dma_supported(dev, bypass_mask)) {
+ dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask);
return bypass_mask;
+ }
}
+ if (!tbl)
+ return 0;
+
mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
tbl->it_page_shift - 1);
mask += mask - 1;
@@ -167,34 +136,6 @@
return mask;
}
-static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
- if (dma_iommu_alloc_bypass(dev))
- dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr,
- size_t sz, enum dma_data_direction dir)
-{
- if (dma_iommu_alloc_bypass(dev))
- dma_direct_sync_single_for_device(dev, addr, sz, dir);
-}
-
-extern void dma_iommu_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
- if (dma_iommu_alloc_bypass(dev))
- dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
-}
-
-extern void dma_iommu_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
- if (dma_iommu_alloc_bypass(dev))
- dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
-}
-
const struct dma_map_ops dma_iommu_ops = {
.alloc = dma_iommu_alloc_coherent,
.free = dma_iommu_free_coherent,
@@ -204,10 +145,8 @@
.map_page = dma_iommu_map_page,
.unmap_page = dma_iommu_unmap_page,
.get_required_mask = dma_iommu_get_required_mask,
- .sync_single_for_cpu = dma_iommu_sync_for_cpu,
- .sync_single_for_device = dma_iommu_sync_for_device,
- .sync_sg_for_cpu = dma_iommu_sync_sg_for_cpu,
- .sync_sg_for_device = dma_iommu_sync_sg_for_device,
.mmap = dma_common_mmap,
.get_sgtable = dma_common_get_sgtable,
+ .alloc_pages = dma_common_alloc_pages,
+ .free_pages = dma_common_free_pages,
};
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 3551f11..9d07965 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -17,6 +17,7 @@
#include <asm/cputable.h>
#include <asm/dt_cpu_ftrs.h>
+#include <asm/mce.h>
#include <asm/mmu.h>
#include <asm/oprofile_impl.h>
#include <asm/prom.h>
@@ -24,8 +25,8 @@
/* Device-tree visible constants follow */
-#define ISA_V2_07B 2070
#define ISA_V3_0B 3000
+#define ISA_V3_1 3100
#define USABLE_PR (1U << 0)
#define USABLE_OS (1U << 1)
@@ -64,9 +65,6 @@
* Set up the base CPU
*/
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
-
static int hv_mode;
static struct {
@@ -74,6 +72,7 @@
u64 lpcr_clear;
u64 hfscr;
u64 fscr;
+ u64 pcr;
} system_registers;
static void (*init_pmu_registers)(void);
@@ -101,7 +100,7 @@
if (hv_mode) {
mtspr(SPRN_LPID, 0);
mtspr(SPRN_HFSCR, system_registers.hfscr);
- mtspr(SPRN_PCR, PCR_MASK);
+ mtspr(SPRN_PCR, system_registers.pcr);
}
mtspr(SPRN_FSCR, system_registers.fscr);
@@ -335,6 +334,7 @@
#ifdef CONFIG_PPC_RADIX_MMU
cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+ cur_cpu_spec->mmu_features |= MMU_FTR_GTSE;
cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
return 1;
@@ -448,6 +448,40 @@
return 1;
}
+static void init_pmu_power10(void)
+{
+ init_pmu_power9();
+
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+}
+
+static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power10();
+ init_pmu_registers = init_pmu_power10;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+ cur_cpu_spec->oprofile_cpu_type = "ppc64/power10";
+
+ return 1;
+}
+
+static int __init feat_enable_mce_power10(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power10";
+ cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p10;
+
+ return 1;
+}
+
static int __init feat_enable_tm(struct dt_cpu_feature *f)
{
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -560,6 +594,18 @@
return 1;
}
+static int __init feat_enable_mma(struct dt_cpu_feature *f)
+{
+ u64 pcr;
+
+ feat_enable(f);
+ pcr = mfspr(SPRN_PCR);
+ pcr &= ~PCR_MMA_DIS;
+ mtspr(SPRN_PCR, pcr);
+
+ return 1;
+}
+
struct dt_cpu_feature_match {
const char *name;
int (*enable)(struct dt_cpu_feature *f);
@@ -573,6 +619,7 @@
{"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
{"smt", feat_enable_smt, 0},
{"interrupt-facilities", feat_enable, 0},
+ {"system-call-vectored", feat_enable, 0},
{"timer-facilities", feat_enable, 0},
{"timer-facilities-v3", feat_enable, 0},
{"debug-facilities", feat_enable, 0},
@@ -624,7 +671,9 @@
{"group-start-register", feat_enable, 0},
{"pc-relative-addressing", feat_enable, 0},
{"machine-check-power9", feat_enable_mce_power9, 0},
+ {"machine-check-power10", feat_enable_mce_power10, 0},
{"performance-monitor-power9", feat_enable_pmu_power9, 0},
+ {"performance-monitor-power10", feat_enable_pmu_power10, 0},
{"event-based-branch-v3", feat_enable, 0},
{"random-number-generator", feat_enable, 0},
{"system-call-vectored", feat_disable, 0},
@@ -633,6 +682,9 @@
{"vector-binary128", feat_enable, 0},
{"vector-binary16", feat_enable, 0},
{"wait-v3", feat_enable, 0},
+ {"prefix-instructions", feat_enable, 0},
+ {"matrix-multiply-assist", feat_enable_mma, 0},
+ {"debug-facilities-v31", feat_enable, CPU_FTR_DAWR1},
};
static bool __initdata using_dt_cpu_ftrs;
@@ -658,10 +710,15 @@
{
pr_info("setup for ISA %d\n", isa);
- if (isa >= 3000) {
+ if (isa >= ISA_V3_0B) {
cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
}
+
+ if (isa >= ISA_V3_1) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_31;
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_1;
+ }
}
static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
@@ -734,17 +791,20 @@
/*
* Not all quirks can be derived from the cpufeatures device tree.
*/
- if ((version & 0xffffefff) == 0x004e0200)
- ; /* DD2.0 has no feature flag */
- else if ((version & 0xffffefff) == 0x004e0201)
+ if ((version & 0xffffefff) == 0x004e0200) {
+ /* DD2.0 has no feature flag */
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+ } else if ((version & 0xffffefff) == 0x004e0201) {
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
- else if ((version & 0xffffefff) == 0x004e0202) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+ } else if ((version & 0xffffefff) == 0x004e0202) {
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
- } else if ((version & 0xffff0000) == 0x004e0000)
+ } else if ((version & 0xffff0000) == 0x004e0000) {
/* DD2.1 and up have DD2_1 */
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+ }
if ((version & 0xffff0000) == 0x004e0000) {
cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
@@ -752,12 +812,6 @@
}
update_tlbie_feature_flag(version);
- /*
- * PKEY was not in the initial base or feature node
- * specification, but it should become optional in the next
- * cpu feature version sequence.
- */
- cur_cpu_spec->cpu_features |= CPU_FTR_PKEY;
}
static void __init cpufeatures_setup_finished(void)
@@ -775,6 +829,7 @@
system_registers.lpcr = mfspr(SPRN_LPCR);
system_registers.hfscr = mfspr(SPRN_HFSCR);
system_registers.fscr = mfspr(SPRN_FSCR);
+ system_registers.pcr = mfspr(SPRN_PCR);
pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n",
cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c
index 3482118..ef2ad49 100644
--- a/arch/powerpc/kernel/early_32.c
+++ b/arch/powerpc/kernel/early_32.c
@@ -19,10 +19,13 @@
*/
notrace unsigned long __init early_init(unsigned long dt_ptr)
{
- unsigned long offset = reloc_offset();
+ unsigned long kva, offset = reloc_offset();
+
+ kva = *PTRRELOC(&kernstart_virt_addr);
/* First zero the BSS */
- memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
+ if (kva == KERNELBASE)
+ memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
/*
* Identify the CPU type and fix up code sections
@@ -32,5 +35,5 @@
apply_feature_fixups();
- return KERNELBASE + offset;
+ return kva + offset;
}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 8b0e523..20c417a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -167,39 +167,33 @@
*/
static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
u32 cfg;
int cap, i;
int n = 0, l = 0;
char buffer[128];
- if (!pdn) {
- pr_warn("EEH: Note: No error log for absent device.\n");
- return 0;
- }
-
n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
- pdn->phb->global_number, pdn->busno,
- PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+ edev->pe->phb->global_number, edev->bdfn >> 8,
+ PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn));
pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
- pdn->phb->global_number, pdn->busno,
- PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+ edev->pe->phb->global_number, edev->bdfn >> 8,
+ PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn));
- eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg);
+ eeh_ops->read_config(edev, PCI_VENDOR_ID, 4, &cfg);
n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
- eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg);
+ eeh_ops->read_config(edev, PCI_COMMAND, 4, &cfg);
n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
/* Gather bridge-specific registers */
if (edev->mode & EEH_DEV_BRIDGE) {
- eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg);
+ eeh_ops->read_config(edev, PCI_SEC_STATUS, 2, &cfg);
n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
- eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg);
+ eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &cfg);
n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
pr_warn("EEH: Bridge control: %04x\n", cfg);
}
@@ -207,11 +201,11 @@
/* Dump out the PCI-X command and status regs */
cap = edev->pcix_cap;
if (cap) {
- eeh_ops->read_config(pdn, cap, 4, &cfg);
+ eeh_ops->read_config(edev, cap, 4, &cfg);
n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
- eeh_ops->read_config(pdn, cap+4, 4, &cfg);
+ eeh_ops->read_config(edev, cap+4, 4, &cfg);
n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
pr_warn("EEH: PCI-X status: %08x\n", cfg);
}
@@ -223,7 +217,7 @@
pr_warn("EEH: PCI-E capabilities and status follow:\n");
for (i=0; i<=8; i++) {
- eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
+ eeh_ops->read_config(edev, cap+4*i, 4, &cfg);
n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
if ((i % 4) == 0) {
@@ -250,7 +244,7 @@
pr_warn("EEH: PCI-E AER capability register set follows:\n");
for (i=0; i<=13; i++) {
- eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
+ eeh_ops->read_config(edev, cap+4*i, 4, &cfg);
n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
if ((i % 4) == 0) {
@@ -469,11 +463,6 @@
return 0;
}
- if (!pe->addr && !pe->config_addr) {
- eeh_stats.no_cfg_addr++;
- return 0;
- }
-
/*
* On PowerNV platform, we might already have fenced PHB
* there and we need take care of that firstly.
@@ -723,7 +712,6 @@
static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
struct pci_dev *dev = userdata;
@@ -731,73 +719,14 @@
return;
/* Apply customization from firmware */
- if (pdn && eeh_ops->restore_config)
- eeh_ops->restore_config(pdn);
+ if (eeh_ops->restore_config)
+ eeh_ops->restore_config(edev);
/* The caller should restore state for the specified device */
if (pdev != dev)
pci_restore_state(pdev);
}
-int eeh_restore_vf_config(struct pci_dn *pdn)
-{
- struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
- u32 devctl, cmd, cap2, aer_capctl;
- int old_mps;
-
- if (edev->pcie_cap) {
- /* Restore MPS */
- old_mps = (ffs(pdn->mps) - 8) << 5;
- eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
- 2, &devctl);
- devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
- devctl |= old_mps;
- eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
- 2, devctl);
-
- /* Disable Completion Timeout if possible */
- eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
- 4, &cap2);
- if (cap2 & PCI_EXP_DEVCAP2_COMP_TMOUT_DIS) {
- eeh_ops->read_config(pdn,
- edev->pcie_cap + PCI_EXP_DEVCTL2,
- 4, &cap2);
- cap2 |= PCI_EXP_DEVCTL2_COMP_TMOUT_DIS;
- eeh_ops->write_config(pdn,
- edev->pcie_cap + PCI_EXP_DEVCTL2,
- 4, cap2);
- }
- }
-
- /* Enable SERR and parity checking */
- eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
- cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
- eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
-
- /* Enable report various errors */
- if (edev->pcie_cap) {
- eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
- 2, &devctl);
- devctl &= ~PCI_EXP_DEVCTL_CERE;
- devctl |= (PCI_EXP_DEVCTL_NFERE |
- PCI_EXP_DEVCTL_FERE |
- PCI_EXP_DEVCTL_URRE);
- eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
- 2, devctl);
- }
-
- /* Enable ECRC generation and check */
- if (edev->pcie_cap && edev->aer_cap) {
- eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
- 4, &aer_capctl);
- aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
- eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
- 4, aer_capctl);
- }
-
- return 0;
-}
-
/**
* pcibios_set_pcie_reset_state - Set PCI-E reset state
* @dev: pci device struct
@@ -974,15 +903,13 @@
*/
void eeh_save_bars(struct eeh_dev *edev)
{
- struct pci_dn *pdn;
int i;
- pdn = eeh_dev_to_pdn(edev);
- if (!pdn)
+ if (!edev)
return;
for (i = 0; i < 16; i++)
- eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]);
+ eeh_ops->read_config(edev, i * 4, 4, &edev->config_space[i]);
/*
* For PCI bridges including root port, we need enable bus
@@ -994,56 +921,6 @@
edev->config_space[1] |= PCI_COMMAND_MASTER;
}
-/**
- * eeh_ops_register - Register platform dependent EEH operations
- * @ops: platform dependent EEH operations
- *
- * Register the platform dependent EEH operation callback
- * functions. The platform should call this function before
- * any other EEH operations.
- */
-int __init eeh_ops_register(struct eeh_ops *ops)
-{
- if (!ops->name) {
- pr_warn("%s: Invalid EEH ops name for %p\n",
- __func__, ops);
- return -EINVAL;
- }
-
- if (eeh_ops && eeh_ops != ops) {
- pr_warn("%s: EEH ops of platform %s already existing (%s)\n",
- __func__, eeh_ops->name, ops->name);
- return -EEXIST;
- }
-
- eeh_ops = ops;
-
- return 0;
-}
-
-/**
- * eeh_ops_unregister - Unreigster platform dependent EEH operations
- * @name: name of EEH platform operations
- *
- * Unregister the platform dependent EEH operation callback
- * functions.
- */
-int __exit eeh_ops_unregister(const char *name)
-{
- if (!name || !strlen(name)) {
- pr_warn("%s: Invalid EEH ops name\n",
- __func__);
- return -EINVAL;
- }
-
- if (eeh_ops && !strcmp(eeh_ops->name, name)) {
- eeh_ops = NULL;
- return 0;
- }
-
- return -EEXIST;
-}
-
static int eeh_reboot_notifier(struct notifier_block *nb,
unsigned long action, void *unused)
{
@@ -1055,45 +932,65 @@
.notifier_call = eeh_reboot_notifier,
};
+static int eeh_device_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct device *dev = data;
+
+ switch (action) {
+ /*
+ * Note: It's not possible to perform EEH device addition (i.e.
+ * {pseries,pnv}_pcibios_bus_add_device()) here because it depends on
+ * the device's resources, which have not yet been set up.
+ */
+ case BUS_NOTIFY_DEL_DEVICE:
+ eeh_remove_device(to_pci_dev(dev));
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_device_nb = {
+ .notifier_call = eeh_device_notifier,
+};
+
/**
- * eeh_init - EEH initialization
+ * eeh_init - System wide EEH initialization
*
- * Initialize EEH by trying to enable it for all of the adapters in the system.
- * As a side effect we can determine here if eeh is supported at all.
- * Note that we leave EEH on so failed config cycles won't cause a machine
- * check. If a user turns off EEH for a particular adapter they are really
- * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't
- * grant access to a slot if EEH isn't enabled, and so we always enable
- * EEH for all slots/all devices.
- *
- * The eeh-force-off option disables EEH checking globally, for all slots.
- * Even if force-off is set, the EEH hardware is still enabled, so that
- * newer systems can boot.
+ * It's the platform's job to call this from an arch_initcall().
*/
-static int eeh_init(void)
+int eeh_init(struct eeh_ops *ops)
{
struct pci_controller *hose, *tmp;
int ret = 0;
+ /* the platform should only initialise EEH once */
+ if (WARN_ON(eeh_ops))
+ return -EEXIST;
+ if (WARN_ON(!ops))
+ return -ENOENT;
+ eeh_ops = ops;
+
/* Register reboot notifier */
ret = register_reboot_notifier(&eeh_reboot_nb);
if (ret) {
- pr_warn("%s: Failed to register notifier (%d)\n",
+ pr_warn("%s: Failed to register reboot notifier (%d)\n",
__func__, ret);
return ret;
}
- /* call platform initialization function */
- if (!eeh_ops) {
- pr_warn("%s: Platform EEH operation not found\n",
- __func__);
- return -EEXIST;
- } else if ((ret = eeh_ops->init()))
+ ret = bus_register_notifier(&pci_bus_type, &eeh_device_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register bus notifier (%d)\n",
+ __func__, ret);
return ret;
+ }
/* Initialize PHB PEs */
list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
- eeh_dev_phb_init_dynamic(hose);
+ eeh_phb_pe_create(hose);
eeh_addr_cache_init();
@@ -1101,94 +998,47 @@
return eeh_event_init();
}
-core_initcall_sync(eeh_init);
-
/**
- * eeh_add_device_early - Enable EEH for the indicated device node
- * @pdn: PCI device node for which to set up EEH
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices that were added after system boot (e.g. hotplug, dlpar).
- * This routine must be called before any i/o is performed to the
- * adapter (inluding any config-space i/o).
- * Whether this actually enables EEH or not for this device depends
- * on the CEC architecture, type of the device, on earlier boot
- * command-line arguments & etc.
- */
-void eeh_add_device_early(struct pci_dn *pdn)
-{
- struct pci_controller *phb = pdn ? pdn->phb : NULL;
- struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
-
- if (!edev)
- return;
-
- if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
- return;
-
- /* USB Bus children of PCI devices will not have BUID's */
- if (NULL == phb ||
- (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid))
- return;
-
- eeh_ops->probe(pdn, NULL);
-}
-
-/**
- * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @pdn: PCI device node
- *
- * This routine must be used to perform EEH initialization for the
- * indicated PCI device that was added after system boot (e.g.
- * hotplug, dlpar).
- */
-void eeh_add_device_tree_early(struct pci_dn *pdn)
-{
- struct pci_dn *n;
-
- if (!pdn)
- return;
-
- list_for_each_entry(n, &pdn->child_list, list)
- eeh_add_device_tree_early(n);
- eeh_add_device_early(pdn);
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
-
-/**
- * eeh_add_device_late - Perform EEH initialization for the indicated pci device
+ * eeh_probe_device() - Perform EEH initialization for the indicated pci device
* @dev: pci device for which to set up EEH
*
* This routine must be used to complete EEH initialization for PCI
* devices that were added after system boot (e.g. hotplug, dlpar).
*/
-void eeh_add_device_late(struct pci_dev *dev)
+void eeh_probe_device(struct pci_dev *dev)
{
- struct pci_dn *pdn;
struct eeh_dev *edev;
- if (!dev)
- return;
+ pr_debug("EEH: Adding device %s\n", pci_name(dev));
- pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
- edev = pdn_to_eeh_dev(pdn);
- eeh_edev_dbg(edev, "Adding device\n");
- if (edev->pdev == dev) {
- eeh_edev_dbg(edev, "Device already referenced!\n");
+ /*
+ * pci_dev_to_eeh_dev() can only work if eeh_probe_dev() was
+ * already called for this device.
+ */
+ if (WARN_ON_ONCE(pci_dev_to_eeh_dev(dev))) {
+ pci_dbg(dev, "Already bound to an eeh_dev!\n");
+ return;
+ }
+
+ edev = eeh_ops->probe(dev);
+ if (!edev) {
+ pr_debug("EEH: Adding device failed\n");
return;
}
/*
- * The EEH cache might not be removed correctly because of
- * unbalanced kref to the device during unplug time, which
- * relies on pcibios_release_device(). So we have to remove
- * that here explicitly.
+ * FIXME: We rely on pcibios_release_device() to remove the
+ * existing EEH state. The release function is only called if
+ * the pci_dev's refcount drops to zero so if something is
+ * keeping a ref to a device (e.g. a filesystem) we need to
+ * remove the old EEH state.
+ *
+ * FIXME: HEY MA, LOOK AT ME, NO LOCKING!
*/
- if (edev->pdev) {
- eeh_rmv_from_parent_pe(edev);
+ if (edev->pdev && edev->pdev != dev) {
+ eeh_pe_tree_remove(edev);
eeh_addr_cache_rmv_dev(edev->pdev);
eeh_sysfs_remove_device(edev->pdev);
- edev->mode &= ~EEH_DEV_SYSFS;
/*
* We definitely should have the PCI device removed
@@ -1196,69 +1046,16 @@
* into error handler afterwards.
*/
edev->mode |= EEH_DEV_NO_HANDLER;
-
- edev->pdev = NULL;
- dev->dev.archdata.edev = NULL;
}
- if (eeh_has_flag(EEH_PROBE_MODE_DEV))
- eeh_ops->probe(pdn, NULL);
-
+ /* bind the pdev and the edev together */
edev->pdev = dev;
dev->dev.archdata.edev = edev;
-
eeh_addr_cache_insert_dev(dev);
+ eeh_sysfs_add_device(dev);
}
/**
- * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_device_tree_late(struct pci_bus *bus)
-{
- struct pci_dev *dev;
-
- if (eeh_has_flag(EEH_FORCE_DISABLED))
- return;
- list_for_each_entry(dev, &bus->devices, bus_list) {
- eeh_add_device_late(dev);
- if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- struct pci_bus *subbus = dev->subordinate;
- if (subbus)
- eeh_add_device_tree_late(subbus);
- }
- }
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
-
-/**
- * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to add EEH sysfs files for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_sysfs_files(struct pci_bus *bus)
-{
- struct pci_dev *dev;
-
- list_for_each_entry(dev, &bus->devices, bus_list) {
- eeh_sysfs_add_device(dev);
- if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- struct pci_bus *subbus = dev->subordinate;
- if (subbus)
- eeh_add_sysfs_files(subbus);
- }
- }
-}
-EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
-
-/**
* eeh_remove_device - Undo EEH setup for the indicated pci device
* @dev: pci device to be removed
*
@@ -1293,17 +1090,11 @@
edev->pdev = NULL;
/*
- * The flag "in_error" is used to trace EEH devices for VFs
- * in error state or not. It's set in eeh_report_error(). If
- * it's not set, eeh_report_{reset,resume}() won't be called
- * for the VF EEH device.
+ * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to
+ * remove the sysfs files before clearing dev.archdata.edev
*/
- edev->in_error = false;
- dev->dev.archdata.edev = NULL;
- if (!(edev->pe->state & EEH_PE_KEEP))
- eeh_rmv_from_parent_pe(edev);
- else
- edev->mode |= EEH_DEV_DISCONNECTED;
+ if (edev->mode & EEH_DEV_SYSFS)
+ eeh_sysfs_remove_device(dev);
/*
* We're removing from the PCI subsystem, that means
@@ -1314,8 +1105,19 @@
edev->mode |= EEH_DEV_NO_HANDLER;
eeh_addr_cache_rmv_dev(dev);
- eeh_sysfs_remove_device(dev);
- edev->mode &= ~EEH_DEV_SYSFS;
+
+ /*
+ * The flag "in_error" is used to trace EEH devices for VFs
+ * in error state or not. It's set in eeh_report_error(). If
+ * it's not set, eeh_report_{reset,resume}() won't be called
+ * for the VF EEH device.
+ */
+ edev->in_error = false;
+ dev->dev.archdata.edev = NULL;
+ if (!(edev->pe->state & EEH_PE_KEEP))
+ eeh_pe_tree_remove(edev);
+ else
+ edev->mode |= EEH_DEV_DISCONNECTED;
}
int eeh_unfreeze_pe(struct eeh_pe *pe)
@@ -1847,7 +1649,7 @@
return -ENODEV;
/* Retrieve PE */
- pe = eeh_pe_get(hose, pe_no, 0);
+ pe = eeh_pe_get(hose, pe_no);
if (!pe)
return -ENODEV;
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 000ebb5..bf32704 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -159,18 +159,10 @@
static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
{
- struct pci_dn *pdn;
struct eeh_dev *edev;
int i;
- pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
- if (!pdn) {
- pr_warn("PCI: no pci dn found for dev=%s\n",
- pci_name(dev));
- return;
- }
-
- edev = pdn_to_eeh_dev(pdn);
+ edev = pci_dev_to_eeh_dev(dev);
if (!edev) {
pr_warn("PCI: no EEH dev found for %s\n",
pci_name(dev));
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
deleted file mode 100644
index 7370185..0000000
--- a/arch/powerpc/kernel/eeh_dev.c
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * The file intends to implement dynamic creation of EEH device, which will
- * be bound with OF node and PCI device simutaneously. The EEH devices would
- * be foundamental information for EEH core components to work proerly. Besides,
- * We have to support multiple situations where dynamic creation of EEH device
- * is required:
- *
- * 1) Before PCI emunation starts, we need create EEH devices according to the
- * PCI sensitive OF nodes.
- * 2) When PCI emunation is done, we need do the binding between PCI device and
- * the associated EEH device.
- * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device
- * will be created while PCI sensitive OF node is detected from DR.
- * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If
- * PHB is newly inserted, we also need create EEH devices accordingly.
- *
- * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
- */
-
-#include <linux/export.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/string.h>
-
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-
-/**
- * eeh_dev_init - Create EEH device according to OF node
- * @pdn: PCI device node
- *
- * It will create EEH device according to the given OF node. The function
- * might be called by PCI emunation, DR, PHB hotplug.
- */
-struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
-{
- struct eeh_dev *edev;
-
- /* Allocate EEH device */
- edev = kzalloc(sizeof(*edev), GFP_KERNEL);
- if (!edev)
- return NULL;
-
- /* Associate EEH device with OF node */
- pdn->edev = edev;
- edev->pdn = pdn;
- edev->bdfn = (pdn->busno << 8) | pdn->devfn;
- edev->controller = pdn->phb;
-
- return edev;
-}
-
-/**
- * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB
- * @phb: PHB
- *
- * Scan the PHB OF node and its child association, then create the
- * EEH devices accordingly
- */
-void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
-{
- /* EEH PE for PHB */
- eeh_phb_pe_create(phb);
-}
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 4fd7efd..3eff6a4 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -1,25 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* PCI Error Recovery Driver for RPA-compliant PPC64 platform.
* Copyright IBM Corp. 2004 2005
* Copyright Linas Vepstas <linas@linas.org> 2004, 2005
*
- * All rights reserved.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
* Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
*/
#include <linux/delay.h>
@@ -230,7 +214,7 @@
pci_save_state(pdev);
}
-static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s)
+static void eeh_set_channel_state(struct eeh_pe *root, pci_channel_state_t s)
{
struct eeh_pe *pe;
struct eeh_dev *edev, *tmp;
@@ -441,8 +425,8 @@
pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED);
#ifdef CONFIG_PCI_IOV
- if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev))
- eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
+ if (eeh_ops->notify_resume)
+ eeh_ops->notify_resume(edev);
#endif
return PCI_ERS_RESULT_NONE;
}
@@ -493,7 +477,7 @@
}
#ifdef CONFIG_PCI_IOV
- pci_iov_add_virtfn(edev->physfn, eeh_dev_to_pdn(edev)->vf_index);
+ pci_iov_add_virtfn(edev->physfn, edev->vf_index);
#endif
return NULL;
}
@@ -537,9 +521,7 @@
if (edev->physfn) {
#ifdef CONFIG_PCI_IOV
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
-
- pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
+ pci_iov_remove_virtfn(edev->physfn, edev->vf_index);
edev->pdev = NULL;
#endif
if (rmv_data)
@@ -560,7 +542,7 @@
continue;
edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
- eeh_rmv_from_parent_pe(edev);
+ eeh_pe_tree_remove(edev);
}
return NULL;
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 177852e..845e024 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -251,43 +251,21 @@
/**
* __eeh_pe_get - Check the PE address
- * @data: EEH PE
- * @flag: EEH device
*
* For one particular PE, it can be identified by PE address
* or tranditional BDF address. BDF address is composed of
* Bus/Device/Function number. The extra data referred by flag
* indicates which type of address should be used.
*/
-struct eeh_pe_get_flag {
- int pe_no;
- int config_addr;
-};
-
static void *__eeh_pe_get(struct eeh_pe *pe, void *flag)
{
- struct eeh_pe_get_flag *tmp = (struct eeh_pe_get_flag *) flag;
+ int *target_pe = flag;
- /* Unexpected PHB PE */
+ /* PHB PEs are special and should be ignored */
if (pe->type & EEH_PE_PHB)
return NULL;
- /*
- * We prefer PE address. For most cases, we should
- * have non-zero PE address
- */
- if (eeh_has_flag(EEH_VALID_PE_ZERO)) {
- if (tmp->pe_no == pe->addr)
- return pe;
- } else {
- if (tmp->pe_no &&
- (tmp->pe_no == pe->addr))
- return pe;
- }
-
- /* Try BDF address */
- if (tmp->config_addr &&
- (tmp->config_addr == pe->config_addr))
+ if (*target_pe == pe->addr)
return pe;
return NULL;
@@ -297,7 +275,6 @@
* eeh_pe_get - Search PE based on the given address
* @phb: PCI controller
* @pe_no: PE number
- * @config_addr: Config address
*
* Search the corresponding PE based on the specified address which
* is included in the eeh device. The function is used to check if
@@ -306,75 +283,30 @@
* which is composed of PCI bus/device/function number, or unified
* PE address.
*/
-struct eeh_pe *eeh_pe_get(struct pci_controller *phb,
- int pe_no, int config_addr)
+struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no)
{
struct eeh_pe *root = eeh_phb_pe_get(phb);
- struct eeh_pe_get_flag tmp = { pe_no, config_addr };
- struct eeh_pe *pe;
- pe = eeh_pe_traverse(root, __eeh_pe_get, &tmp);
-
- return pe;
+ return eeh_pe_traverse(root, __eeh_pe_get, &pe_no);
}
/**
- * eeh_pe_get_parent - Retrieve the parent PE
+ * eeh_pe_tree_insert - Add EEH device to parent PE
* @edev: EEH device
+ * @new_pe_parent: PE to create additional PEs under
*
- * The whole PEs existing in the system are organized as hierarchy
- * tree. The function is used to retrieve the parent PE according
- * to the parent EEH device.
- */
-static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
-{
- struct eeh_dev *parent;
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
-
- /*
- * It might have the case for the indirect parent
- * EEH device already having associated PE, but
- * the direct parent EEH device doesn't have yet.
- */
- if (edev->physfn)
- pdn = pci_get_pdn(edev->physfn);
- else
- pdn = pdn ? pdn->parent : NULL;
- while (pdn) {
- /* We're poking out of PCI territory */
- parent = pdn_to_eeh_dev(pdn);
- if (!parent)
- return NULL;
-
- if (parent->pe)
- return parent->pe;
-
- pdn = pdn->parent;
- }
-
- return NULL;
-}
-
-/**
- * eeh_add_to_parent_pe - Add EEH device to parent PE
- * @edev: EEH device
+ * Add EEH device to the PE in edev->pe_config_addr. If a PE already
+ * exists with that address then @edev is added to that PE. Otherwise
+ * a new PE is created and inserted into the PE tree as a child of
+ * @new_pe_parent.
*
- * Add EEH device to the parent PE. If the parent PE already
- * exists, the PE type will be changed to EEH_PE_BUS. Otherwise,
- * we have to create new PE to hold the EEH device and the new
- * PE will be linked to its parent PE as well.
+ * If @new_pe_parent is NULL then the new PE will be inserted under
+ * directly under the the PHB.
*/
-int eeh_add_to_parent_pe(struct eeh_dev *edev)
+int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent)
{
+ struct pci_controller *hose = edev->controller;
struct eeh_pe *pe, *parent;
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
- int config_addr = (pdn->busno << 8) | (pdn->devfn);
-
- /* Check if the PE number is valid */
- if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
- eeh_edev_err(edev, "PE#0 is invalid for this PHB!\n");
- return -EINVAL;
- }
/*
* Search the PE has been existing or not according
@@ -382,7 +314,7 @@
* PE should be composed of PCI bus and its subordinate
* components.
*/
- pe = eeh_pe_get(pdn->phb, edev->pe_config_addr, config_addr);
+ pe = eeh_pe_get(hose, edev->pe_config_addr);
if (pe) {
if (pe->type & EEH_PE_INVALID) {
list_add_tail(&edev->entry, &pe->edevs);
@@ -399,8 +331,7 @@
parent = parent->parent;
}
- eeh_edev_dbg(edev,
- "Added to device PE (parent: PE#%x)\n",
+ eeh_edev_dbg(edev, "Added to existing PE (parent: PE#%x)\n",
pe->parent->addr);
} else {
/* Mark the PE as type of PCI bus */
@@ -416,15 +347,15 @@
/* Create a new EEH PE */
if (edev->physfn)
- pe = eeh_pe_alloc(pdn->phb, EEH_PE_VF);
+ pe = eeh_pe_alloc(hose, EEH_PE_VF);
else
- pe = eeh_pe_alloc(pdn->phb, EEH_PE_DEVICE);
+ pe = eeh_pe_alloc(hose, EEH_PE_DEVICE);
if (!pe) {
pr_err("%s: out of memory!\n", __func__);
return -ENOMEM;
}
- pe->addr = edev->pe_config_addr;
- pe->config_addr = config_addr;
+
+ pe->addr = edev->pe_config_addr;
/*
* Put the new EEH PE into hierarchy tree. If the parent
@@ -432,34 +363,35 @@
* to PHB directly. Otherwise, we have to associate the
* PE with its parent.
*/
- parent = eeh_pe_get_parent(edev);
- if (!parent) {
- parent = eeh_phb_pe_get(pdn->phb);
- if (!parent) {
+ if (!new_pe_parent) {
+ new_pe_parent = eeh_phb_pe_get(hose);
+ if (!new_pe_parent) {
pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
- __func__, pdn->phb->global_number);
+ __func__, hose->global_number);
edev->pe = NULL;
kfree(pe);
return -EEXIST;
}
}
- pe->parent = parent;
+
+ /* link new PE into the tree */
+ pe->parent = new_pe_parent;
+ list_add_tail(&pe->child, &new_pe_parent->child_list);
/*
* Put the newly created PE into the child list and
* link the EEH device accordingly.
*/
- list_add_tail(&pe->child, &parent->child_list);
list_add_tail(&edev->entry, &pe->edevs);
edev->pe = pe;
- eeh_edev_dbg(edev, "Added to device PE (parent: PE#%x)\n",
- pe->parent->addr);
+ eeh_edev_dbg(edev, "Added to new (parent: PE#%x)\n",
+ new_pe_parent->addr);
return 0;
}
/**
- * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
+ * eeh_pe_tree_remove - Remove one EEH device from the associated PE
* @edev: EEH device
*
* The PE hierarchy tree might be changed when doing PCI hotplug.
@@ -467,7 +399,7 @@
* during EEH recovery. So we have to call the function remove the
* corresponding PE accordingly if necessary.
*/
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
+int eeh_pe_tree_remove(struct eeh_dev *edev)
{
struct eeh_pe *pe, *parent, *child;
bool keep, recover;
@@ -698,7 +630,6 @@
*/
static void eeh_bridge_check_link(struct eeh_dev *edev)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int cap;
uint32_t val;
int timeout = 0;
@@ -714,32 +645,32 @@
/* Check slot status */
cap = edev->pcie_cap;
- eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTSTA, 2, &val);
if (!(val & PCI_EXP_SLTSTA_PDS)) {
eeh_edev_dbg(edev, "No card in the slot (0x%04x) !\n", val);
return;
}
/* Check power status if we have the capability */
- eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTCAP, 2, &val);
if (val & PCI_EXP_SLTCAP_PCP) {
- eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTCTL, 2, &val);
if (val & PCI_EXP_SLTCTL_PCC) {
eeh_edev_dbg(edev, "In power-off state, power it on ...\n");
val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
- eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
+ eeh_ops->write_config(edev, cap + PCI_EXP_SLTCTL, 2, val);
msleep(2 * 1000);
}
}
/* Enable link */
- eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_LNKCTL, 2, &val);
val &= ~PCI_EXP_LNKCTL_LD;
- eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val);
+ eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
/* Check link */
- eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val);
if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
msleep(1000);
@@ -752,7 +683,7 @@
msleep(20);
timeout += 20;
- eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val);
+ eeh_ops->read_config(edev, cap + PCI_EXP_LNKSTA, 2, &val);
if (val & PCI_EXP_LNKSTA_DLLLA)
break;
}
@@ -769,7 +700,6 @@
static void eeh_restore_bridge_bars(struct eeh_dev *edev)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int i;
/*
@@ -777,20 +707,20 @@
* Bus numbers and windows: 0x18 - 0x30
*/
for (i = 4; i < 13; i++)
- eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
+ eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]);
/* Rom: 0x38 */
- eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]);
+ eeh_ops->write_config(edev, 14*4, 4, edev->config_space[14]);
/* Cache line & Latency timer: 0xC 0xD */
- eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
+ eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1,
SAVED_BYTE(PCI_CACHE_LINE_SIZE));
- eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
- SAVED_BYTE(PCI_LATENCY_TIMER));
+ eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1,
+ SAVED_BYTE(PCI_LATENCY_TIMER));
/* Max latency, min grant, interrupt ping and line: 0x3C */
- eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
+ eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]);
/* PCI Command: 0x4 */
- eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
+ eeh_ops->write_config(edev, PCI_COMMAND, 4, edev->config_space[1] |
PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
/* Check the PCIe link is ready */
@@ -799,28 +729,27 @@
static void eeh_restore_device_bars(struct eeh_dev *edev)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int i;
u32 cmd;
for (i = 4; i < 10; i++)
- eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
+ eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]);
/* 12 == Expansion ROM Address */
- eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]);
+ eeh_ops->write_config(edev, 12*4, 4, edev->config_space[12]);
- eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
+ eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1,
SAVED_BYTE(PCI_CACHE_LINE_SIZE));
- eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
+ eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1,
SAVED_BYTE(PCI_LATENCY_TIMER));
/* max latency, min grant, interrupt pin and line */
- eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
+ eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]);
/*
* Restore PERR & SERR bits, some devices require it,
* don't touch the other command bits
*/
- eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd);
+ eeh_ops->read_config(edev, PCI_COMMAND, 4, &cmd);
if (edev->config_space[1] & PCI_COMMAND_PARITY)
cmd |= PCI_COMMAND_PARITY;
else
@@ -829,7 +758,7 @@
cmd |= PCI_COMMAND_SERR;
else
cmd &= ~PCI_COMMAND_SERR;
- eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd);
+ eeh_ops->write_config(edev, PCI_COMMAND, 4, cmd);
}
/**
@@ -843,16 +772,14 @@
*/
static void eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag)
{
- struct pci_dn *pdn = eeh_dev_to_pdn(edev);
-
/* Do special restore for bridges */
if (edev->mode & EEH_DEV_BRIDGE)
eeh_restore_bridge_bars(edev);
else
eeh_restore_device_bars(edev);
- if (eeh_ops->restore_config && pdn)
- eeh_ops->restore_config(pdn);
+ if (eeh_ops->restore_config)
+ eeh_ops->restore_config(edev);
}
/**
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index 3fa04dd..429620d 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -1,25 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Sysfs entries for PCI Error Recovery for PAPR-compliant platform.
* Copyright IBM Corporation 2007
* Copyright Linas Vepstas <linas@austin.ibm.com> 2007
*
- * All rights reserved.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
* Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
*/
#include <linux/pci.h>
@@ -30,7 +14,7 @@
/**
* EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
* @_name: name of file in sysfs directory
- * @_memb: name of member in struct pci_dn to access
+ * @_memb: name of member in struct eeh_dev to access
* @_format: printf format for display
*
* All of the attributes look very similar, so just
@@ -91,7 +75,7 @@
static DEVICE_ATTR_RW(eeh_pe_state);
-#ifdef CONFIG_PCI_IOV
+#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PPC_PSERIES)
static ssize_t eeh_notify_resume_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -102,7 +86,6 @@
if (!edev || !edev->pe)
return -ENODEV;
- pdn = pci_get_pdn(pdev);
return sprintf(buf, "%d\n", pdn->last_allow_rc);
}
@@ -116,7 +99,7 @@
if (!edev || !edev->pe || !eeh_ops->notify_resume)
return -ENODEV;
- if (eeh_ops->notify_resume(pci_get_pdn(pdev)))
+ if (eeh_ops->notify_resume(edev))
return -EIO;
return count;
@@ -148,7 +131,7 @@
#else
static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; }
static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { }
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_IOV && CONFIG PPC_PSERIES*/
void eeh_sysfs_add_device(struct pci_dev *pdev)
{
@@ -176,22 +159,23 @@
{
struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+ if (!edev) {
+ WARN_ON(eeh_enabled());
+ return;
+ }
+
+ edev->mode &= ~EEH_DEV_SYSFS;
+
/*
* The parent directory might have been removed. We needn't
* continue for that case.
*/
- if (!pdev->dev.kobj.sd) {
- if (edev)
- edev->mode &= ~EEH_DEV_SYSFS;
+ if (!pdev->dev.kobj.sd)
return;
- }
device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
eeh_notify_resume_remove(pdev);
-
- if (edev)
- edev->mode &= ~EEH_DEV_SYSFS;
}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index c72894f..459f5d0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -28,7 +28,6 @@
#include <asm/unistd.h>
#include <asm/ptrace.h>
#include <asm/export.h>
-#include <asm/asm-405.h>
#include <asm/feature-fixups.h>
#include <asm/barrier.h>
#include <asm/kup.h>
@@ -37,6 +36,12 @@
#include "head_32.h"
/*
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional
+ * synchronisation instructions.
+ */
+
+/*
* Align to 4k in order to ensure that all functions modyfing srr0/srr1
* fit into one page in order to not encounter a TLB miss between the
* modification of srr0/srr1 and the associated rfi.
@@ -51,6 +56,7 @@
mfspr r0,SPRN_DSRR1
stw r0,_DSRR1(r11)
/* fall through */
+_ASM_NOKPROBE_SYMBOL(mcheck_transfer_to_handler)
.globl debug_transfer_to_handler
debug_transfer_to_handler:
@@ -59,6 +65,7 @@
mfspr r0,SPRN_CSRR1
stw r0,_CSRR1(r11)
/* fall through */
+_ASM_NOKPROBE_SYMBOL(debug_transfer_to_handler)
.globl crit_transfer_to_handler
crit_transfer_to_handler:
@@ -94,6 +101,7 @@
rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
+_ASM_NOKPROBE_SYMBOL(crit_transfer_to_handler)
#endif
#ifdef CONFIG_40x
@@ -115,6 +123,7 @@
rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
+_ASM_NOKPROBE_SYMBOL(crit_transfer_to_handler)
#endif
/*
@@ -127,6 +136,7 @@
.globl transfer_to_handler_full
transfer_to_handler_full:
SAVE_NVGPRS(r11)
+_ASM_NOKPROBE_SYMBOL(transfer_to_handler_full)
/* fall through */
.globl transfer_to_handler
@@ -140,6 +150,7 @@
stw r12,_CTR(r11)
stw r2,_XER(r11)
mfspr r12,SPRN_SPRG_THREAD
+ tovirt_vmstack r12, r12
beq 2f /* if from user, fix up THREAD.regs */
addi r2, r12, -THREAD
addi r11,r1,STACK_FRAME_OVERHEAD
@@ -181,9 +192,11 @@
*/
kuap_save_and_lock r11, r12, r9, r2, r6
addi r2, r12, -THREAD
+#ifndef CONFIG_VMAP_STACK
lwz r9,KSP_LIMIT(r12)
cmplw r1,r9 /* if r1 <= ksp_limit */
ble- stack_ovf /* then the kernel stack overflowed */
+#endif
5:
#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
lwz r12,TI_LOCAL_FLAGS(r2)
@@ -195,7 +208,8 @@
transfer_to_handler_cont:
3:
mflr r9
- tovirt(r2, r2) /* set r2 to current */
+ tovirt_novmstack r2, r2 /* set r2 to current */
+ tovirt_vmstack r9, r9
lwz r11,0(r9) /* virtual address of handler */
lwz r9,4(r9) /* where to go when done */
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
@@ -210,7 +224,7 @@
* To speed up the syscall path where interrupts stay on, let's check
* first if we are changing the MSR value at all.
*/
- tophys(r12, r1)
+ tophys_novmstack r12, r1
lwz r12,_MSR(r12)
andi. r12,r12,MSR_EE
bne 1f
@@ -220,59 +234,8 @@
mtspr SPRN_SRR0,r11
mtspr SPRN_SRR1,r10
mtlr r9
- SYNC
RFI /* jump to handler, enable MMU */
-#ifdef CONFIG_TRACE_IRQFLAGS
-1: /* MSR is changing, re-enable MMU so we can notify lockdep. We need to
- * keep interrupts disabled at this point otherwise we might risk
- * taking an interrupt before we tell lockdep they are enabled.
- */
- lis r12,reenable_mmu@h
- ori r12,r12,reenable_mmu@l
- LOAD_REG_IMMEDIATE(r0, MSR_KERNEL)
- mtspr SPRN_SRR0,r12
- mtspr SPRN_SRR1,r0
- SYNC
- RFI
-
-reenable_mmu:
- /*
- * We save a bunch of GPRs,
- * r3 can be different from GPR3(r1) at this point, r9 and r11
- * contains the old MSR and handler address respectively,
- * r4 & r5 can contain page fault arguments that need to be passed
- * along as well. r12, CCR, CTR, XER etc... are left clobbered as
- * they aren't useful past this point (aren't syscall arguments),
- * the rest is restored from the exception frame.
- */
-
- stwu r1,-32(r1)
- stw r9,8(r1)
- stw r11,12(r1)
- stw r3,16(r1)
- stw r4,20(r1)
- stw r5,24(r1)
-
- /* If we are disabling interrupts (normal case), simply log it with
- * lockdep
- */
-1: bl trace_hardirqs_off
-2: lwz r5,24(r1)
- lwz r4,20(r1)
- lwz r3,16(r1)
- lwz r11,12(r1)
- lwz r9,8(r1)
- addi r1,r1,32
- lwz r0,GPR0(r1)
- lwz r6,GPR6(r1)
- lwz r7,GPR7(r1)
- lwz r8,GPR8(r1)
- mtctr r11
- mtlr r9
- bctr /* jump to handler */
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
#if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
4: rlwinm r12,r12,0,~_TLF_NAPPING
stw r12,TI_LOCAL_FLAGS(r2)
@@ -287,7 +250,54 @@
lwz r2, GPR2(r11)
b fast_exception_return
#endif
+_ASM_NOKPROBE_SYMBOL(transfer_to_handler)
+_ASM_NOKPROBE_SYMBOL(transfer_to_handler_cont)
+#ifdef CONFIG_TRACE_IRQFLAGS
+1: /* MSR is changing, re-enable MMU so we can notify lockdep. We need to
+ * keep interrupts disabled at this point otherwise we might risk
+ * taking an interrupt before we tell lockdep they are enabled.
+ */
+ lis r12,reenable_mmu@h
+ ori r12,r12,reenable_mmu@l
+ LOAD_REG_IMMEDIATE(r0, MSR_KERNEL)
+ mtspr SPRN_SRR0,r12
+ mtspr SPRN_SRR1,r0
+ RFI
+
+reenable_mmu:
+ /*
+ * We save a bunch of GPRs,
+ * r3 can be different from GPR3(r1) at this point, r9 and r11
+ * contains the old MSR and handler address respectively,
+ * r4 & r5 can contain page fault arguments that need to be passed
+ * along as well. r0, r6-r8, r12, CCR, CTR, XER etc... are left
+ * clobbered as they aren't useful past this point.
+ */
+
+ stwu r1,-32(r1)
+ stw r9,8(r1)
+ stw r11,12(r1)
+ stw r3,16(r1)
+ stw r4,20(r1)
+ stw r5,24(r1)
+
+ /* If we are disabling interrupts (normal case), simply log it with
+ * lockdep
+ */
+1: bl trace_hardirqs_off
+ lwz r5,24(r1)
+ lwz r4,20(r1)
+ lwz r3,16(r1)
+ lwz r11,12(r1)
+ lwz r9,8(r1)
+ addi r1,r1,32
+ mtctr r11
+ mtlr r9
+ bctr /* jump to handler */
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
+#ifndef CONFIG_VMAP_STACK
/*
* On kernel stack overflow, load up an initial stack pointer
* and call StackOverflow(regs), which should not return.
@@ -311,8 +321,9 @@
#endif
mtspr SPRN_SRR0,r9
mtspr SPRN_SRR1,r10
- SYNC
RFI
+_ASM_NOKPROBE_SYMBOL(stack_ovf)
+#endif
#ifdef CONFIG_TRACE_IRQFLAGS
trace_syscall_entry_irq_off:
@@ -400,8 +411,7 @@
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
- SYNC
- MTMSRD(r10)
+ mtmsr r10
lwz r9,TI_FLAGS(r2)
li r8,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
@@ -457,13 +467,14 @@
lwz r7,_NIP(r1)
lwz r2,GPR2(r1)
lwz r1,GPR1(r1)
+syscall_exit_finish:
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
mtspr SPRN_SRR0,r7
mtspr SPRN_SRR1,r8
- SYNC
RFI
+_ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
#ifdef CONFIG_44x
2: li r7,0
iccci r0,r0
@@ -543,9 +554,6 @@
addi r12,r2,TI_FLAGS
3: lwarx r8,0,r12
andc r8,r8,r11
-#ifdef CONFIG_IBM405_ERR77
- dcbt 0,r12
-#endif
stwcx. r8,0,r12
bne- 3b
@@ -557,8 +565,7 @@
* lockdep as we are supposed to have IRQs on at this point
*/
ori r10,r10,MSR_EE
- SYNC
- MTMSRD(r10)
+ mtmsr r10
/* Save NVGPRS if they're not saved already */
lwz r4,_TRAP(r1)
@@ -572,6 +579,33 @@
bl do_syscall_trace_leave
b ret_from_except_full
+ /*
+ * System call was called from kernel. We get here with SRR1 in r9.
+ * Mark the exception as recoverable once we have retrieved SRR0,
+ * trap a warning and return ENOSYS with CR[SO] set.
+ */
+ .globl ret_from_kernel_syscall
+ret_from_kernel_syscall:
+ mfspr r9, SPRN_SRR0
+ mfspr r10, SPRN_SRR1
+#if !defined(CONFIG_4xx) && !defined(CONFIG_BOOKE)
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_IR|MSR_DR))
+ mtmsr r11
+#endif
+
+0: trap
+ EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+
+ li r3, ENOSYS
+ crset so
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
+ mtspr SPRN_NRI, r0
+#endif
+ mtspr SPRN_SRR0, r9
+ mtspr SPRN_SRR1, r10
+ RFI
+_ASM_NOKPROBE_SYMBOL(ret_from_kernel_syscall)
+
/*
* The fork/clone functions need to copy the full register set into
* the child process. Therefore we need to save all the nonvolatile
@@ -625,7 +659,6 @@
*/
.globl handle_page_fault
handle_page_fault:
- stw r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_BOOK3S_32
andis. r0,r5,DSISR_DABRMATCH@h
@@ -701,7 +734,7 @@
and. r0,r0,r11 /* FP or altivec or SPE enabled? */
beq+ 1f
andc r11,r11,r0
- MTMSRD(r11)
+ mtmsr r11
isync
1: stw r11,_MSR(r1)
mfcr r10
@@ -773,27 +806,19 @@
REST_GPR(9, r11)
REST_GPR(12, r11)
lwz r11,GPR11(r11)
- SYNC
RFI
+_ASM_NOKPROBE_SYMBOL(fast_exception_return)
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
/* check if the exception happened in a restartable section */
1: lis r3,exc_exit_restart_end@ha
addi r3,r3,exc_exit_restart_end@l
cmplw r12,r3
-#ifdef CONFIG_PPC_BOOK3S_601
- bge 2b
-#else
bge 3f
-#endif
lis r4,exc_exit_restart@ha
addi r4,r4,exc_exit_restart@l
cmplw r12,r4
-#ifdef CONFIG_PPC_BOOK3S_601
- blt 2b
-#else
blt 3f
-#endif
lis r3,fee_restarts@ha
tophys(r3,r3)
lwz r5,fee_restarts@l(r3)
@@ -810,7 +835,6 @@
/* aargh, a nonrecoverable interrupt, panic */
/* aargh, we don't know which trap this is */
-/* but the 601 doesn't implement the RI bit, so assume it's OK */
3:
li r10,-1
stw r10,_TRAP(r11)
@@ -834,8 +858,7 @@
* from the interrupt. */
/* Note: We don't bother telling lockdep about it */
LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
- SYNC /* Some chip revs have problems here... */
- MTMSRD(r10) /* disable interrupts */
+ mtmsr r10 /* disable interrupts */
lwz r3,_MSR(r1) /* Returning to user mode? */
andi. r0,r3,MSR_PR
@@ -894,14 +917,11 @@
addi r5,r2,TI_FLAGS
0: lwarx r8,0,r5
andc r8,r8,r11
-#ifdef CONFIG_IBM405_ERR77
- dcbt 0,r5
-#endif
stwcx. r8,0,r5
bne- 0b
1:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
/* check current_thread_info->preempt_count */
lwz r0,TI_PREEMPT(r2)
cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
@@ -925,7 +945,7 @@
*/
bl trace_hardirqs_on
#endif
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
restore_kuap:
kuap_restore r1, r2, r9, r10, r0
@@ -973,7 +993,6 @@
mtspr SPRN_XER,r10
mtctr r11
- PPC405_ERR77(0,r1)
BEGIN_FTR_SECTION
lwarx r11,0,r1
END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
@@ -1001,8 +1020,7 @@
* exc_exit_restart below. -- paulus
*/
LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
- SYNC
- MTMSRD(r10) /* clear the RI bit */
+ mtmsr r10 /* clear the RI bit */
.globl exc_exit_restart
exc_exit_restart:
lwz r12,_NIP(r1)
@@ -1012,8 +1030,9 @@
lwz r1,GPR1(r1)
.globl exc_exit_restart_end
exc_exit_restart_end:
- SYNC
RFI
+_ASM_NOKPROBE_SYMBOL(exc_exit_restart)
+_ASM_NOKPROBE_SYMBOL(exc_exit_restart_end)
#else /* !(CONFIG_4xx || CONFIG_BOOKE) */
/*
@@ -1035,16 +1054,15 @@
exc_exit_restart:
lwz r11,_NIP(r1)
lwz r12,_MSR(r1)
-exc_exit_start:
mtspr SPRN_SRR0,r11
mtspr SPRN_SRR1,r12
REST_2GPRS(11, r1)
lwz r1,GPR1(r1)
.globl exc_exit_restart_end
exc_exit_restart_end:
- PPC405_ERR77_SYNC
rfi
b . /* prevent prefetch past rfi */
+_ASM_NOKPROBE_SYMBOL(exc_exit_restart)
/*
* Returning from a critical interrupt in user mode doesn't need
@@ -1085,7 +1103,6 @@
lwz r11,_CTR(r1); \
mtspr SPRN_XER,r10; \
mtctr r11; \
- PPC405_ERR77(0,r1); \
stwcx. r0,0,r1; /* to clear the reservation */ \
lwz r11,_LINK(r1); \
mtlr r11; \
@@ -1105,7 +1122,6 @@
lwz r10,GPR10(r1); \
lwz r11,GPR11(r1); \
lwz r1,GPR1(r1); \
- PPC405_ERR77_SYNC; \
exc_lvl_rfi; \
b .; /* prevent prefetch past exc_lvl_rfi */
@@ -1158,6 +1174,7 @@
mtspr SPRN_SRR0,r9;
mtspr SPRN_SRR1,r10;
RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
#endif /* CONFIG_40x */
#ifdef CONFIG_BOOKE
@@ -1169,6 +1186,7 @@
RESTORE_xSRR(SRR0,SRR1);
RESTORE_MMU_REGS;
RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
.globl ret_from_debug_exc
ret_from_debug_exc:
@@ -1179,6 +1197,7 @@
RESTORE_xSRR(CSRR0,CSRR1);
RESTORE_MMU_REGS;
RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, PPC_RFDI)
+_ASM_NOKPROBE_SYMBOL(ret_from_debug_exc)
.globl ret_from_mcheck_exc
ret_from_mcheck_exc:
@@ -1190,6 +1209,7 @@
RESTORE_xSRR(DSRR0,DSRR1);
RESTORE_MMU_REGS;
RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, PPC_RFMCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_mcheck_exc)
#endif /* CONFIG_BOOKE */
/*
@@ -1237,8 +1257,7 @@
mfmsr r10
#endif
ori r10,r10,MSR_EE
- SYNC
- MTMSRD(r10) /* hard-enable interrupts */
+ mtmsr r10 /* hard-enable interrupts */
bl schedule
recheck:
/* Note: And we don't tell it we are disabling them again
@@ -1246,8 +1265,7 @@
* TI_FLAGS aren't advertised.
*/
LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
- SYNC
- MTMSRD(r10) /* disable interrupts */
+ mtmsr r10 /* disable interrupts */
lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_NEED_RESCHED
bne- do_resched
@@ -1255,8 +1273,7 @@
beq restore_user
do_user_signal: /* r10 contains MSR_KERNEL here */
ori r10,r10,MSR_EE
- SYNC
- MTMSRD(r10) /* hard-enable interrupts */
+ mtmsr r10 /* hard-enable interrupts */
/* save r13-r31 in the exception frame, if not already done */
lwz r3,_TRAP(r1)
andi. r0,r3,1
@@ -1279,19 +1296,11 @@
lis r10,exc_exit_restart_end@ha
addi r10,r10,exc_exit_restart_end@l
cmplw r12,r10
-#ifdef CONFIG_PPC_BOOK3S_601
- bgelr
-#else
bge 3f
-#endif
lis r11,exc_exit_restart@ha
addi r11,r11,exc_exit_restart@l
cmplw r12,r11
-#ifdef CONFIG_PPC_BOOK3S_601
- bltlr
-#else
blt 3f
-#endif
lis r10,ee_restarts@ha
lwz r12,ee_restarts@l(r10)
addi r12,r12,1
@@ -1299,7 +1308,6 @@
mr r12,r11 /* restart at exc_exit_restart */
blr
3: /* OK, we can't recover, kill this process */
- /* but the 601 doesn't implement the RI bit, so assume it's OK */
lwz r3,_TRAP(r1)
andi. r0,r3,1
beq 5f
@@ -1313,6 +1321,7 @@
bl unrecoverable_exception
/* shouldn't return */
b 4b
+_ASM_NOKPROBE_SYMBOL(nonrecoverable)
.section .bss
.align 2
@@ -1338,34 +1347,33 @@
lis r6,1f@ha /* physical return address for rtas */
addi r6,r6,1f@l
tophys(r6,r6)
- tophys(r7,r1)
+ tophys_novmstack r7, r1
lwz r8,RTASENTRY(r4)
lwz r4,RTASBASE(r4)
mfmsr r9
stw r9,8(r1)
LOAD_REG_IMMEDIATE(r0,MSR_KERNEL)
- SYNC /* disable interrupts so SRR0/1 */
- MTMSRD(r0) /* don't get trashed */
+ mtmsr r0 /* disable interrupts so SRR0/1 don't get trashed */
li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
mtlr r6
stw r7, THREAD + RTAS_SP(r2)
mtspr SPRN_SRR0,r8
mtspr SPRN_SRR1,r9
RFI
-1: tophys(r9,r1)
+1: tophys_novmstack r9, r1
+#ifdef CONFIG_VMAP_STACK
+ li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */
+ mtmsr r0
+ isync
+#endif
lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */
lwz r9,8(r9) /* original msr value */
addi r1,r1,INT_FRAME_SIZE
li r0,0
- tophys(r7, r2)
+ tophys_novmstack r7, r2
stw r0, THREAD + RTAS_SP(r7)
mtspr SPRN_SRR0,r8
mtspr SPRN_SRR1,r9
RFI /* return to caller */
-
- .globl machine_check_in_rtas
-machine_check_in_rtas:
- twi 31,0,0
- /* XXX load up BATs and panic */
-
+_ASM_NOKPROBE_SYMBOL(enter_rtas)
#endif /* CONFIG_PPC_RTAS */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3fd3ef3..2831b0a 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -16,6 +16,7 @@
#include <linux/errno.h>
#include <linux/err.h>
+#include <asm/cache.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
@@ -51,8 +52,10 @@
SYS_CALL_TABLE:
.tc sys_call_table[TC],sys_call_table
+#ifdef CONFIG_COMPAT
COMPAT_SYS_CALL_TABLE:
.tc compat_sys_call_table[TC],compat_sys_call_table
+#endif
/* This value is used to mark exception frames on the stack. */
exception_marker:
@@ -61,8 +64,171 @@
.section ".text"
.align 7
+#ifdef CONFIG_PPC_BOOK3S
+.macro system_call_vectored name trapnr
+ .globl system_call_vectored_\name
+system_call_vectored_\name:
+_ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+ bne .Ltabort_syscall
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+ SCV_INTERRUPT_TO_KERNEL
+ mr r10,r1
+ ld r1,PACAKSAVE(r13)
+ std r10,0(r1)
+ std r11,_NIP(r1)
+ std r12,_MSR(r1)
+ std r0,GPR0(r1)
+ std r10,GPR1(r1)
+ std r2,GPR2(r1)
+ ld r2,PACATOC(r13)
+ mfcr r12
+ li r11,0
+ /* Can we avoid saving r3-r8 in common case? */
+ std r3,GPR3(r1)
+ std r4,GPR4(r1)
+ std r5,GPR5(r1)
+ std r6,GPR6(r1)
+ std r7,GPR7(r1)
+ std r8,GPR8(r1)
+ /* Zero r9-r12, this should only be required when restoring all GPRs */
+ std r11,GPR9(r1)
+ std r11,GPR10(r1)
+ std r11,GPR11(r1)
+ std r11,GPR12(r1)
+ std r9,GPR13(r1)
+ SAVE_NVGPRS(r1)
+ std r11,_XER(r1)
+ std r11,_LINK(r1)
+ std r11,_CTR(r1)
+
+ li r11,\trapnr
+ std r11,_TRAP(r1)
+ std r12,_CCR(r1)
+ std r3,ORIG_GPR3(r1)
+ addi r10,r1,STACK_FRAME_OVERHEAD
+ ld r11,exception_marker@toc(r2)
+ std r11,-16(r10) /* "regshere" marker */
+
+BEGIN_FTR_SECTION
+ HMT_MEDIUM
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ /*
+ * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
+ * would clobber syscall parameters. Also we always enter with IRQs
+ * enabled and nothing pending. system_call_exception() will call
+ * trace_hardirqs_off().
+ *
+ * scv enters with MSR[EE]=1, so don't set PACA_IRQ_HARD_DIS. The
+ * entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED.
+ */
+
+ /* Calling convention has r9 = orig r0, r10 = regs */
+ mr r9,r0
+ bl system_call_exception
+
+.Lsyscall_vectored_\name\()_exit:
+ addi r4,r1,STACK_FRAME_OVERHEAD
+ li r5,1 /* scv */
+ bl syscall_exit_prepare
+
+ ld r2,_CCR(r1)
+ ld r4,_NIP(r1)
+ ld r5,_MSR(r1)
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+BEGIN_FTR_SECTION
+ HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ cmpdi r3,0
+ bne .Lsyscall_vectored_\name\()_restore_regs
+
+ /* rfscv returns with LR->NIA and CTR->MSR */
+ mtlr r4
+ mtctr r5
+
+ /* Could zero these as per ABI, but we may consider a stricter ABI
+ * which preserves these if libc implementations can benefit, so
+ * restore them for now until further measurement is done. */
+ ld r0,GPR0(r1)
+ ld r4,GPR4(r1)
+ ld r5,GPR5(r1)
+ ld r6,GPR6(r1)
+ ld r7,GPR7(r1)
+ ld r8,GPR8(r1)
+ /* Zero volatile regs that may contain sensitive kernel data */
+ li r9,0
+ li r10,0
+ li r11,0
+ li r12,0
+ mtspr SPRN_XER,r0
+
+ /*
+ * We don't need to restore AMR on the way back to userspace for KUAP.
+ * The value of AMR only matters while we're in the kernel.
+ */
+ mtcr r2
+ ld r2,GPR2(r1)
+ ld r3,GPR3(r1)
+ ld r13,GPR13(r1)
+ ld r1,GPR1(r1)
+ RFSCV_TO_USER
+ b . /* prevent speculative execution */
+
+.Lsyscall_vectored_\name\()_restore_regs:
+ li r3,0
+ mtmsrd r3,1
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r5
+
+ ld r3,_CTR(r1)
+ ld r4,_LINK(r1)
+ ld r5,_XER(r1)
+
+ REST_NVGPRS(r1)
+ ld r0,GPR0(r1)
+ mtcr r2
+ mtctr r3
+ mtlr r4
+ mtspr SPRN_XER,r5
+ REST_10GPRS(2, r1)
+ REST_2GPRS(12, r1)
+ ld r1,GPR1(r1)
+ RFI_TO_USER
+.endm
+
+system_call_vectored common 0x3000
+/*
+ * We instantiate another entry copy for the SIGILL variant, with TRAP=0x7ff0
+ * which is tested by system_call_exception when r0 is -1 (as set by vector
+ * entry code).
+ */
+system_call_vectored sigill 0x7ff0
+
+
+/*
+ * Entered via kernel return set up by kernel/sstep.c, must match entry regs
+ */
+ .globl system_call_vectored_emulate
+system_call_vectored_emulate:
+_ASM_NOKPROBE_SYMBOL(system_call_vectored_emulate)
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ b system_call_vectored_common
+#endif
+
+ .balign IFETCH_ALIGN_BYTES
.globl system_call_common
system_call_common:
+_ASM_NOKPROBE_SYMBOL(system_call_common)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
@@ -76,342 +242,123 @@
std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
+ std r2,GPR2(r1)
#ifdef CONFIG_PPC_FSL_BOOK3E
START_BTB_FLUSH_SECTION
BTB_FLUSH(r10)
END_BTB_FLUSH_SECTION
#endif
- ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
- std r2,GPR2(r1)
+ ld r2,PACATOC(r13)
+ mfcr r12
+ li r11,0
+ /* Can we avoid saving r3-r8 in common case? */
std r3,GPR3(r1)
- mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
std r7,GPR7(r1)
std r8,GPR8(r1)
- li r11,0
+ /* Zero r9-r12, this should only be required when restoring all GPRs */
std r11,GPR9(r1)
std r11,GPR10(r1)
std r11,GPR11(r1)
std r11,GPR12(r1)
+ std r9,GPR13(r1)
+ SAVE_NVGPRS(r1)
std r11,_XER(r1)
std r11,_CTR(r1)
- std r9,GPR13(r1)
mflr r10
+
/*
* This clears CR0.SO (bit 28), which is the error indication on
* return from this system call.
*/
- rldimi r2,r11,28,(63-28)
- li r11,0xc01
+ rldimi r12,r11,28,(63-28)
+ li r11,0xc00
std r10,_LINK(r1)
std r11,_TRAP(r1)
+ std r12,_CCR(r1)
std r3,ORIG_GPR3(r1)
- std r2,_CCR(r1)
- ld r2,PACATOC(r13)
- addi r9,r1,STACK_FRAME_OVERHEAD
+ addi r10,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
- std r11,-16(r9) /* "regshere" marker */
-
- kuap_check_amr r10, r11
-
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
-BEGIN_FW_FTR_SECTION
- /* see if there are any DTL entries to process */
- ld r10,PACALPPACAPTR(r13) /* get ptr to VPA */
- ld r11,PACA_DTL_RIDX(r13) /* get log read index */
- addi r10,r10,LPPACA_DTLIDX
- LDX_BE r10,0,r10 /* get log write index */
- cmpd r11,r10
- beq+ 33f
- bl accumulate_stolen_time
- REST_GPR(0,r1)
- REST_4GPRS(3,r1)
- REST_2GPRS(7,r1)
- addi r9,r1,STACK_FRAME_OVERHEAD
-33:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
+ std r11,-16(r10) /* "regshere" marker */
/*
- * A syscall should always be called with interrupts enabled
- * so we just unconditionally hard-enable here. When some kind
- * of irq tracing is used, we additionally check that condition
- * is correct
+ * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
+ * would clobber syscall parameters. Also we always enter with IRQs
+ * enabled and nothing pending. system_call_exception() will call
+ * trace_hardirqs_off().
*/
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
- lbz r10,PACAIRQSOFTMASK(r13)
-1: tdnei r10,IRQS_ENABLED
- EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
+ li r11,IRQS_ALL_DISABLED
+ li r12,PACA_IRQ_HARD_DIS
+ stb r11,PACAIRQSOFTMASK(r13)
+ stb r12,PACAIRQHAPPENED(r13)
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 1
-#else
- li r11,MSR_RI
- ori r11,r11,MSR_EE
- mtmsrd r11,1
-#endif /* CONFIG_PPC_BOOK3E */
+ /* Calling convention has r9 = orig r0, r10 = regs */
+ mr r9,r0
+ bl system_call_exception
-system_call: /* label this so stack traces look sane */
- /* We do need to set SOFTE in the stack frame or the return
- * from interrupt will be painful
- */
- li r10,IRQS_ENABLED
- std r10,SOFTE(r1)
-
- ld r11, PACA_THREAD_INFO(r13)
- ld r10,TI_FLAGS(r11)
- andi. r11,r10,_TIF_SYSCALL_DOTRACE
- bne .Lsyscall_dotrace /* does not return */
- cmpldi 0,r0,NR_syscalls
- bge- .Lsyscall_enosys
-
-.Lsyscall:
-/*
- * Need to vector to 32 Bit or default sys_call_table here,
- * based on caller's run-mode / personality.
- */
- ld r11,SYS_CALL_TABLE@toc(2)
- andis. r10,r10,_TIF_32BIT@h
- beq 15f
- ld r11,COMPAT_SYS_CALL_TABLE@toc(2)
- clrldi r3,r3,32
- clrldi r4,r4,32
- clrldi r5,r5,32
- clrldi r6,r6,32
- clrldi r7,r7,32
- clrldi r8,r8,32
-15:
- slwi r0,r0,3
-
- barrier_nospec_asm
- /*
- * Prevent the load of the handler below (based on the user-passed
- * system call number) being speculatively executed until the test
- * against NR_syscalls and branch to .Lsyscall_enosys above has
- * committed.
- */
-
- ldx r12,r11,r0 /* Fetch system call handler [ptr] */
- mtctr r12
- bctrl /* Call handler */
-
- /* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
.Lsyscall_exit:
- std r3,RESULT(r1)
+ addi r4,r1,STACK_FRAME_OVERHEAD
+ li r5,0 /* !scv */
+ bl syscall_exit_prepare
-#ifdef CONFIG_DEBUG_RSEQ
- /* Check whether the syscall is issued inside a restartable sequence */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl rseq_syscall
- ld r3,RESULT(r1)
-#endif
+ ld r2,_CCR(r1)
+ ld r4,_NIP(r1)
+ ld r5,_MSR(r1)
+ ld r6,_LINK(r1)
- ld r12, PACA_THREAD_INFO(r13)
-
- ld r8,_MSR(r1)
-
-/*
- * This is a few instructions into the actual syscall exit path (which actually
- * starts at .Lsyscall_exit) to cater to kprobe blacklisting and to reduce the
- * number of visible symbols for profiling purposes.
- *
- * We can probe from system_call until this point as MSR_RI is set. But once it
- * is cleared below, we won't be able to take a trap.
- *
- * This is blacklisted from kprobes further below with _ASM_NOKPROBE_SYMBOL().
- */
-system_call_exit:
- /*
- * Disable interrupts so current_thread_info()->flags can't change,
- * and so that we don't get interrupted after loading SRR0/1.
- *
- * Leave MSR_RI enabled for now, because with THREAD_INFO_IN_TASK we
- * could fault on the load of the TI_FLAGS below.
- */
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 0
-#else
- li r11,MSR_RI
- mtmsrd r11,1
-#endif /* CONFIG_PPC_BOOK3E */
-
- ld r9,TI_FLAGS(r12)
- li r11,-MAX_ERRNO
- andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
- bne- .Lsyscall_exit_work
-
- andi. r0,r8,MSR_FP
- beq 2f
-#ifdef CONFIG_ALTIVEC
- andis. r0,r8,MSR_VEC@h
- bne 3f
-#endif
-2: addi r3,r1,STACK_FRAME_OVERHEAD
- bl restore_math
- ld r8,_MSR(r1)
- ld r3,RESULT(r1)
- li r11,-MAX_ERRNO
-
-3: cmpld r3,r11
- ld r5,_CCR(r1)
- bge- .Lsyscall_error
-.Lsyscall_error_cont:
- ld r7,_NIP(r1)
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
- andi. r6,r8,MSR_PR
- ld r4,_LINK(r1)
- kuap_check_amr r10, r11
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r5
+ mtlr r6
-#ifdef CONFIG_PPC_BOOK3S
- /*
- * Clear MSR_RI, MSR_EE is already and remains disabled. We could do
- * this later, but testing shows that doing it here causes less slow
- * down than doing it closer to the rfid.
- */
+ cmpdi r3,0
+ bne .Lsyscall_restore_regs
+ /* Zero volatile regs that may contain sensitive kernel data */
+ li r0,0
+ li r4,0
+ li r5,0
+ li r6,0
+ li r7,0
+ li r8,0
+ li r9,0
+ li r10,0
li r11,0
- mtmsrd r11,1
-#endif
-
- beq- 1f
- ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
+ li r12,0
+ mtctr r0
+ mtspr SPRN_XER,r0
+.Lsyscall_restore_regs_cont:
BEGIN_FTR_SECTION
HMT_MEDIUM_LOW
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- std r8, PACATMSCRATCH(r13)
-#endif
-
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
* The value of AMR only matters while we're in the kernel.
*/
- ld r13,GPR13(r1) /* only restore r13 if returning to usermode */
+ mtcr r2
ld r2,GPR2(r1)
+ ld r3,GPR3(r1)
+ ld r13,GPR13(r1)
ld r1,GPR1(r1)
- mtlr r4
- mtcr r5
- mtspr SPRN_SRR0,r7
- mtspr SPRN_SRR1,r8
RFI_TO_USER
b . /* prevent speculative execution */
-1: /* exit to kernel */
- kuap_restore_amr r2
-
- ld r2,GPR2(r1)
- ld r1,GPR1(r1)
- mtlr r4
- mtcr r5
- mtspr SPRN_SRR0,r7
- mtspr SPRN_SRR1,r8
- RFI_TO_KERNEL
- b . /* prevent speculative execution */
-
-.Lsyscall_error:
- oris r5,r5,0x1000 /* Set SO bit in CR */
- neg r3,r3
- std r5,_CCR(r1)
- b .Lsyscall_error_cont
-
-/* Traced system call support */
-.Lsyscall_dotrace:
- bl save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_syscall_trace_enter
-
- /*
- * We use the return value of do_syscall_trace_enter() as the syscall
- * number. If the syscall was rejected for any reason do_syscall_trace_enter()
- * returns an invalid syscall number and the test below against
- * NR_syscalls will fail.
- */
- mr r0,r3
-
- /* Restore argument registers just clobbered and/or possibly changed. */
- ld r3,GPR3(r1)
- ld r4,GPR4(r1)
- ld r5,GPR5(r1)
- ld r6,GPR6(r1)
- ld r7,GPR7(r1)
- ld r8,GPR8(r1)
-
- /* Repopulate r9 and r10 for the syscall path */
- addi r9,r1,STACK_FRAME_OVERHEAD
- ld r10, PACA_THREAD_INFO(r13)
- ld r10,TI_FLAGS(r10)
-
- cmpldi r0,NR_syscalls
- blt+ .Lsyscall
-
- /* Return code is already in r3 thanks to do_syscall_trace_enter() */
- b .Lsyscall_exit
-
-
-.Lsyscall_enosys:
- li r3,-ENOSYS
- b .Lsyscall_exit
-
-.Lsyscall_exit_work:
- /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
- If TIF_NOERROR is set, just save r3 as it is. */
-
- andi. r0,r9,_TIF_RESTOREALL
- beq+ 0f
+.Lsyscall_restore_regs:
+ ld r3,_CTR(r1)
+ ld r4,_XER(r1)
REST_NVGPRS(r1)
- b 2f
-0: cmpld r3,r11 /* r11 is -MAX_ERRNO */
- blt+ 1f
- andi. r0,r9,_TIF_NOERROR
- bne- 1f
- ld r5,_CCR(r1)
- neg r3,r3
- oris r5,r5,0x1000 /* Set SO bit in CR */
- std r5,_CCR(r1)
-1: std r3,GPR3(r1)
-2: andi. r0,r9,(_TIF_PERSYSCALL_MASK)
- beq 4f
-
- /* Clear per-syscall TIF flags if any are set. */
-
- li r11,_TIF_PERSYSCALL_MASK
- addi r12,r12,TI_FLAGS
-3: ldarx r10,0,r12
- andc r10,r10,r11
- stdcx. r10,0,r12
- bne- 3b
- subi r12,r12,TI_FLAGS
-
-4: /* Anything else left to do? */
-BEGIN_FTR_SECTION
- lis r3,DEFAULT_PPR@highest /* Set default PPR */
- sldi r3,r3,32 /* bits 11-13 are used for ppr */
- std r3,_PPR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-
- andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
- beq ret_from_except_lite
-
- /* Re-enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 1
-#else
- li r10,MSR_RI
- ori r10,r10,MSR_EE
- mtmsrd r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
- bl save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_syscall_trace_leave
- b ret_from_except
+ mtctr r3
+ mtspr SPRN_XER,r4
+ ld r0,GPR0(r1)
+ REST_8GPRS(4, r1)
+ ld r12,GPR12(r1)
+ b .Lsyscall_restore_regs_cont
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
.Ltabort_syscall:
@@ -439,9 +386,34 @@
RFI_TO_USER
b . /* prevent speculative execution */
#endif
-_ASM_NOKPROBE_SYMBOL(system_call_common);
-_ASM_NOKPROBE_SYMBOL(system_call_exit);
+#ifdef CONFIG_PPC_BOOK3S
+_GLOBAL(ret_from_fork_scv)
+ bl schedule_tail
+ REST_NVGPRS(r1)
+ li r3,0 /* fork() return value */
+ b .Lsyscall_vectored_common_exit
+#endif
+
+_GLOBAL(ret_from_fork)
+ bl schedule_tail
+ REST_NVGPRS(r1)
+ li r3,0 /* fork() return value */
+ b .Lsyscall_exit
+
+_GLOBAL(ret_from_kernel_thread)
+ bl schedule_tail
+ REST_NVGPRS(r1)
+ mtctr r14
+ mr r3,r15
+#ifdef PPC64_ELF_ABI_v2
+ mr r12,r14
+#endif
+ bctrl
+ li r3,0
+ b .Lsyscall_exit
+
+#ifdef CONFIG_PPC_BOOK3E
/* Save non-volatile GPRs, if not already saved. */
_GLOBAL(save_nvgprs)
ld r11,_TRAP(r1)
@@ -452,78 +424,17 @@
std r0,_TRAP(r1)
blr
_ASM_NOKPROBE_SYMBOL(save_nvgprs);
-
-
-/*
- * The sigsuspend and rt_sigsuspend system calls can call do_signal
- * and thus put the process into the stopped state where we might
- * want to examine its user state with ptrace. Therefore we need
- * to save all the nonvolatile registers (r14 - r31) before calling
- * the C code. Similarly, fork, vfork and clone need the full
- * register state on the stack so that it can be copied to the child.
- */
-
-_GLOBAL(ppc_fork)
- bl save_nvgprs
- bl sys_fork
- b .Lsyscall_exit
-
-_GLOBAL(ppc_vfork)
- bl save_nvgprs
- bl sys_vfork
- b .Lsyscall_exit
-
-_GLOBAL(ppc_clone)
- bl save_nvgprs
- bl sys_clone
- b .Lsyscall_exit
-
-_GLOBAL(ppc_clone3)
- bl save_nvgprs
- bl sys_clone3
- b .Lsyscall_exit
-
-_GLOBAL(ppc32_swapcontext)
- bl save_nvgprs
- bl compat_sys_swapcontext
- b .Lsyscall_exit
-
-_GLOBAL(ppc64_swapcontext)
- bl save_nvgprs
- bl sys_swapcontext
- b .Lsyscall_exit
-
-_GLOBAL(ppc_switch_endian)
- bl save_nvgprs
- bl sys_switch_endian
- b .Lsyscall_exit
-
-_GLOBAL(ret_from_fork)
- bl schedule_tail
- REST_NVGPRS(r1)
- li r3,0
- b .Lsyscall_exit
-
-_GLOBAL(ret_from_kernel_thread)
- bl schedule_tail
- REST_NVGPRS(r1)
- mtlr r14
- mr r3,r15
-#ifdef PPC64_ELF_ABI_v2
- mr r12,r14
#endif
- blrl
- li r3,0
- b .Lsyscall_exit
#ifdef CONFIG_PPC_BOOK3S_64
#define FLUSH_COUNT_CACHE \
1: nop; \
- patch_site 1b, patch__call_flush_count_cache
-
-
-#define BCCTR_FLUSH .long 0x4c400420
+ patch_site 1b, patch__call_flush_branch_caches1; \
+1: nop; \
+ patch_site 1b, patch__call_flush_branch_caches2; \
+1: nop; \
+ patch_site 1b, patch__call_flush_branch_caches3
.macro nops number
.rept \number
@@ -532,8 +443,8 @@
.endm
.balign 32
-.global flush_count_cache
-flush_count_cache:
+.global flush_branch_caches
+flush_branch_caches:
/* Save LR into r9 */
mflr r9
@@ -555,7 +466,7 @@
li r9,0x7fff
mtctr r9
- BCCTR_FLUSH
+ PPC_BCCTR_FLUSH
2: nop
patch_site 2b patch__flush_count_cache_return
@@ -564,7 +475,7 @@
.rept 278
.balign 32
- BCCTR_FLUSH
+ PPC_BCCTR_FLUSH
nops 7
.endr
@@ -578,7 +489,7 @@
* state of one is saved on its kernel stack. Then the state
* of the other is restored from its kernel stack. The memory
* management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via ret_from_except.
+ * Finally, we can return to the second process, via interrupt_return.
* On entry, r3 points to the THREAD for the current task, r4
* points to the THREAD for the new task.
*
@@ -597,8 +508,7 @@
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1)
/* r3-r13 are caller saved -- Cort */
- SAVE_8GPRS(14, r1)
- SAVE_10GPRS(22, r1)
+ SAVE_NVGPRS(r1)
std r0,_NIP(r1) /* Return to switch caller */
mfcr r23
std r23,_CCR(r1)
@@ -606,7 +516,7 @@
kuap_check_amr r9, r10
- FLUSH_COUNT_CACHE
+ FLUSH_COUNT_CACHE /* Clobbers r9, ctr */
/*
* On SMP kernels, care must be taken because a task may be
@@ -619,7 +529,7 @@
* kernel/sched/core.c).
*
* Uncacheable stores in the case of involuntary preemption must
- * be taken care of. The smp_mb__before_spin_lock() in __schedule()
+ * be taken care of. The smp_mb__after_spinlock() in __schedule()
* is implemented as hwsync on powerpc, which orders MMIO too. So
* long as there is an hwsync in the context switch path, it will
* be executed on the source CPU after the task has performed
@@ -722,8 +632,7 @@
mtcrf 0xFF,r6
/* r3-r13 are destroyed -- Cort */
- REST_8GPRS(14, r1)
- REST_10GPRS(22, r1)
+ REST_NVGPRS(r1)
/* convert old thread to its task_struct for return value */
addi r3,r3,-THREAD
@@ -732,408 +641,148 @@
addi r1,r1,SWITCH_FRAME_SIZE
blr
- .align 7
-_GLOBAL(ret_from_except)
- ld r11,_TRAP(r1)
- andi. r0,r11,1
- bne ret_from_except_lite
- REST_NVGPRS(r1)
-
-_GLOBAL(ret_from_except_lite)
+#ifdef CONFIG_PPC_BOOK3S
/*
- * Disable interrupts so that current_thread_info()->flags
- * can't change between when we test it and when we return
- * from the interrupt.
+ * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
+ * touched, no exit work created, then this can be used.
*/
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 0
-#else
- li r10,MSR_RI
- mtmsrd r10,1 /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-
- ld r9, PACA_THREAD_INFO(r13)
- ld r3,_MSR(r1)
-#ifdef CONFIG_PPC_BOOK3E
- ld r10,PACACURRENT(r13)
-#endif /* CONFIG_PPC_BOOK3E */
- ld r4,TI_FLAGS(r9)
- andi. r3,r3,MSR_PR
- beq resume_kernel
-#ifdef CONFIG_PPC_BOOK3E
- lwz r3,(THREAD+THREAD_DBCR0)(r10)
-#endif /* CONFIG_PPC_BOOK3E */
-
- /* Check current_thread_info()->flags */
- andi. r0,r4,_TIF_USER_WORK_MASK
- bne 1f
-#ifdef CONFIG_PPC_BOOK3E
- /*
- * Check to see if the dbcr0 register is set up to debug.
- * Use the internal debug mode bit to do this.
- */
- andis. r0,r3,DBCR0_IDM@h
- beq restore
- mfmsr r0
- rlwinm r0,r0,0,~MSR_DE /* Clear MSR.DE */
- mtmsr r0
- mtspr SPRN_DBCR0,r3
- li r10, -1
- mtspr SPRN_DBSR,r10
- b restore
-#else
+ .balign IFETCH_ALIGN_BYTES
+ .globl fast_interrupt_return
+fast_interrupt_return:
+_ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
+ kuap_check_amr r3, r4
+ ld r5,_MSR(r1)
+ andi. r0,r5,MSR_PR
+ bne .Lfast_user_interrupt_return
+ kuap_restore_amr r3, r4
+ andi. r0,r5,MSR_RI
+ li r3,0 /* 0 return value, no EMULATE_STACK_STORE */
+ bne+ .Lfast_kernel_interrupt_return
addi r3,r1,STACK_FRAME_OVERHEAD
- bl restore_math
- b restore
-#endif
-1: andi. r0,r4,_TIF_NEED_RESCHED
- beq 2f
- bl restore_interrupts
- SCHEDULE_USER
- b ret_from_except_lite
-2:
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
- bne 3f /* only restore TM if nothing else to do */
+ bl unrecoverable_exception
+ b . /* should not get here */
+
+ .balign IFETCH_ALIGN_BYTES
+ .globl interrupt_return
+interrupt_return:
+_ASM_NOKPROBE_SYMBOL(interrupt_return)
+ ld r4,_MSR(r1)
+ andi. r0,r4,MSR_PR
+ beq .Lkernel_interrupt_return
addi r3,r1,STACK_FRAME_OVERHEAD
- bl restore_tm_state
- b restore
-3:
-#endif
- bl save_nvgprs
- /*
- * Use a non volatile GPR to save and restore our thread_info flags
- * across the call to restore_interrupts.
- */
- mr r30,r4
- bl restore_interrupts
- mr r4,r30
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_notify_resume
- b ret_from_except
+ bl interrupt_exit_user_prepare
+ cmpdi r3,0
+ bne- .Lrestore_nvgprs
-resume_kernel:
- /* check current_thread_info, _TIF_EMULATE_STACK_STORE */
- andis. r8,r4,_TIF_EMULATE_STACK_STORE@h
- beq+ 1f
+.Lfast_user_interrupt_return:
+ ld r11,_NIP(r1)
+ ld r12,_MSR(r1)
+BEGIN_FTR_SECTION
+ ld r10,_PPR(r1)
+ mtspr SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
- addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
-
- ld r3,GPR1(r1)
- subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
- mr r4,r1 /* src: current exception frame */
- mr r1,r3 /* Reroute the trampoline frame to r1 */
-
- /* Copy from the original to the trampoline. */
- li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */
- li r6,0 /* start offset: 0 */
- mtctr r5
-2: ldx r0,r6,r4
- stdx r0,r6,r3
- addi r6,r6,8
- bdnz 2b
-
- /* Do real store operation to complete stdu */
- ld r5,GPR1(r1)
- std r8,0(r5)
-
- /* Clear _TIF_EMULATE_STACK_STORE flag */
- lis r11,_TIF_EMULATE_STACK_STORE@h
- addi r5,r9,TI_FLAGS
-0: ldarx r4,0,r5
- andc r4,r4,r11
- stdcx. r4,0,r5
- bne- 0b
-1:
-
-#ifdef CONFIG_PREEMPT
- /* Check if we need to preempt */
- andi. r0,r4,_TIF_NEED_RESCHED
- beq+ restore
- /* Check that preempt_count() == 0 and interrupts are enabled */
- lwz r8,TI_PREEMPT(r9)
- cmpwi cr0,r8,0
- bne restore
- ld r0,SOFTE(r1)
- andi. r0,r0,IRQS_DISABLED
- bne restore
-
- /*
- * Here we are preempting the current task. We want to make
- * sure we are soft-disabled first and reconcile irq state.
- */
- RECONCILE_IRQ_STATE(r3,r4)
- bl preempt_schedule_irq
-
- /*
- * arch_local_irq_restore() from preempt_schedule_irq above may
- * enable hard interrupt but we really should disable interrupts
- * when we return from the interrupt, and so that we don't get
- * interrupted after loading SRR0/1.
- */
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 0
-#else
- li r10,MSR_RI
- mtmsrd r10,1 /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPT */
-
- .globl fast_exc_return_irq
-fast_exc_return_irq:
-restore:
- /*
- * This is the main kernel exit path. First we check if we
- * are about to re-enable interrupts
- */
- ld r5,SOFTE(r1)
- lbz r6,PACAIRQSOFTMASK(r13)
- andi. r5,r5,IRQS_DISABLED
- bne .Lrestore_irq_off
-
- /* We are enabling, were we already enabled ? Yes, just return */
- andi. r6,r6,IRQS_DISABLED
- beq cr0,.Ldo_restore
-
- /*
- * We are about to soft-enable interrupts (we are hard disabled
- * at this point). We check if there's anything that needs to
- * be replayed first.
- */
- lbz r0,PACAIRQHAPPENED(r13)
- cmpwi cr0,r0,0
- bne- .Lrestore_check_irq_replay
-
- /*
- * Get here when nothing happened while soft-disabled, just
- * soft-enable and move-on. We will hard-enable as a side
- * effect of rfi
- */
-.Lrestore_no_replay:
- TRACE_ENABLE_INTS
- li r0,IRQS_ENABLED
- stb r0,PACAIRQSOFTMASK(r13);
-
- /*
- * Final return path. BookE is handled in a different file
- */
-.Ldo_restore:
-#ifdef CONFIG_PPC_BOOK3E
- b exception_return_book3e
-#else
- /*
- * Clear the reservation. If we know the CPU tracks the address of
- * the reservation then we can potentially save some cycles and use
- * a larx. On POWER6 and POWER7 this is significantly faster.
- */
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
FTR_SECTION_ELSE
- ldarx r4,0,r1
+ ldarx r0,0,r1
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
- /*
- * Some code path such as load_up_fpu or altivec return directly
- * here. They run entirely hard disabled and do not alter the
- * interrupt state. They also don't use lwarx/stwcx. and thus
- * are known not to leave dangling reservations.
- */
- .globl fast_exception_return
-fast_exception_return:
- ld r3,_MSR(r1)
- ld r4,_CTR(r1)
- ld r0,_LINK(r1)
- mtctr r4
- mtlr r0
- ld r4,_XER(r1)
- mtspr SPRN_XER,r4
+ ld r3,_CCR(r1)
+ ld r4,_LINK(r1)
+ ld r5,_CTR(r1)
+ ld r6,_XER(r1)
+ li r0,0
- kuap_check_amr r5, r6
-
- REST_8GPRS(5, r1)
-
- andi. r0,r3,MSR_RI
- beq- .Lunrecov_restore
-
- /*
- * Clear RI before restoring r13. If we are returning to
- * userspace and we take an exception after restoring r13,
- * we end up corrupting the userspace r13 value.
- */
- li r4,0
- mtmsrd r4,1
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- /* TM debug */
- std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
-#endif
- /*
- * r13 is our per cpu area, only restore it if we are returning to
- * userspace the value stored in the stack frame may belong to
- * another CPU.
- */
- andi. r0,r3,MSR_PR
- beq 1f
-BEGIN_FTR_SECTION
- /* Restore PPR */
- ld r2,_PPR(r1)
- mtspr SPRN_PPR,r2
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
- ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
+ REST_4GPRS(7, r1)
+ REST_2GPRS(11, r1)
REST_GPR(13, r1)
- /*
- * We don't need to restore AMR on the way back to userspace for KUAP.
- * The value of AMR only matters while we're in the kernel.
- */
- mtspr SPRN_SRR1,r3
+ mtcr r3
+ mtlr r4
+ mtctr r5
+ mtspr SPRN_XER,r6
- ld r2,_CCR(r1)
- mtcrf 0xFF,r2
- ld r2,_NIP(r1)
- mtspr SPRN_SRR0,r2
-
- ld r0,GPR0(r1)
- ld r2,GPR2(r1)
- ld r3,GPR3(r1)
- ld r4,GPR4(r1)
- ld r1,GPR1(r1)
+ REST_4GPRS(2, r1)
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
RFI_TO_USER
b . /* prevent speculative execution */
-1: mtspr SPRN_SRR1,r3
+.Lrestore_nvgprs:
+ REST_NVGPRS(r1)
+ b .Lfast_user_interrupt_return
- ld r2,_CCR(r1)
- mtcrf 0xFF,r2
- ld r2,_NIP(r1)
- mtspr SPRN_SRR0,r2
+ .balign IFETCH_ALIGN_BYTES
+.Lkernel_interrupt_return:
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl interrupt_exit_kernel_prepare
+
+.Lfast_kernel_interrupt_return:
+ cmpdi cr1,r3,0
+ ld r11,_NIP(r1)
+ ld r12,_MSR(r1)
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ ldarx r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ ld r3,_LINK(r1)
+ ld r4,_CTR(r1)
+ ld r5,_XER(r1)
+ ld r6,_CCR(r1)
+ li r0,0
+
+ REST_4GPRS(7, r1)
+ REST_2GPRS(11, r1)
+
+ mtlr r3
+ mtctr r4
+ mtspr SPRN_XER,r5
/*
* Leaving a stale exception_marker on the stack can confuse
* the reliable stack unwinder later on. Clear it.
*/
- li r2,0
- std r2,STACK_FRAME_OVERHEAD-16(r1)
+ std r0,STACK_FRAME_OVERHEAD-16(r1)
- ld r0,GPR0(r1)
- ld r2,GPR2(r1)
- ld r3,GPR3(r1)
+ REST_4GPRS(2, r1)
- kuap_restore_amr r4
-
- ld r4,GPR4(r1)
- ld r1,GPR1(r1)
+ bne- cr1,1f /* emulate stack store */
+ mtcr r6
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
RFI_TO_KERNEL
b . /* prevent speculative execution */
-#endif /* CONFIG_PPC_BOOK3E */
-
- /*
- * We are returning to a context with interrupts soft disabled.
- *
- * However, we may also about to hard enable, so we need to
- * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
- * or that bit can get out of sync and bad things will happen
+1: /*
+ * Emulate stack store with update. New r1 value was already calculated
+ * and updated in our interrupt regs by emulate_loadstore, but we can't
+ * store the previous value of r1 to the stack before re-loading our
+ * registers from it, otherwise they could be clobbered. Use
+ * PACA_EXGEN as temporary storage to hold the store data, as
+ * interrupts are disabled here so it won't be clobbered.
*/
-.Lrestore_irq_off:
- ld r3,_MSR(r1)
- lbz r7,PACAIRQHAPPENED(r13)
- andi. r0,r3,MSR_EE
- beq 1f
- rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS
- stb r7,PACAIRQHAPPENED(r13)
-1:
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
- /* The interrupt should not have soft enabled. */
- lbz r7,PACAIRQSOFTMASK(r13)
-1: tdeqi r7,IRQS_ENABLED
- EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
- b .Ldo_restore
+ mtcr r6
+ std r9,PACA_EXGEN+0(r13)
+ addi r9,r1,INT_FRAME_SIZE /* get original r1 */
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ std r9,0(r1) /* perform store component of stdu */
+ ld r9,PACA_EXGEN+0(r13)
- /*
- * Something did happen, check if a re-emit is needed
- * (this also clears paca->irq_happened)
- */
-.Lrestore_check_irq_replay:
- /* XXX: We could implement a fast path here where we check
- * for irq_happened being just 0x01, in which case we can
- * clear it and return. That means that we would potentially
- * miss a decrementer having wrapped all the way around.
- *
- * Still, this might be useful for things like hash_page
- */
- bl __check_irq_replay
- cmpwi cr0,r3,0
- beq .Lrestore_no_replay
-
- /*
- * We need to re-emit an interrupt. We do so by re-using our
- * existing exception frame. We first change the trap value,
- * but we need to ensure we preserve the low nibble of it
- */
- ld r4,_TRAP(r1)
- clrldi r4,r4,60
- or r4,r4,r3
- std r4,_TRAP(r1)
-
- /*
- * PACA_IRQ_HARD_DIS won't always be set here, so set it now
- * to reconcile the IRQ state. Tracing is already accounted for.
- */
- lbz r4,PACAIRQHAPPENED(r13)
- ori r4,r4,PACA_IRQ_HARD_DIS
- stb r4,PACAIRQHAPPENED(r13)
-
- /*
- * Then find the right handler and call it. Interrupts are
- * still soft-disabled and we keep them that way.
- */
- cmpwi cr0,r3,0x500
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl do_IRQ
- b ret_from_except
-1: cmpwi cr0,r3,0xf00
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl performance_monitor_exception
- b ret_from_except
-1: cmpwi cr0,r3,0xe60
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl handle_hmi_exception
- b ret_from_except
-1: cmpwi cr0,r3,0x900
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl timer_interrupt
- b ret_from_except
-#ifdef CONFIG_PPC_DOORBELL
-1:
-#ifdef CONFIG_PPC_BOOK3E
- cmpwi cr0,r3,0x280
-#else
- cmpwi cr0,r3,0xa00
-#endif /* CONFIG_PPC_BOOK3E */
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl doorbell_exception
-#endif /* CONFIG_PPC_DOORBELL */
-1: b ret_from_except /* What else to do here ? */
-
-.Lunrecov_restore:
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl unrecoverable_exception
- b .Lunrecov_restore
-
-_ASM_NOKPROBE_SYMBOL(ret_from_except);
-_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
-_ASM_NOKPROBE_SYMBOL(resume_kernel);
-_ASM_NOKPROBE_SYMBOL(fast_exc_return_irq);
-_ASM_NOKPROBE_SYMBOL(restore);
-_ASM_NOKPROBE_SYMBOL(fast_exception_return);
-
+ RFI_TO_KERNEL
+ b . /* prevent speculative execution */
+#endif /* CONFIG_PPC_BOOK3S */
#ifdef CONFIG_PPC_RTAS
/*
@@ -1155,8 +804,7 @@
*/
SAVE_GPR(2, r1) /* Save the TOC */
SAVE_GPR(13, r1) /* Save paca */
- SAVE_8GPRS(14, r1) /* Save the non-volatiles */
- SAVE_10GPRS(22, r1) /* ditto */
+ SAVE_NVGPRS(r1) /* Save the non-volatiles */
mfcr r4
std r4,_CCR(r1)
@@ -1263,8 +911,7 @@
/* relocation is on at this point */
REST_GPR(2, r1) /* Restore the TOC */
REST_GPR(13, r1) /* Restore paca */
- REST_8GPRS(14, r1) /* Restore the non-volatiles */
- REST_10GPRS(22, r1) /* ditto */
+ REST_NVGPRS(r1) /* Restore the non-volatiles */
GET_PACA(r13)
@@ -1298,8 +945,7 @@
*/
SAVE_GPR(2, r1)
SAVE_GPR(13, r1)
- SAVE_8GPRS(14, r1)
- SAVE_10GPRS(22, r1)
+ SAVE_NVGPRS(r1)
mfcr r10
mfmsr r11
std r10,_CCR(r1)
@@ -1343,8 +989,7 @@
/* Restore other registers */
REST_GPR(2, r1)
REST_GPR(13, r1)
- REST_8GPRS(14, r1)
- REST_10GPRS(22, r1)
+ REST_NVGPRS(r1)
ld r4,_CCR(r1)
mtcr r4
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 9d32158..2ed14d4 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -11,6 +11,7 @@
#include <asm/cacheflush.h>
#include <asm/code-patching.h>
#include <asm/machdep.h>
+#include <asm/inst.h>
#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
extern void epapr_ev_idle(void);
@@ -36,10 +37,10 @@
return -1;
for (i = 0; i < (len / 4); i++) {
- u32 inst = be32_to_cpu(insts[i]);
- patch_instruction(epapr_hypercall_start + i, inst);
+ struct ppc_inst inst = ppc_inst(be32_to_cpu(insts[i]));
+ patch_instruction((struct ppc_inst *)(epapr_hypercall_start + i), inst);
#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
- patch_instruction(epapr_ev_idle_start + i, inst);
+ patch_instruction((struct ppc_inst *)(epapr_ev_idle_start + i), inst);
#endif
}
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 829950b..f579ce4 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -24,6 +24,7 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_booke_hv_asm.h>
#include <asm/feature-fixups.h>
+#include <asm/context_tracking.h>
/* XXX This will ultimately add space for a special exception save
* structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
@@ -987,7 +988,6 @@
.endm
masked_interrupt_book3e_0x500:
- // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE
masked_interrupt_book3e PACA_IRQ_EE 1
masked_interrupt_book3e_0x900:
@@ -1003,38 +1003,6 @@
masked_interrupt_book3e PACA_IRQ_DBELL 0
/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280
- * to indicate the kind of interrupt. MSR:EE is already off.
- * We generate a stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- */
-_GLOBAL(__replay_interrupt)
- /* We are going to jump to the exception common code which
- * will retrieve various register values from the PACA which
- * we don't give a damn about.
- */
- mflr r10
- mfmsr r11
- mfcr r4
- mtspr SPRN_SPRG_GEN_SCRATCH,r13;
- std r1,PACA_EXGEN+EX_R1(r13);
- stw r4,PACA_EXGEN+EX_CR(r13);
- ori r11,r11,MSR_EE
- subi r1,r1,INT_FRAME_SIZE;
- cmpwi cr0,r3,0x500
- beq exc_0x500_common
- cmpwi cr0,r3,0x900
- beq exc_0x900_common
- cmpwi cr0,r3,0x280
- beq exc_0x280_common
- blr
-
-
-/*
* This is called from 0x300 and 0x400 handlers after the prologs with
* r14 and r15 containing the fault address and error code, with the
* original values stashed away in the PACA
@@ -1073,17 +1041,161 @@
bl alignment_exception
b ret_from_except
-/*
- * We branch here from entry_64.S for the last stage of the exception
- * return code path. MSR:EE is expected to be off at that point
- */
-_GLOBAL(exception_return_book3e)
- b 1f
+ .align 7
+_GLOBAL(ret_from_except)
+ ld r11,_TRAP(r1)
+ andi. r0,r11,1
+ bne ret_from_except_lite
+ REST_NVGPRS(r1)
+
+_GLOBAL(ret_from_except_lite)
+ /*
+ * Disable interrupts so that current_thread_info()->flags
+ * can't change between when we test it and when we return
+ * from the interrupt.
+ */
+ wrteei 0
+
+ ld r9, PACA_THREAD_INFO(r13)
+ ld r3,_MSR(r1)
+ ld r10,PACACURRENT(r13)
+ ld r4,TI_FLAGS(r9)
+ andi. r3,r3,MSR_PR
+ beq resume_kernel
+ lwz r3,(THREAD+THREAD_DBCR0)(r10)
+
+ /* Check current_thread_info()->flags */
+ andi. r0,r4,_TIF_USER_WORK_MASK
+ bne 1f
+ /*
+ * Check to see if the dbcr0 register is set up to debug.
+ * Use the internal debug mode bit to do this.
+ */
+ andis. r0,r3,DBCR0_IDM@h
+ beq restore
+ mfmsr r0
+ rlwinm r0,r0,0,~MSR_DE /* Clear MSR.DE */
+ mtmsr r0
+ mtspr SPRN_DBCR0,r3
+ li r10, -1
+ mtspr SPRN_DBSR,r10
+ b restore
+1: andi. r0,r4,_TIF_NEED_RESCHED
+ beq 2f
+ bl restore_interrupts
+ SCHEDULE_USER
+ b ret_from_except_lite
+2:
+ bl save_nvgprs
+ /*
+ * Use a non volatile GPR to save and restore our thread_info flags
+ * across the call to restore_interrupts.
+ */
+ mr r30,r4
+ bl restore_interrupts
+ mr r4,r30
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_notify_resume
+ b ret_from_except
+
+resume_kernel:
+ /* check current_thread_info, _TIF_EMULATE_STACK_STORE */
+ andis. r8,r4,_TIF_EMULATE_STACK_STORE@h
+ beq+ 1f
+
+ addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
+
+ ld r3,GPR1(r1)
+ subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
+ mr r4,r1 /* src: current exception frame */
+ mr r1,r3 /* Reroute the trampoline frame to r1 */
+
+ /* Copy from the original to the trampoline. */
+ li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */
+ li r6,0 /* start offset: 0 */
+ mtctr r5
+2: ldx r0,r6,r4
+ stdx r0,r6,r3
+ addi r6,r6,8
+ bdnz 2b
+
+ /* Do real store operation to complete stdu */
+ ld r5,GPR1(r1)
+ std r8,0(r5)
+
+ /* Clear _TIF_EMULATE_STACK_STORE flag */
+ lis r11,_TIF_EMULATE_STACK_STORE@h
+ addi r5,r9,TI_FLAGS
+0: ldarx r4,0,r5
+ andc r4,r4,r11
+ stdcx. r4,0,r5
+ bne- 0b
+1:
+
+#ifdef CONFIG_PREEMPT
+ /* Check if we need to preempt */
+ andi. r0,r4,_TIF_NEED_RESCHED
+ beq+ restore
+ /* Check that preempt_count() == 0 and interrupts are enabled */
+ lwz r8,TI_PREEMPT(r9)
+ cmpwi cr0,r8,0
+ bne restore
+ ld r0,SOFTE(r1)
+ andi. r0,r0,IRQS_DISABLED
+ bne restore
+
+ /*
+ * Here we are preempting the current task. We want to make
+ * sure we are soft-disabled first and reconcile irq state.
+ */
+ RECONCILE_IRQ_STATE(r3,r4)
+ bl preempt_schedule_irq
+
+ /*
+ * arch_local_irq_restore() from preempt_schedule_irq above may
+ * enable hard interrupt but we really should disable interrupts
+ * when we return from the interrupt, and so that we don't get
+ * interrupted after loading SRR0/1.
+ */
+ wrteei 0
+#endif /* CONFIG_PREEMPT */
+
+restore:
+ /*
+ * This is the main kernel exit path. First we check if we
+ * are about to re-enable interrupts
+ */
+ ld r5,SOFTE(r1)
+ lbz r6,PACAIRQSOFTMASK(r13)
+ andi. r5,r5,IRQS_DISABLED
+ bne .Lrestore_irq_off
+
+ /* We are enabling, were we already enabled ? Yes, just return */
+ andi. r6,r6,IRQS_DISABLED
+ beq cr0,fast_exception_return
+
+ /*
+ * We are about to soft-enable interrupts (we are hard disabled
+ * at this point). We check if there's anything that needs to
+ * be replayed first.
+ */
+ lbz r0,PACAIRQHAPPENED(r13)
+ cmpwi cr0,r0,0
+ bne- .Lrestore_check_irq_replay
+
+ /*
+ * Get here when nothing happened while soft-disabled, just
+ * soft-enable and move-on. We will hard-enable as a side
+ * effect of rfi
+ */
+.Lrestore_no_replay:
+ TRACE_ENABLE_INTS
+ li r0,IRQS_ENABLED
+ stb r0,PACAIRQSOFTMASK(r13);
/* This is the return from load_up_fpu fast path which could do with
* less GPR restores in fact, but for now we have a single return path
*/
- .globl fast_exception_return
fast_exception_return:
wrteei 0
1: mr r0,r13
@@ -1124,6 +1236,92 @@
mfspr r13,SPRN_SPRG_GEN_SCRATCH
rfi
+ /*
+ * We are returning to a context with interrupts soft disabled.
+ *
+ * However, we may also about to hard enable, so we need to
+ * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+ * or that bit can get out of sync and bad things will happen
+ */
+.Lrestore_irq_off:
+ ld r3,_MSR(r1)
+ lbz r7,PACAIRQHAPPENED(r13)
+ andi. r0,r3,MSR_EE
+ beq 1f
+ rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS
+ stb r7,PACAIRQHAPPENED(r13)
+1:
+#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
+ /* The interrupt should not have soft enabled. */
+ lbz r7,PACAIRQSOFTMASK(r13)
+1: tdeqi r7,IRQS_ENABLED
+ EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
+ b fast_exception_return
+
+ /*
+ * Something did happen, check if a re-emit is needed
+ * (this also clears paca->irq_happened)
+ */
+.Lrestore_check_irq_replay:
+ /* XXX: We could implement a fast path here where we check
+ * for irq_happened being just 0x01, in which case we can
+ * clear it and return. That means that we would potentially
+ * miss a decrementer having wrapped all the way around.
+ *
+ * Still, this might be useful for things like hash_page
+ */
+ bl __check_irq_replay
+ cmpwi cr0,r3,0
+ beq .Lrestore_no_replay
+
+ /*
+ * We need to re-emit an interrupt. We do so by re-using our
+ * existing exception frame. We first change the trap value,
+ * but we need to ensure we preserve the low nibble of it
+ */
+ ld r4,_TRAP(r1)
+ clrldi r4,r4,60
+ or r4,r4,r3
+ std r4,_TRAP(r1)
+
+ /*
+ * PACA_IRQ_HARD_DIS won't always be set here, so set it now
+ * to reconcile the IRQ state. Tracing is already accounted for.
+ */
+ lbz r4,PACAIRQHAPPENED(r13)
+ ori r4,r4,PACA_IRQ_HARD_DIS
+ stb r4,PACAIRQHAPPENED(r13)
+
+ /*
+ * Then find the right handler and call it. Interrupts are
+ * still soft-disabled and we keep them that way.
+ */
+ cmpwi cr0,r3,0x500
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl do_IRQ
+ b ret_from_except
+1: cmpwi cr0,r3,0x900
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl timer_interrupt
+ b ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
+ cmpwi cr0,r3,0x280
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl doorbell_exception
+#endif /* CONFIG_PPC_DOORBELL */
+1: b ret_from_except /* What else to do here ? */
+
+_ASM_NOKPROBE_SYMBOL(ret_from_except);
+_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
+_ASM_NOKPROBE_SYMBOL(resume_kernel);
+_ASM_NOKPROBE_SYMBOL(restore);
+_ASM_NOKPROBE_SYMBOL(fast_exception_return);
+
/*
* Trampolines used when spotting a bad kernel stack pointer in
* the exception entry code.
@@ -1346,16 +1544,6 @@
sync
isync
-/*
- * The mapping only needs to be cache-coherent on SMP, except on
- * Freescale e500mc derivatives where it's also needed for coherent DMA.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
-
/* 6. Setup KERNELBASE mapping in TLB[0]
*
* r3 = MAS0 w/TLBSEL & ESEL for the entry we started in
@@ -1368,7 +1556,7 @@
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
mtspr SPRN_MAS1,r6
- LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_NEEDED)
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | MAS2_M_IF_NEEDED)
mtspr SPRN_MAS2,r6
rlwinm r5,r5,0,0,25
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 88bba0a..10df278 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -32,16 +32,10 @@
#define EX_CCR 52
#define EX_CFAR 56
#define EX_PPR 64
-#if defined(CONFIG_RELOCATABLE)
#define EX_CTR 72
.if EX_SIZE != 10
.error "EX_SIZE is wrong"
.endif
-#else
-.if EX_SIZE != 9
- .error "EX_SIZE is wrong"
-.endif
-#endif
/*
* Following are fixed section helper macros.
@@ -50,7 +44,6 @@
* EXC_VIRT_BEGIN/END - virt (AIL), unrelocated exception vectors
* TRAMP_REAL_BEGIN - real, unrelocated helpers (virt may call these)
* TRAMP_VIRT_BEGIN - virt, unreloc helpers (in practice, real can use)
- * TRAMP_KVM_BEGIN - KVM handlers, these are put into real, unrelocated
* EXC_COMMON - After switching to virtual, relocated mode.
*/
@@ -80,13 +73,6 @@
#define TRAMP_VIRT_BEGIN(name) \
FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define TRAMP_KVM_BEGIN(name) \
- TRAMP_VIRT_BEGIN(name)
-#else
-#define TRAMP_KVM_BEGIN(name)
-#endif
-
#define EXC_REAL_NONE(start, size) \
FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size)
@@ -119,67 +105,6 @@
ori reg,reg,(ABS_ADDR(label))@l; \
addis reg,reg,(ABS_ADDR(label))@h
-/* Exception register prefixes */
-#define EXC_HV_OR_STD 2 /* depends on HVMODE */
-#define EXC_HV 1
-#define EXC_STD 0
-
-#if defined(CONFIG_RELOCATABLE)
-/*
- * If we support interrupts with relocation on AND we're a relocatable kernel,
- * we need to use CTR to get to the 2nd level handler. So, save/restore it
- * when required.
- */
-#define SAVE_CTR(reg, area) mfctr reg ; std reg,area+EX_CTR(r13)
-#define GET_CTR(reg, area) ld reg,area+EX_CTR(r13)
-#define RESTORE_CTR(reg, area) ld reg,area+EX_CTR(r13) ; mtctr reg
-#else
-/* ...else CTR is unused and in register. */
-#define SAVE_CTR(reg, area)
-#define GET_CTR(reg, area) mfctr reg
-#define RESTORE_CTR(reg, area)
-#endif
-
-/*
- * PPR save/restore macros used in exceptions-64s.S
- * Used for P7 or later processors
- */
-#define SAVE_PPR(area, ra) \
-BEGIN_FTR_SECTION_NESTED(940) \
- ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \
- std ra,_PPR(r1); \
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940)
-
-#define RESTORE_PPR_PACA(area, ra) \
-BEGIN_FTR_SECTION_NESTED(941) \
- ld ra,area+EX_PPR(r13); \
- mtspr SPRN_PPR,ra; \
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
-
-/*
- * Get an SPR into a register if the CPU has the given feature
- */
-#define OPT_GET_SPR(ra, spr, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- mfspr ra,spr; \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Set an SPR from a register if the CPU has the given feature
- */
-#define OPT_SET_SPR(ra, spr, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- mtspr spr,ra; \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Save a register to the PACA if the CPU has the given feature
- */
-#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- std ra,offset(r13); \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
/*
* Branch to label using its 0xC000 address. This results in instruction
* address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
@@ -193,89 +118,199 @@
mtctr reg; \
bctr
-.macro INT_KVM_HANDLER name, vec, hsrr, area, skip
- TRAMP_KVM_BEGIN(\name\()_kvm)
- KVM_HANDLER \vec, \hsrr, \area, \skip
+/*
+ * Interrupt code generation macros
+ */
+#define IVEC .L_IVEC_\name\() /* Interrupt vector address */
+#define IHSRR .L_IHSRR_\name\() /* Sets SRR or HSRR registers */
+#define IHSRR_IF_HVMODE .L_IHSRR_IF_HVMODE_\name\() /* HSRR if HV else SRR */
+#define IAREA .L_IAREA_\name\() /* PACA save area */
+#define IVIRT .L_IVIRT_\name\() /* Has virt mode entry point */
+#define IISIDE .L_IISIDE_\name\() /* Uses SRR0/1 not DAR/DSISR */
+#define IDAR .L_IDAR_\name\() /* Uses DAR (or SRR0) */
+#define IDSISR .L_IDSISR_\name\() /* Uses DSISR (or SRR1) */
+#define ISET_RI .L_ISET_RI_\name\() /* Run common code w/ MSR[RI]=1 */
+#define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
+#define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
+#define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */
+#define IKVM_SKIP .L_IKVM_SKIP_\name\() /* Generate KVM skip handler */
+#define IKVM_REAL .L_IKVM_REAL_\name\() /* Real entry tests KVM */
+#define __IKVM_REAL(name) .L_IKVM_REAL_ ## name
+#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
+#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
+#define __ISTACK(name) .L_ISTACK_ ## name
+#define IRECONCILE .L_IRECONCILE_\name\() /* Do RECONCILE_IRQ_STATE */
+#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
+
+#define INT_DEFINE_BEGIN(n) \
+.macro int_define_ ## n name
+
+#define INT_DEFINE_END(n) \
+.endm ; \
+int_define_ ## n n ; \
+do_define_int n
+
+.macro do_define_int name
+ .ifndef IVEC
+ .error "IVEC not defined"
+ .endif
+ .ifndef IHSRR
+ IHSRR=0
+ .endif
+ .ifndef IHSRR_IF_HVMODE
+ IHSRR_IF_HVMODE=0
+ .endif
+ .ifndef IAREA
+ IAREA=PACA_EXGEN
+ .endif
+ .ifndef IVIRT
+ IVIRT=1
+ .endif
+ .ifndef IISIDE
+ IISIDE=0
+ .endif
+ .ifndef IDAR
+ IDAR=0
+ .endif
+ .ifndef IDSISR
+ IDSISR=0
+ .endif
+ .ifndef ISET_RI
+ ISET_RI=1
+ .endif
+ .ifndef IBRANCH_TO_COMMON
+ IBRANCH_TO_COMMON=1
+ .endif
+ .ifndef IREALMODE_COMMON
+ IREALMODE_COMMON=0
+ .else
+ .if ! IBRANCH_TO_COMMON
+ .error "IREALMODE_COMMON=1 but IBRANCH_TO_COMMON=0"
+ .endif
+ .endif
+ .ifndef IMASK
+ IMASK=0
+ .endif
+ .ifndef IKVM_SKIP
+ IKVM_SKIP=0
+ .endif
+ .ifndef IKVM_REAL
+ IKVM_REAL=0
+ .endif
+ .ifndef IKVM_VIRT
+ IKVM_VIRT=0
+ .endif
+ .ifndef ISTACK
+ ISTACK=1
+ .endif
+ .ifndef IRECONCILE
+ IRECONCILE=1
+ .endif
+ .ifndef IKUAP
+ IKUAP=1
+ .endif
.endm
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/*
- * If hv is possible, interrupts come into to the hv version
- * of the kvmppc_interrupt code, which then jumps to the PR handler,
- * kvmppc_interrupt_pr, if the guest is a PR guest.
+ * All interrupts which set HSRR registers, as well as SRESET and MCE and
+ * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
+ * so they all generally need to test whether they were taken in guest context.
+ *
+ * Note: SRESET and MCE may also be sent to the guest by the hypervisor, and be
+ * taken with MSR[HV]=0.
+ *
+ * Interrupts which set SRR registers (with the above exceptions) do not
+ * elevate to MSR[HV]=1 mode, though most can be taken when running with
+ * MSR[HV]=1 (e.g., bare metal kernel and userspace). So these interrupts do
+ * not need to test whether a guest is running because they get delivered to
+ * the guest directly, including nested HV KVM guests.
+ *
+ * The exception is PR KVM, where the guest runs with MSR[PR]=1 and the host
+ * runs with MSR[HV]=0, so the host takes all interrupts on behalf of the
+ * guest. PR KVM runs with LPCR[AIL]=0 which causes interrupts to always be
+ * delivered to the real-mode entry point, therefore such interrupts only test
+ * KVM in their real mode handlers, and only when PR KVM is possible.
+ *
+ * Interrupts that are taken in MSR[HV]=0 and escalate to MSR[HV]=1 are always
+ * delivered in real-mode when the MMU is in hash mode because the MMU
+ * registers are not set appropriately to translate host addresses. In nested
+ * radix mode these can be delivered in virt-mode as the host translations are
+ * used implicitly (see: effective LPID, effective PID).
+ */
+
+/*
+ * If an interrupt is taken while a guest is running, it is immediately routed
+ * to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first
+ * to kvmppc_interrupt_hv, which handles the PR guest case.
*/
#define kvmppc_interrupt kvmppc_interrupt_hv
#else
#define kvmppc_interrupt kvmppc_interrupt_pr
#endif
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
lbz r10,HSTATE_IN_GUEST(r13)
cmpwi r10,0
bne \name\()_kvm
.endm
-.macro KVM_HANDLER vec, hsrr, area, skip
- .if \skip
+.macro GEN_KVM name
+ .balign IFETCH_ALIGN_BYTES
+\name\()_kvm:
+
+ .if IKVM_SKIP
cmpwi r10,KVM_GUEST_MODE_SKIP
beq 89f
.else
-BEGIN_FTR_SECTION_NESTED(947)
- ld r10,\area+EX_CFAR(r13)
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_CFAR(r13)
std r10,HSTATE_CFAR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.endif
-BEGIN_FTR_SECTION_NESTED(948)
- ld r10,\area+EX_PPR(r13)
+ ld r10,IAREA+EX_CTR(r13)
+ mtctr r10
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_PPR(r13)
std r10,HSTATE_PPR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
- ld r10,\area+EX_R10(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ ld r11,IAREA+EX_R11(r13)
+ ld r12,IAREA+EX_R12(r13)
std r12,HSTATE_SCRATCH0(r13)
sldi r12,r9,32
+ ld r9,IAREA+EX_R9(r13)
+ ld r10,IAREA+EX_R10(r13)
/* HSRR variants have the 0x2 bit added to their trap number */
- .if \hsrr == EXC_HV_OR_STD
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
- ori r12,r12,(\vec + 0x2)
+ ori r12,r12,(IVEC + 0x2)
FTR_SECTION_ELSE
- ori r12,r12,(\vec)
+ ori r12,r12,(IVEC)
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- ori r12,r12,(\vec + 0x2)
+ .elseif IHSRR
+ ori r12,r12,(IVEC+ 0x2)
.else
- ori r12,r12,(\vec)
+ ori r12,r12,(IVEC)
.endif
-
-#ifdef CONFIG_RELOCATABLE
- /*
- * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
- * outside the head section. CONFIG_RELOCATABLE KVM expects CTR
- * to be saved in HSTATE_SCRATCH1.
- */
- mfctr r9
- std r9,HSTATE_SCRATCH1(r13)
- __LOAD_FAR_HANDLER(r9, kvmppc_interrupt)
- mtctr r9
- ld r9,\area+EX_R9(r13)
- bctr
-#else
- ld r9,\area+EX_R9(r13)
b kvmppc_interrupt
-#endif
-
- .if \skip
+ .if IKVM_SKIP
89: mtocrf 0x80,r9
- ld r9,\area+EX_R9(r13)
- ld r10,\area+EX_R10(r13)
- .if \hsrr == EXC_HV_OR_STD
+ ld r10,IAREA+EX_CTR(r13)
+ mtctr r10
+ ld r9,IAREA+EX_R9(r13)
+ ld r10,IAREA+EX_R10(r13)
+ ld r11,IAREA+EX_R11(r13)
+ ld r12,IAREA+EX_R12(r13)
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
b kvmppc_skip_Hinterrupt
FTR_SECTION_ELSE
b kvmppc_skip_interrupt
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
+ .elseif IHSRR
b kvmppc_skip_Hinterrupt
.else
b kvmppc_skip_interrupt
@@ -284,107 +319,12 @@
.endm
#else
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
.endm
-.macro KVM_HANDLER name, vec, hsrr, area, skip
+.macro GEN_KVM name
.endm
#endif
-.macro INT_SAVE_SRR_AND_JUMP label, hsrr, set_ri
- ld r10,PACAKMSR(r13) /* get MSR value for kernel */
- .if ! \set_ri
- xori r10,r10,MSR_RI /* Clear MSR_RI */
- .endif
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- mtspr SPRN_HSRR1,r10
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- mtspr SPRN_SRR1,r10
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- mtspr SPRN_HSRR1,r10
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- mtspr SPRN_SRR1,r10
- .endif
- LOAD_HANDLER(r10, \label\())
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mtspr SPRN_HSRR0,r10
- HRFI_TO_KERNEL
- FTR_SECTION_ELSE
- mtspr SPRN_SRR0,r10
- RFI_TO_KERNEL
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mtspr SPRN_HSRR0,r10
- HRFI_TO_KERNEL
- .else
- mtspr SPRN_SRR0,r10
- RFI_TO_KERNEL
- .endif
- b . /* prevent speculative execution */
-.endm
-
-/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */
-.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr
-#ifdef CONFIG_RELOCATABLE
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- .endif
- LOAD_HANDLER(r12, \label\())
- mtctr r12
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- FTR_SECTION_ELSE
- mfspr r12,SPRN_SRR1 /* and HSRR1 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- .else
- mfspr r12,SPRN_SRR1 /* and HSRR1 */
- .endif
- li r10,MSR_RI
- mtmsrd r10,1 /* Set RI (EE=0) */
- bctr
-#else
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- .endif
- li r10,MSR_RI
- mtmsrd r10,1 /* Set RI (EE=0) */
- b \label
-#endif
-.endm
-
/*
* This is the BOOK3S interrupt entry code macro.
*
@@ -405,14 +345,41 @@
* - Fall through and continue executing in real, unrelocated mode.
* This is done if early=2.
*/
-.macro INT_HANDLER name, vec, ool=0, early=0, virt=0, hsrr=0, area=PACA_EXGEN, ri=1, dar=0, dsisr=0, bitmask=0, kvm=0
+
+.macro GEN_BRANCH_TO_COMMON name, virt
+ .if IREALMODE_COMMON
+ LOAD_HANDLER(r10, \name\()_common)
+ mtctr r10
+ bctr
+ .else
+ .if \virt
+#ifndef CONFIG_RELOCATABLE
+ b \name\()_common_virt
+#else
+ LOAD_HANDLER(r10, \name\()_common_virt)
+ mtctr r10
+ bctr
+#endif
+ .else
+ LOAD_HANDLER(r10, \name\()_common_real)
+ mtctr r10
+ bctr
+ .endif
+ .endif
+.endm
+
+.macro GEN_INT_ENTRY name, virt, ool=0
SET_SCRATCH0(r13) /* save r13 */
GET_PACA(r13)
- std r9,\area\()+EX_R9(r13) /* save r9 */
- OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR)
+ std r9,IAREA+EX_R9(r13) /* save r9 */
+BEGIN_FTR_SECTION
+ mfspr r9,SPRN_PPR
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
HMT_MEDIUM
- std r10,\area\()+EX_R10(r13) /* save r10 - r12 */
- OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
+ std r10,IAREA+EX_R10(r13) /* save r10 - r12 */
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_CFAR
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.if \ool
.if !\virt
b tramp_real_\name
@@ -425,47 +392,18 @@
.endif
.endif
- OPT_SAVE_REG_TO_PACA(\area\()+EX_PPR, r9, CPU_FTR_HAS_PPR)
- OPT_SAVE_REG_TO_PACA(\area\()+EX_CFAR, r10, CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+ std r9,IAREA+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+ std r10,IAREA+EX_CFAR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
INTERRUPT_TO_KERNEL
- SAVE_CTR(r10, \area\())
+ mfctr r10
+ std r10,IAREA+EX_CTR(r13)
mfcr r9
- .if \kvm
- KVMTEST \name \hsrr \vec
- .endif
- .if \bitmask
- lbz r10,PACAIRQSOFTMASK(r13)
- andi. r10,r10,\bitmask
- /* Associate vector numbers with bits in paca->irq_happened */
- .if \vec == 0x500 || \vec == 0xea0
- li r10,PACA_IRQ_EE
- .elseif \vec == 0x900
- li r10,PACA_IRQ_DEC
- .elseif \vec == 0xa00 || \vec == 0xe80
- li r10,PACA_IRQ_DBELL
- .elseif \vec == 0xe60
- li r10,PACA_IRQ_HMI
- .elseif \vec == 0xf00
- li r10,PACA_IRQ_PMI
- .else
- .abort "Bad maskable vector"
- .endif
-
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- bne masked_Hinterrupt
- FTR_SECTION_ELSE
- bne masked_interrupt
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- bne masked_Hinterrupt
- .else
- bne masked_interrupt
- .endif
- .endif
-
- std r11,\area\()+EX_R11(r13)
- std r12,\area\()+EX_R12(r13)
+ std r11,IAREA+EX_R11(r13)
+ std r12,IAREA+EX_R12(r13)
/*
* DAR/DSISR, SCRATCH0 must be read before setting MSR[RI],
@@ -473,51 +411,152 @@
* not recoverable if they are live.
*/
GET_SCRATCH0(r10)
- std r10,\area\()+EX_R13(r13)
- .if \dar
- .if \hsrr
+ std r10,IAREA+EX_R13(r13)
+ .if IDAR && !IISIDE
+ .if IHSRR
mfspr r10,SPRN_HDAR
.else
mfspr r10,SPRN_DAR
.endif
- std r10,\area\()+EX_DAR(r13)
+ std r10,IAREA+EX_DAR(r13)
.endif
- .if \dsisr
- .if \hsrr
+ .if IDSISR && !IISIDE
+ .if IHSRR
mfspr r10,SPRN_HDSISR
.else
mfspr r10,SPRN_DSISR
.endif
- stw r10,\area\()+EX_DSISR(r13)
+ stw r10,IAREA+EX_DSISR(r13)
.endif
- .if \early == 2
- /* nothing more */
- .elseif \early
- mfctr r10 /* save ctr, even for !RELOCATABLE */
- BRANCH_TO_C000(r11, \name\()_early_common)
- .elseif !\virt
- INT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr, \ri
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
+ FTR_SECTION_ELSE
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
.else
- INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
.endif
+
+ .if IBRANCH_TO_COMMON
+ GEN_BRANCH_TO_COMMON \name \virt
+ .endif
+
.if \ool
.popsection
.endif
.endm
/*
- * On entry r13 points to the paca, r9-r13 are saved in the paca,
- * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
- * SRR1, and relocation is on.
+ * __GEN_COMMON_ENTRY is required to receive the branch from interrupt
+ * entry, except in the case of the real-mode handlers which require
+ * __GEN_REALMODE_COMMON_ENTRY.
*
- * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
- * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ * This switches to virtual mode and sets MSR[RI].
*/
-.macro INT_COMMON vec, area, stack, kaup, reconcile, dar, dsisr
- .if \stack
+.macro __GEN_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name
+ .endif
+
+ ld r10,PACAKMSR(r13) /* get MSR value for kernel */
+ /* MSR[RI] is clear iff using SRR regs */
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ xori r10,r10,MSR_RI
+ END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+ .elseif ! IHSRR
+ xori r10,r10,MSR_RI
+ .endif
+ mtmsrd r10
+
+ .if IVIRT
+ .if IKVM_VIRT
+ b 1f /* skip the virt test coming from real */
+ .endif
+
+ .balign IFETCH_ALIGN_BYTES
+DEFINE_FIXED_SYMBOL(\name\()_common_virt)
+\name\()_common_virt:
+ .if IKVM_VIRT
+ KVMTEST \name
+1:
+ .endif
+ .endif /* IVIRT */
+.endm
+
+/*
+ * Don't switch to virt mode. Used for early MCE and HMI handlers that
+ * want to run in real mode.
+ */
+.macro __GEN_REALMODE_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name
+ .endif
+.endm
+
+.macro __GEN_COMMON_BODY name
+ .if IMASK
+ .if ! ISTACK
+ .error "No support for masked interrupt to use custom stack"
+ .endif
+
+ /* If coming from user, skip soft-mask tests. */
+ andi. r10,r12,MSR_PR
+ bne 2f
+
+ /* Kernel code running below __end_interrupts is implicitly
+ * soft-masked */
+ LOAD_HANDLER(r10, __end_interrupts)
+ cmpld r11,r10
+ li r10,IMASK
+ blt- 1f
+
+ /* Test the soft mask state against our interrupt's bit */
+ lbz r10,PACAIRQSOFTMASK(r13)
+1: andi. r10,r10,IMASK
+ /* Associate vector numbers with bits in paca->irq_happened */
+ .if IVEC == 0x500 || IVEC == 0xea0
+ li r10,PACA_IRQ_EE
+ .elseif IVEC == 0x900
+ li r10,PACA_IRQ_DEC
+ .elseif IVEC == 0xa00 || IVEC == 0xe80
+ li r10,PACA_IRQ_DBELL
+ .elseif IVEC == 0xe60
+ li r10,PACA_IRQ_HMI
+ .elseif IVEC == 0xf00
+ li r10,PACA_IRQ_PMI
+ .else
+ .abort "Bad maskable vector"
+ .endif
+
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ bne masked_Hinterrupt
+ FTR_SECTION_ELSE
+ bne masked_interrupt
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ bne masked_Hinterrupt
+ .else
+ bne masked_interrupt
+ .endif
+ .endif
+
+ .if ISTACK
andi. r10,r12,MSR_PR /* See if coming from user */
- mr r10,r1 /* Save r1 */
+2: mr r10,r1 /* Save r1 */
subi r1,r1,INT_FRAME_SIZE /* alloc frame on kernel stack */
beq- 100f
ld r1,PACAKSAVE(r13) /* kernel stack to use */
@@ -532,54 +571,67 @@
std r0,GPR0(r1) /* save r0 in stackframe */
std r10,GPR1(r1) /* save r1 in stackframe */
- .if \stack
- .if \kaup
+ .if ISET_RI
+ li r10,MSR_RI
+ mtmsrd r10,1 /* Set MSR_RI */
+ .endif
+
+ .if ISTACK
+ .if IKUAP
kuap_save_amr_and_lock r9, r10, cr1, cr0
.endif
beq 101f /* if from kernel mode */
ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
- SAVE_PPR(\area, r9)
+BEGIN_FTR_SECTION
+ ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
+ std r9,_PPR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
101:
.else
- .if \kaup
+ .if IKUAP
kuap_save_amr_and_lock r9, r10, cr1
.endif
.endif
/* Save original regs values from save area to stack frame. */
- ld r9,\area+EX_R9(r13) /* move r9, r10 to stackframe */
- ld r10,\area+EX_R10(r13)
+ ld r9,IAREA+EX_R9(r13) /* move r9, r10 to stackframe */
+ ld r10,IAREA+EX_R10(r13)
std r9,GPR9(r1)
std r10,GPR10(r1)
- ld r9,\area+EX_R11(r13) /* move r11 - r13 to stackframe */
- ld r10,\area+EX_R12(r13)
- ld r11,\area+EX_R13(r13)
+ ld r9,IAREA+EX_R11(r13) /* move r11 - r13 to stackframe */
+ ld r10,IAREA+EX_R12(r13)
+ ld r11,IAREA+EX_R13(r13)
std r9,GPR11(r1)
std r10,GPR12(r1)
std r11,GPR13(r1)
- .if \dar
- .if \dar == 2
+
+ SAVE_NVGPRS(r1)
+
+ .if IDAR
+ .if IISIDE
ld r10,_NIP(r1)
.else
- ld r10,\area+EX_DAR(r13)
+ ld r10,IAREA+EX_DAR(r13)
.endif
std r10,_DAR(r1)
.endif
- .if \dsisr
- .if \dsisr == 2
+
+ .if IDSISR
+ .if IISIDE
ld r10,_MSR(r1)
lis r11,DSISR_SRR1_MATCH_64S@h
and r10,r10,r11
.else
- lwz r10,\area+EX_DSISR(r13)
+ lwz r10,IAREA+EX_DSISR(r13)
.endif
std r10,_DSISR(r1)
.endif
-BEGIN_FTR_SECTION_NESTED(66)
- ld r10,\area+EX_CFAR(r13)
+
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_CFAR(r13)
std r10,ORIG_GPR3(r1)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
- GET_CTR(r10, \area)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ ld r10,IAREA+EX_CTR(r13)
std r10,_CTR(r1)
std r2,GPR2(r1) /* save r2 in stackframe */
SAVE_4GPRS(3, r1) /* save r3 - r6 in stackframe */
@@ -591,32 +643,42 @@
mfspr r11,SPRN_XER /* save XER in stackframe */
std r10,SOFTE(r1)
std r11,_XER(r1)
- li r9,(\vec)+1
+ li r9,IVEC
std r9,_TRAP(r1) /* set trap number */
li r10,0
ld r11,exception_marker@toc(r2)
std r10,RESULT(r1) /* clear regs->result */
std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
- .if \stack
+ .if ISTACK
ACCOUNT_STOLEN_TIME
.endif
- .if \reconcile
+ .if IRECONCILE
RECONCILE_IRQ_STATE(r10, r11)
.endif
.endm
/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro GEN_COMMON name
+ __GEN_COMMON_ENTRY \name
+ __GEN_COMMON_BODY \name
+.endm
+
+/*
* Restore all registers including H/SRR0/1 saved in a stack frame of a
* standard exception.
*/
-.macro EXCEPTION_RESTORE_REGS hsrr
+.macro EXCEPTION_RESTORE_REGS hsrr=0
/* Move original SRR0 and SRR1 into the respective regs */
ld r9,_MSR(r1)
- .if \hsrr == EXC_HV_OR_STD
- .error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS"
- .endif
.if \hsrr
mtspr SPRN_HSRR1,r9
.else
@@ -670,28 +732,6 @@
#define FINISH_NAP
#endif
-#define EXC_COMMON(name, realvec, hdlr) \
- EXC_COMMON_BEGIN(name); \
- INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \
- bl save_nvgprs; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
- bl hdlr; \
- b ret_from_except
-
-/*
- * Like EXC_COMMON, but for exceptions that can occur in the idle task and
- * therefore need the special idle handling (finish nap and runlatch)
- */
-#define EXC_COMMON_ASYNC(name, realvec, hdlr) \
- EXC_COMMON_BEGIN(name); \
- INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \
- FINISH_NAP; \
- RUNLATCH_ON; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
- bl hdlr; \
- b ret_from_except_lite
-
-
/*
* There are a few constraints to be concerned with.
* - Real mode exceptions code/data must be located at their physical location.
@@ -716,6 +756,9 @@
* guarantee they will be delivered virtually. Some conditions (see the ISA)
* cause exceptions to be delivered in real mode.
*
+ * The scv instructions are a special case. They get a 0x3000 offset applied.
+ * scv exceptions have unique reentrancy properties, see below.
+ *
* It's impossible to receive interrupts below 0x300 via AIL.
*
* KVM: None of the virtual exceptions are from the guest. Anything that
@@ -725,8 +768,8 @@
* We layout physical memory as follows:
* 0x0000 - 0x00ff : Secondary processor spin code
* 0x0100 - 0x18ff : Real mode pSeries interrupt vectors
- * 0x1900 - 0x3fff : Real mode trampolines
- * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
+ * 0x1900 - 0x2fff : Real mode trampolines
+ * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
* 0x5900 - 0x6fff : Relon mode trampolines
* 0x7000 - 0x7fff : FWNMI data area
* 0x8000 - .... : Common interrupt handlers, remaining early
@@ -737,8 +780,8 @@
* vectors there.
*/
OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900)
-OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x4000)
-OPEN_FIXED_SECTION(virt_vectors, 0x4000, 0x5900)
+OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x3000)
+OPEN_FIXED_SECTION(virt_vectors, 0x3000, 0x5900)
OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000)
#ifdef CONFIG_PPC_POWERNV
@@ -774,10 +817,128 @@
.globl __start_interrupts
__start_interrupts:
+/**
+ * Interrupt 0x3000 - System Call Vectored Interrupt (syscall).
+ * This is a synchronous interrupt invoked with the "scv" instruction. The
+ * system call does not alter the HV bit, so it is directed to the OS.
+ *
+ * Handling:
+ * scv instructions enter the kernel without changing EE, RI, ME, or HV.
+ * In particular, this means we can take a maskable interrupt at any point
+ * in the scv handler, which is unlike any other interrupt. This is solved
+ * by treating the instruction addresses below __end_interrupts as being
+ * soft-masked.
+ *
+ * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and
+ * ensure scv is never executed with relocation off, which means AIL-0
+ * should never happen.
+ *
+ * Before leaving the below __end_interrupts text, at least of the following
+ * must be true:
+ * - MSR[PR]=1 (i.e., return to userspace)
+ * - MSR_EE|MSR_RI is set (no reentrant exceptions)
+ * - Standard kernel environment is set up (stack, paca, etc)
+ *
+ * Call convention:
+ *
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ */
+EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
+ /* SCV 0 */
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_tramp
+#else
+ b system_call_vectored_common
+#endif
+ nop
+
+ /* SCV 1 - 127 */
+ .rept 127
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ li r0,-1 /* cause failure */
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_sigill_tramp
+#else
+ b system_call_vectored_sigill
+#endif
+ .endr
+EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
+
+#ifdef CONFIG_RELOCATABLE
+TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_common)
+ mtctr r10
+ bctr
+
+TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_sigill)
+ mtctr r10
+ bctr
+#endif
+
+
/* No virt vectors corresponding with 0x0..0x100 */
EXC_VIRT_NONE(0x4000, 0x100)
+/**
+ * Interrupt 0x100 - System Reset Interrupt (SRESET aka NMI).
+ * This is a non-maskable, asynchronous interrupt always taken in real-mode.
+ * It is caused by:
+ * - Wake from power-saving state, on powernv.
+ * - An NMI from another CPU, triggered by firmware or hypercall.
+ * - As crash/debug signal injected from BMC, firmware or hypervisor.
+ *
+ * Handling:
+ * Power-save wakeup is the only performance critical path, so this is
+ * determined quickly as possible first. In this case volatile registers
+ * can be discarded and SPRs like CFAR don't need to be read.
+ *
+ * If not a powersave wakeup, then it's run as a regular interrupt, however
+ * it uses its own stack and PACA save area to preserve the regular kernel
+ * environment for debugging.
+ *
+ * This interrupt is not maskable, so triggering it when MSR[RI] is clear,
+ * or SCRATCH0 is in use, etc. may cause a crash. It's also not entirely
+ * correct to switch to virtual mode to run the regular interrupt handler
+ * because it might be interrupted when the MMU is in a bad state (e.g., SLB
+ * is clear).
+ *
+ * FWNMI:
+ * PAPR specifies a "fwnmi" facility which sends the sreset to a different
+ * entry point with a different register set up. Some hypervisors will
+ * send the sreset to 0x100 in the guest if it is not fwnmi capable.
+ *
+ * KVM:
+ * Unlike most SRR interrupts, this may be taken by the host while executing
+ * in a guest, so a KVM test is required. KVM will pull the CPU out of guest
+ * mode and then raise the sreset.
+ */
+INT_DEFINE_BEGIN(system_reset)
+ IVEC=0x100
+ IAREA=PACA_EXNMI
+ IVIRT=0 /* no virt entry point */
+ /*
+ * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
+ * being used, so a nested NMI exception would corrupt it.
+ */
+ ISET_RI=0
+ ISTACK=0
+ IRECONCILE=0
+ IKVM_REAL=1
+INT_DEFINE_END(system_reset)
+
EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
#ifdef CONFIG_PPC_P7_NAP
/*
@@ -815,11 +976,8 @@
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif
- INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0, kvm=1
+ GEN_INT_ENTRY system_reset, virt=0
/*
- * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
- * being used, so a nested NMI exception would corrupt it.
- *
* In theory, we should not enable relocation here if it was disabled
* in SRR1, because the MMU may not be configured to support it (e.g.,
* SLB may have been cleared). In practice, there should only be a few
@@ -828,7 +986,6 @@
*/
EXC_REAL_END(system_reset, 0x100, 0x100)
EXC_VIRT_NONE(0x4100, 0x100)
-INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0
#ifdef CONFIG_PPC_P7_NAP
TRAMP_REAL_BEGIN(system_reset_idle_wake)
@@ -843,12 +1000,12 @@
* Vectors for the FWNMI option. Share common code.
*/
TRAMP_REAL_BEGIN(system_reset_fwnmi)
- /* See comment at system_reset exception, don't turn on RI */
- INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0
+ GEN_INT_ENTRY system_reset, virt=0
#endif /* CONFIG_PPC_PSERIES */
EXC_COMMON_BEGIN(system_reset_common)
+ __GEN_COMMON_ENTRY system_reset
/*
* Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
* to recover, but nested NMI will notice in_nmi and not recover
@@ -864,21 +1021,21 @@
mr r10,r1
ld r1,PACA_NMI_EMERG_SP(r13)
subi r1,r1,INT_FRAME_SIZE
- INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0
- bl save_nvgprs
+ __GEN_COMMON_BODY system_reset
/*
- * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+ * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
* the right thing. We do not want to reconcile because that goes
* through irq tracing which we don't want in NMI.
*
- * Save PACAIRQHAPPENED because some code will do a hard disable
- * (e.g., xmon). So we want to restore this back to where it was
- * when we return. DAR is unused in the stack, so save it there.
+ * Save PACAIRQHAPPENED to RESULT (otherwise unused), and set HARD_DIS
+ * as we are running with MSR[EE]=0.
*/
li r10,IRQS_ALL_DISABLED
stb r10,PACAIRQSOFTMASK(r13)
lbz r10,PACAIRQHAPPENED(r13)
- std r10,_DAR(r1)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
addi r3,r1,STACK_FRAME_OVERHEAD
bl system_reset_exception
@@ -897,33 +1054,101 @@
/*
* Restore soft mask settings.
*/
- ld r10,_DAR(r1)
+ ld r10,RESULT(r1)
stb r10,PACAIRQHAPPENED(r13)
ld r10,SOFTE(r1)
stb r10,PACAIRQSOFTMASK(r13)
- EXCEPTION_RESTORE_REGS EXC_STD
+ kuap_restore_amr r9, r10
+ EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
+ GEN_KVM system_reset
-EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
- INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+
+/**
+ * Interrupt 0x200 - Machine Check Interrupt (MCE).
+ * This is a non-maskable interrupt always taken in real-mode. It can be
+ * synchronous or asynchronous, caused by hardware or software, and it may be
+ * taken in a power-saving state.
+ *
+ * Handling:
+ * Similarly to system reset, this uses its own stack and PACA save area,
+ * the difference is re-entrancy is allowed on the machine check stack.
+ *
+ * machine_check_early is run in real mode, and carefully decodes the
+ * machine check and tries to handle it (e.g., flush the SLB if there was an
+ * error detected there), determines if it was recoverable and logs the
+ * event.
+ *
+ * This early code does not "reconcile" irq soft-mask state like SRESET or
+ * regular interrupts do, so irqs_disabled() among other things may not work
+ * properly (irq disable/enable already doesn't work because irq tracing can
+ * not work in real mode).
+ *
+ * Then, depending on the execution context when the interrupt is taken, there
+ * are 3 main actions:
+ * - Executing in kernel mode. The event is queued with irq_work, which means
+ * it is handled when it is next safe to do so (i.e., the kernel has enabled
+ * interrupts), which could be immediately when the interrupt returns. This
+ * avoids nasty issues like switching to virtual mode when the MMU is in a
+ * bad state, or when executing OPAL code. (SRESET is exposed to such issues,
+ * but it has different priorities). Check to see if the CPU was in power
+ * save, and return via the wake up code if it was.
+ *
+ * - Executing in user mode. machine_check_exception is run like a normal
+ * interrupt handler, which processes the data generated by the early handler.
+ *
+ * - Executing in guest mode. The interrupt is run with its KVM test, and
+ * branches to KVM to deal with. KVM may queue the event for the host
+ * to report later.
+ *
+ * This interrupt is not maskable, so if it triggers when MSR[RI] is clear,
+ * or SCRATCH0 is in use, it may cause a crash.
+ *
+ * KVM:
+ * See SRESET.
+ */
+INT_DEFINE_BEGIN(machine_check_early)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ IREALMODE_COMMON=1
/*
* MSR_RI is not enabled, because PACA_EXMC is being used, so a
* nested machine check corrupts it. machine_check_common enables
* MSR_RI.
*/
+ ISET_RI=0
+ ISTACK=0
+ IDAR=1
+ IDSISR=1
+ IRECONCILE=0
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+INT_DEFINE_END(machine_check_early)
+
+INT_DEFINE_BEGIN(machine_check)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ ISET_RI=0
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(machine_check)
+
+EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
+ GEN_INT_ENTRY machine_check_early, virt=0
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
#ifdef CONFIG_PPC_PSERIES
TRAMP_REAL_BEGIN(machine_check_fwnmi)
/* See comment at machine_check exception, don't turn on RI */
- INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+ GEN_INT_ENTRY machine_check_early, virt=0
#endif
-INT_KVM_HANDLER machine_check 0x200, EXC_STD, PACA_EXMC, 1
-
#define MACHINE_CHECK_HANDLER_WINDUP \
/* Clear MSR_RI before setting SRR0 and SRR1. */\
li r9,0; \
@@ -932,12 +1157,10 @@
lhz r12,PACA_IN_MCE(r13); \
subi r12,r12,1; \
sth r12,PACA_IN_MCE(r13); \
- EXCEPTION_RESTORE_REGS EXC_STD
+ EXCEPTION_RESTORE_REGS
EXC_COMMON_BEGIN(machine_check_early_common)
- mtctr r10 /* Restore ctr */
- mfspr r11,SPRN_SRR0
- mfspr r12,SPRN_SRR1
+ __GEN_REALMODE_COMMON_ENTRY machine_check_early
/*
* Switch to mc_emergency stack and handle re-entrancy (we limit
@@ -974,8 +1197,7 @@
bgt cr1,unrecoverable_mce /* Check if we hit limit of 4 */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- /* We don't touch AMR here, we never go to virtual mode */
- INT_COMMON 0x200, PACA_EXMC, 0, 0, 0, 1, 1
+ __GEN_COMMON_BODY machine_check_early
BEGIN_FTR_SECTION
bl enable_machine_check
@@ -983,12 +1205,30 @@
li r10,MSR_RI
mtmsrd r10,1
- bl save_nvgprs
+ /*
+ * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
+ * system_reset_common)
+ */
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ lbz r10,PACAIRQHAPPENED(r13)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
+ /*
+ * Restore soft mask settings.
+ */
+ ld r10,RESULT(r1)
+ stb r10,PACAIRQHAPPENED(r13)
+ ld r10,SOFTE(r1)
+ stb r10,PACAIRQSOFTMASK(r13)
+
#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
@@ -1063,23 +1303,25 @@
mtspr SPRN_CFAR,r10
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
MACHINE_CHECK_HANDLER_WINDUP
- /* See comment at machine_check exception, don't turn on RI */
- INT_HANDLER machine_check, 0x200, area=PACA_EXMC, ri=0, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY machine_check, virt=0
EXC_COMMON_BEGIN(machine_check_common)
/*
* Machine check is different because we use a different
* save area: PACA_EXMC instead of PACA_EXGEN.
*/
- INT_COMMON 0x200, PACA_EXMC, 1, 1, 1, 1, 1
+ GEN_COMMON machine_check
+
FINISH_NAP
/* Enable MSR_RI when finished with PACA_EXMC */
li r10,MSR_RI
mtmsrd r10,1
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_exception
- b ret_from_except
+ b interrupt_return
+
+ GEN_KVM machine_check
+
#ifdef CONFIG_PPC_P7_NAP
/*
@@ -1133,6 +1375,10 @@
andc r10,r10,r3
mtmsrd r10
+ lhz r12,PACA_IN_MCE(r13)
+ subi r12,r12,1
+ sth r12,PACA_IN_MCE(r13)
+
/* Invoke machine_check_exception to print MCE event and panic. */
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_exception
@@ -1146,21 +1392,51 @@
b .
+/**
+ * Interrupt 0x300 - Data Storage Interrupt (DSI).
+ * This is a synchronous interrupt generated due to a data access exception,
+ * e.g., a load orstore which does not have a valid page table entry with
+ * permissions. DAWR matches also fault here, as do RC updates, and minor misc
+ * errors e.g., copy/paste, AMO, certain invalid CI accesses, etc.
+ *
+ * Handling:
+ * - Hash MMU
+ * Go to do_hash_page first to see if the HPT can be filled from an entry in
+ * the Linux page table. Hash faults can hit in kernel mode in a fairly
+ * arbitrary state (e.g., interrupts disabled, locks held) when accessing
+ * "non-bolted" regions, e.g., vmalloc space. However these should always be
+ * backed by Linux page tables.
+ *
+ * If none is found, do a Linux page fault. Linux page faults can happen in
+ * kernel mode due to user copy operations of course.
+ *
+ * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
+ * MMU context, which may cause a DSI in the host, which must go to the
+ * KVM handler. MSR[IR] is not enabled, so the real-mode handler will
+ * always be used regardless of AIL setting.
+ *
+ * - Radix MMU
+ * The hardware loads from the Linux page table directly, so a fault goes
+ * immediately to Linux page fault.
+ *
+ * Conditions like DAWR match are handled on the way in to Linux page fault.
+ */
+INT_DEFINE_BEGIN(data_access)
+ IVEC=0x300
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access)
+
EXC_REAL_BEGIN(data_access, 0x300, 0x80)
- INT_HANDLER data_access, 0x300, ool=1, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY data_access, virt=0
EXC_REAL_END(data_access, 0x300, 0x80)
EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
- INT_HANDLER data_access, 0x300, ool=1, virt=1, dar=1, dsisr=1
+ GEN_INT_ENTRY data_access, virt=1
EXC_VIRT_END(data_access, 0x4300, 0x80)
-INT_KVM_HANDLER data_access, 0x300, EXC_STD, PACA_EXGEN, 1
EXC_COMMON_BEGIN(data_access_common)
- /*
- * Here r13 points to the paca, r9 contains the saved CR,
- * SRR0 and SRR1 are saved in r11 and r12,
- * r9 - r13 are saved in paca->exgen.
- * EX_DAR and EX_DSISR have saved DAR/DSISR
- */
- INT_COMMON 0x300, PACA_EXGEN, 1, 1, 1, 1, 1
+ GEN_COMMON data_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
BEGIN_MMU_FTR_SECTION
@@ -1171,16 +1447,46 @@
b handle_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ GEN_KVM data_access
+
+
+/**
+ * Interrupt 0x380 - Data Segment Interrupt (DSLB).
+ * This is a synchronous interrupt in response to an MMU fault missing SLB
+ * entry for HPT, or an address outside RPT translation range.
+ *
+ * Handling:
+ * - HPT:
+ * This refills the SLB, or reports an access fault similarly to a bad page
+ * fault. When coming from user-mode, the SLB handler may access any kernel
+ * data, though it may itself take a DSLB. When coming from kernel mode,
+ * recursive faults must be avoided so access is restricted to the kernel
+ * image text/data, kernel stack, and any data allocated below
+ * ppc64_bolted_size (first segment). The kernel handler must avoid stomping
+ * on user-handler data structures.
+ *
+ * KVM: Same as 0x300, DSLB must test for KVM guest.
+ *
+ * A dedicated save area EXSLB is used (XXX: but it actually need not be
+ * these days, we could use EXGEN).
+ */
+INT_DEFINE_BEGIN(data_access_slb)
+ IVEC=0x380
+ IAREA=PACA_EXSLB
+ IRECONCILE=0
+ IDAR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access_slb)
EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
- INT_HANDLER data_access_slb, 0x380, ool=1, area=PACA_EXSLB, dar=1, kvm=1
+ GEN_INT_ENTRY data_access_slb, virt=0
EXC_REAL_END(data_access_slb, 0x380, 0x80)
EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
- INT_HANDLER data_access_slb, 0x380, virt=1, area=PACA_EXSLB, dar=1
+ GEN_INT_ENTRY data_access_slb, virt=1
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
-INT_KVM_HANDLER data_access_slb, 0x380, EXC_STD, PACA_EXSLB, 1
EXC_COMMON_BEGIN(data_access_slb_common)
- INT_COMMON 0x380, PACA_EXSLB, 1, 1, 0, 1, 0
+ GEN_COMMON data_access_slb
ld r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
@@ -1188,31 +1494,50 @@
bl do_slb_fault
cmpdi r3,0
bne- 1f
- b fast_exception_return
+ b fast_interrupt_return
1: /* Error case */
MMU_FTR_SECTION_ELSE
/* Radix case, access is outside page table range */
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
ld r4,_DAR(r1)
ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
- b ret_from_except
+ b interrupt_return
+ GEN_KVM data_access_slb
+
+
+/**
+ * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSI, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR), and status in SRR1 (rather than DSISR).
+ */
+INT_DEFINE_BEGIN(instruction_access)
+ IVEC=0x400
+ IISIDE=1
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access)
EXC_REAL_BEGIN(instruction_access, 0x400, 0x80)
- INT_HANDLER instruction_access, 0x400, ool=1, kvm=1
+ GEN_INT_ENTRY instruction_access, virt=0
EXC_REAL_END(instruction_access, 0x400, 0x80)
EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
- INT_HANDLER instruction_access, 0x400, virt=1
+ GEN_INT_ENTRY instruction_access, virt=1
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
-INT_KVM_HANDLER instruction_access, 0x400, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(instruction_access_common)
- INT_COMMON 0x400, PACA_EXGEN, 1, 1, 1, 2, 2
+ GEN_COMMON instruction_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
BEGIN_MMU_FTR_SECTION
@@ -1223,16 +1548,37 @@
b handle_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ GEN_KVM instruction_access
+
+
+/**
+ * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSLB, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR).
+ */
+INT_DEFINE_BEGIN(instruction_access_slb)
+ IVEC=0x480
+ IAREA=PACA_EXSLB
+ IRECONCILE=0
+ IISIDE=1
+ IDAR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access_slb)
EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
- INT_HANDLER instruction_access_slb, 0x480, ool=1, area=PACA_EXSLB, kvm=1
+ GEN_INT_ENTRY instruction_access_slb, virt=0
EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
- INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB
+ GEN_INT_ENTRY instruction_access_slb, virt=1
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
-INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0
EXC_COMMON_BEGIN(instruction_access_slb_common)
- INT_COMMON 0x480, PACA_EXSLB, 1, 1, 0, 2, 0
+ GEN_COMMON instruction_access_slb
ld r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
@@ -1240,54 +1586,125 @@
bl do_slb_fault
cmpdi r3,0
bne- 1f
- b fast_exception_return
+ b fast_interrupt_return
1: /* Error case */
MMU_FTR_SECTION_ELSE
/* Radix case, access is outside page table range */
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
ld r4,_DAR(r1)
ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
- b ret_from_except
+ b interrupt_return
+
+ GEN_KVM instruction_access_slb
+
+
+/**
+ * Interrupt 0x500 - External Interrupt.
+ * This is an asynchronous maskable interrupt in response to an "external
+ * exception" from the interrupt controller or hypervisor (e.g., device
+ * interrupt). It is maskable in hardware by clearing MSR[EE], and
+ * soft-maskable with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * When running in HV mode, Linux sets up the LPCR[LPES] bit such that
+ * interrupts are delivered with HSRR registers, guests use SRRs, which
+ * reqiures IHSRR_IF_HVMODE.
+ *
+ * On bare metal POWER9 and later, Linux sets the LPCR[HVICE] bit such that
+ * external interrupts are delivered as Hypervisor Virtualization Interrupts
+ * rather than External Interrupts.
+ *
+ * Handling:
+ * This calls into Linux IRQ handler. NVGPRs are not saved to reduce overhead,
+ * because registers at the time of the interrupt are not so important as it is
+ * asynchronous.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(hardware_interrupt)
+ IVEC=0x500
+ IHSRR_IF_HVMODE=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(hardware_interrupt)
EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
- INT_HANDLER hardware_interrupt, 0x500, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY hardware_interrupt, virt=0
EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
- INT_HANDLER hardware_interrupt, 0x500, virt=1, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY hardware_interrupt, virt=1
EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
-INT_KVM_HANDLER hardware_interrupt, 0x500, EXC_HV_OR_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ)
+EXC_COMMON_BEGIN(hardware_interrupt_common)
+ GEN_COMMON hardware_interrupt
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_IRQ
+ b interrupt_return
+ GEN_KVM hardware_interrupt
+
+
+/**
+ * Interrupt 0x600 - Alignment Interrupt
+ * This is a synchronous interrupt in response to data alignment fault.
+ */
+INT_DEFINE_BEGIN(alignment)
+ IVEC=0x600
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(alignment)
EXC_REAL_BEGIN(alignment, 0x600, 0x100)
- INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY alignment, virt=0
EXC_REAL_END(alignment, 0x600, 0x100)
EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
- INT_HANDLER alignment, 0x600, virt=1, dar=1, dsisr=1
+ GEN_INT_ENTRY alignment, virt=1
EXC_VIRT_END(alignment, 0x4600, 0x100)
-INT_KVM_HANDLER alignment, 0x600, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(alignment_common)
- INT_COMMON 0x600, PACA_EXGEN, 1, 1, 1, 1, 1
- bl save_nvgprs
+ GEN_COMMON alignment
addi r3,r1,STACK_FRAME_OVERHEAD
bl alignment_exception
- b ret_from_except
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM alignment
+
+
+/**
+ * Interrupt 0x700 - Program Interrupt (program check).
+ * This is a synchronous interrupt in response to various instruction faults:
+ * traps, privilege errors, TM errors, floating point exceptions.
+ *
+ * Handling:
+ * This interrupt may use the "emergency stack" in some cases when being taken
+ * from kernel context, which complicates handling.
+ */
+INT_DEFINE_BEGIN(program_check)
+ IVEC=0x700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(program_check)
EXC_REAL_BEGIN(program_check, 0x700, 0x100)
- INT_HANDLER program_check, 0x700, kvm=1
+ GEN_INT_ENTRY program_check, virt=0
EXC_REAL_END(program_check, 0x700, 0x100)
EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
- INT_HANDLER program_check, 0x700, virt=1
+ GEN_INT_ENTRY program_check, virt=1
EXC_VIRT_END(program_check, 0x4700, 0x100)
-INT_KVM_HANDLER program_check, 0x700, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(program_check_common)
+ __GEN_COMMON_ENTRY program_check
+
/*
* It's possible to receive a TM Bad Thing type program check with
* userspace register values (in particular r1), but with SRR1 reporting
@@ -1298,42 +1715,64 @@
*/
andi. r10,r12,MSR_PR
- bne 2f /* If userspace, go normal path */
+ bne .Lnormal_stack /* If userspace, go normal path */
andis. r10,r12,(SRR1_PROGTM)@h
- bne 1f /* If TM, emergency */
+ bne .Lemergency_stack /* If TM, emergency */
cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */
- blt 2f /* normal path if not */
+ blt .Lnormal_stack /* normal path if not */
/* Use the emergency stack */
-1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */
+.Lemergency_stack:
+ andi. r10,r12,MSR_PR /* Set CR0 correctly for label */
/* 3 in EXCEPTION_PROLOG_COMMON */
mr r10,r1 /* Save r1 */
ld r1,PACAEMERGSP(r13) /* Use emergency stack */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0
- b 3f
-2:
- INT_COMMON 0x700, PACA_EXGEN, 1, 1, 1, 0, 0
-3:
- bl save_nvgprs
+ __ISTACK(program_check)=0
+ __GEN_COMMON_BODY program_check
+ b .Ldo_program_check
+
+.Lnormal_stack:
+ __ISTACK(program_check)=1
+ __GEN_COMMON_BODY program_check
+
+.Ldo_program_check:
addi r3,r1,STACK_FRAME_OVERHEAD
bl program_check_exception
- b ret_from_except
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM program_check
+
+
+/*
+ * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
+ * This is a synchronous interrupt in response to executing an fp instruction
+ * with MSR[FP]=0.
+ *
+ * Handling:
+ * This will load FP registers and enable the FP bit if coming from userspace,
+ * otherwise report a bad kernel use of FP.
+ */
+INT_DEFINE_BEGIN(fp_unavailable)
+ IVEC=0x800
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(fp_unavailable)
EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
- INT_HANDLER fp_unavailable, 0x800, kvm=1
+ GEN_INT_ENTRY fp_unavailable, virt=0
EXC_REAL_END(fp_unavailable, 0x800, 0x100)
EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100)
- INT_HANDLER fp_unavailable, 0x800, virt=1
+ GEN_INT_ENTRY fp_unavailable, virt=1
EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
-INT_KVM_HANDLER fp_unavailable, 0x800, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(fp_unavailable_common)
- INT_COMMON 0x800, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
@@ -1350,88 +1789,185 @@
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
bl load_up_fpu
- b fast_exception_return
+ b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
+ GEN_KVM fp_unavailable
+
+
+/**
+ * Interrupt 0x900 - Decrementer Interrupt.
+ * This is an asynchronous interrupt in response to a decrementer exception
+ * (e.g., DEC has wrapped below zero). It is maskable in hardware by clearing
+ * MSR[EE], and soft-maskable with IRQS_DISABLED mask (i.e.,
+ * local_irq_disable()).
+ *
+ * Handling:
+ * This calls into Linux timer handler. NVGPRs are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and bump the decrementer to a high value, leaving MSR[EE] enabled
+ * in the interrupted context.
+ * If PPC_WATCHDOG is configured, the soft masked handler will actually set
+ * things back up to run soft_nmi_interrupt as a regular interrupt handler
+ * on the emergency stack.
+ */
+INT_DEFINE_BEGIN(decrementer)
+ IVEC=0x900
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(decrementer)
EXC_REAL_BEGIN(decrementer, 0x900, 0x80)
- INT_HANDLER decrementer, 0x900, ool=1, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY decrementer, virt=0
EXC_REAL_END(decrementer, 0x900, 0x80)
EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
- INT_HANDLER decrementer, 0x900, ool=1, virt=1, bitmask=IRQS_DISABLED
+ GEN_INT_ENTRY decrementer, virt=1
EXC_VIRT_END(decrementer, 0x4900, 0x80)
-INT_KVM_HANDLER decrementer, 0x900, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
+EXC_COMMON_BEGIN(decrementer_common)
+ GEN_COMMON decrementer
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl timer_interrupt
+ b interrupt_return
+ GEN_KVM decrementer
+
+
+/**
+ * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
+ * This is an asynchronous interrupt, similar to 0x900 but for the HDEC
+ * register.
+ *
+ * Handling:
+ * Linux does not use this outside KVM where it's used to keep a host timer
+ * while the guest is given control of DEC. It should normally be caught by
+ * the KVM test and routed there.
+ */
+INT_DEFINE_BEGIN(hdecrementer)
+ IVEC=0x980
+ IHSRR=1
+ ISTACK=0
+ IRECONCILE=0
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(hdecrementer)
EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80)
- INT_HANDLER hdecrementer, 0x980, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY hdecrementer, virt=0
EXC_REAL_END(hdecrementer, 0x980, 0x80)
EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
- INT_HANDLER hdecrementer, 0x980, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY hdecrementer, virt=1
EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
-INT_KVM_HANDLER hdecrementer, 0x980, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
+EXC_COMMON_BEGIN(hdecrementer_common)
+ __GEN_COMMON_ENTRY hdecrementer
+ /*
+ * Hypervisor decrementer interrupts not caught by the KVM test
+ * shouldn't occur but are sometimes left pending on exit from a KVM
+ * guest. We don't need to do anything to clear them, as they are
+ * edge-triggered.
+ *
+ * Be careful to avoid touching the kernel stack.
+ */
+ ld r10,PACA_EXGEN+EX_CTR(r13)
+ mtctr r10
+ mtcrf 0x80,r9
+ ld r9,PACA_EXGEN+EX_R9(r13)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ HRFI_TO_KERNEL
+ GEN_KVM hdecrementer
+
+
+/**
+ * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsndp doorbell.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * Guests may use this for IPIs between threads in a core if the
+ * hypervisor supports it. NVGPRS are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, leaving MSR[EE] enabled in the interrupted context because the
+ * doorbells are edge triggered.
+ */
+INT_DEFINE_BEGIN(doorbell_super)
+ IVEC=0xa00
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(doorbell_super)
EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100)
- INT_HANDLER doorbell_super, 0xa00, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY doorbell_super, virt=0
EXC_REAL_END(doorbell_super, 0xa00, 0x100)
EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
- INT_HANDLER doorbell_super, 0xa00, virt=1, bitmask=IRQS_DISABLED
+ GEN_INT_ENTRY doorbell_super, virt=1
EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
-INT_KVM_HANDLER doorbell_super, 0xa00, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(doorbell_super_common)
+ GEN_COMMON doorbell_super
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception)
+ bl doorbell_exception
#else
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+
+ GEN_KVM doorbell_super
EXC_REAL_NONE(0xb00, 0x100)
EXC_VIRT_NONE(0x4b00, 0x100)
-/*
- * system call / hypercall (0xc00, 0x4c00)
- *
- * The system call exception is invoked with "sc 0" and does not alter HV bit.
- *
- * The hypercall is invoked with "sc 1" and sets HV=1.
+/**
+ * Interrupt 0xc00 - System Call Interrupt (syscall, hcall).
+ * This is a synchronous interrupt invoked with the "sc" instruction. The
+ * system call is invoked with "sc 0" and does not alter the HV bit, so it
+ * is directed to the currently running OS. The hypercall is invoked with
+ * "sc 1" and it sets HV=1, so it elevates to hypervisor.
*
* In HPT, sc 1 always goes to 0xc00 real mode. In RADIX, sc 1 can go to
* 0x4c00 virtual mode.
*
+ * Handling:
+ * If the KVM test fires then it was due to a hypercall and is accordingly
+ * routed to KVM. Otherwise this executes a normal Linux system call.
+ *
* Call convention:
*
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
- *
- * For hypercalls, the register convention is as follows:
- * r0 volatile
- * r1-2 nonvolatile
- * r3 volatile parameter and return value for status
- * r4-r10 volatile input and output value
- * r11 volatile hypercall number and output value
- * r12 volatile input and output value
- * r13-r31 nonvolatile
- * LR nonvolatile
- * CTR volatile
- * XER volatile
- * CR0-1 CR5-7 volatile
- * CR2-4 nonvolatile
- * Other registers nonvolatile
+ * syscall and hypercalls register conventions are documented in
+ * Documentation/powerpc/syscall64-abi.rst and
+ * Documentation/powerpc/papr_hcalls.rst respectively.
*
* The intersection of volatile registers that don't contain possible
* inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
* without saving, though xer is not a good idea to use, as hardware may
* interpret some bits so it may be costly to change them.
*/
+INT_DEFINE_BEGIN(system_call)
+ IVEC=0xc00
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(system_call)
+
.macro SYSTEM_CALL virt
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
/*
@@ -1446,7 +1982,7 @@
GET_PACA(r13)
std r10,PACA_EXGEN+EX_R10(r13)
INTERRUPT_TO_KERNEL
- KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */
+ KVMTEST system_call /* uses r10, branch to system_call_kvm */
mfctr r9
#else
mr r9,r13
@@ -1505,6 +2041,7 @@
EXC_VIRT_END(system_call, 0x4c00, 0x100)
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+TRAMP_REAL_BEGIN(system_call_kvm)
/*
* This is a hcall, so register convention is as above, with these
* differences:
@@ -1512,43 +2049,95 @@
* ctr = orig r13
* orig r10 saved in PACA
*/
-TRAMP_KVM_BEGIN(system_call_kvm)
/*
* Save the PPR (on systems that support it) before changing to
* HMT_MEDIUM. That allows the KVM code to save that value into the
* guest state (it is the guest's PPR value).
*/
- OPT_GET_SPR(r10, SPRN_PPR, CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_PPR
+ std r10,HSTATE_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
HMT_MEDIUM
- OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r10, CPU_FTR_HAS_PPR)
mfctr r10
SET_SCRATCH0(r10)
- std r9,PACA_EXGEN+EX_R9(r13)
- mfcr r9
- KVM_HANDLER 0xc00, EXC_STD, PACA_EXGEN, 0
+ mfcr r10
+ std r12,HSTATE_SCRATCH0(r13)
+ sldi r12,r10,32
+ ori r12,r12,0xc00
+#ifdef CONFIG_RELOCATABLE
+ /*
+ * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
+ * outside the head section.
+ */
+ __LOAD_FAR_HANDLER(r10, kvmppc_interrupt)
+ mtctr r10
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ bctr
+#else
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ b kvmppc_interrupt
+#endif
#endif
+/**
+ * Interrupt 0xd00 - Trace Interrupt.
+ * This is a synchronous interrupt in response to instruction step or
+ * breakpoint faults.
+ */
+INT_DEFINE_BEGIN(single_step)
+ IVEC=0xd00
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(single_step)
+
EXC_REAL_BEGIN(single_step, 0xd00, 0x100)
- INT_HANDLER single_step, 0xd00, kvm=1
+ GEN_INT_ENTRY single_step, virt=0
EXC_REAL_END(single_step, 0xd00, 0x100)
EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
- INT_HANDLER single_step, 0xd00, virt=1
+ GEN_INT_ENTRY single_step, virt=1
EXC_VIRT_END(single_step, 0x4d00, 0x100)
-INT_KVM_HANDLER single_step, 0xd00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(single_step_common, 0xd00, single_step_exception)
+EXC_COMMON_BEGIN(single_step_common)
+ GEN_COMMON single_step
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl single_step_exception
+ b interrupt_return
+ GEN_KVM single_step
+
+
+/**
+ * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest data access.
+ *
+ * Handling:
+ * This should always get routed to KVM. In radix MMU mode, this is caused
+ * by a guest nested radix access that can't be performed due to the
+ * partition scope page table. In hash mode, this can be caused by guests
+ * running with translation disabled (virtual real mode) or with VPM enabled.
+ * KVM will update the page table structures or disallow the access.
+ */
+INT_DEFINE_BEGIN(h_data_storage)
+ IVEC=0xe00
+ IHSRR=1
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_data_storage)
EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20)
- INT_HANDLER h_data_storage, 0xe00, ool=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY h_data_storage, virt=0, ool=1
EXC_REAL_END(h_data_storage, 0xe00, 0x20)
EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
- INT_HANDLER h_data_storage, 0xe00, ool=1, virt=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY h_data_storage, virt=1, ool=1
EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
-INT_KVM_HANDLER h_data_storage, 0xe00, EXC_HV, PACA_EXGEN, 1
EXC_COMMON_BEGIN(h_data_storage_common)
- INT_COMMON 0xe00, PACA_EXGEN, 1, 1, 1, 1, 1
- bl save_nvgprs
+ GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
ld r4,_DAR(r1)
@@ -1557,56 +2146,125 @@
MMU_FTR_SECTION_ELSE
bl unknown_exception
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
- b ret_from_except
+ b interrupt_return
+ GEN_KVM h_data_storage
+
+
+/**
+ * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest instruction fetch, similar to HDSI.
+ */
+INT_DEFINE_BEGIN(h_instr_storage)
+ IVEC=0xe20
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_instr_storage)
EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20)
- INT_HANDLER h_instr_storage, 0xe20, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_instr_storage, virt=0, ool=1
EXC_REAL_END(h_instr_storage, 0xe20, 0x20)
EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
- INT_HANDLER h_instr_storage, 0xe20, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_instr_storage, virt=1, ool=1
EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
-INT_KVM_HANDLER h_instr_storage, 0xe20, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception)
+EXC_COMMON_BEGIN(h_instr_storage_common)
+ GEN_COMMON h_instr_storage
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b interrupt_return
+ GEN_KVM h_instr_storage
+
+
+/**
+ * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
+ */
+INT_DEFINE_BEGIN(emulation_assist)
+ IVEC=0xe40
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(emulation_assist)
EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20)
- INT_HANDLER emulation_assist, 0xe40, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY emulation_assist, virt=0, ool=1
EXC_REAL_END(emulation_assist, 0xe40, 0x20)
EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
- INT_HANDLER emulation_assist, 0xe40, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY emulation_assist, virt=1, ool=1
EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
-INT_KVM_HANDLER emulation_assist, 0xe40, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt)
+EXC_COMMON_BEGIN(emulation_assist_common)
+ GEN_COMMON emulation_assist
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl emulation_assist_interrupt
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+
+ GEN_KVM emulation_assist
-/*
- * hmi_exception trampoline is a special case. It jumps to hmi_exception_early
- * first, and then eventaully from there to the trampoline to get into virtual
- * mode.
+/**
+ * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
+ * This is an asynchronous interrupt caused by a Hypervisor Maintenance
+ * Exception. It is always taken in real mode but uses HSRR registers
+ * unlike SRESET and MCE.
+ *
+ * It is maskable in hardware by clearing MSR[EE], and partially soft-maskable
+ * with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * This is a special case, this is handled similarly to machine checks, with an
+ * initial real mode handler that is not soft-masked, which attempts to fix the
+ * problem. Then a regular handler which is soft-maskable and reports the
+ * problem.
+ *
+ * The emergency stack is used for the early real mode handler.
+ *
+ * XXX: unclear why MCE and HMI schemes could not be made common, e.g.,
+ * either use soft-masking for the MCE, or use irq_work for the HMI.
+ *
+ * KVM:
+ * Unlike MCE, this calls into KVM without calling the real mode handler
+ * first.
*/
+INT_DEFINE_BEGIN(hmi_exception_early)
+ IVEC=0xe60
+ IHSRR=1
+ IREALMODE_COMMON=1
+ ISTACK=0
+ IRECONCILE=0
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception_early)
+
+INT_DEFINE_BEGIN(hmi_exception)
+ IVEC=0xe60
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception)
+
EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20)
- INT_HANDLER hmi_exception, 0xe60, ool=1, early=1, hsrr=EXC_HV, ri=0, kvm=1
+ GEN_INT_ENTRY hmi_exception_early, virt=0, ool=1
EXC_REAL_END(hmi_exception, 0xe60, 0x20)
EXC_VIRT_NONE(0x4e60, 0x20)
-INT_KVM_HANDLER hmi_exception, 0xe60, EXC_HV, PACA_EXGEN, 0
+
EXC_COMMON_BEGIN(hmi_exception_early_common)
- mtctr r10 /* Restore ctr */
- mfspr r11,SPRN_HSRR0 /* Save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* Save HSRR1 */
+ __GEN_REALMODE_COMMON_ENTRY hmi_exception_early
+
mr r10,r1 /* Save r1 */
ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- /* We don't touch AMR here, we never go to virtual mode */
- INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0
+ __GEN_COMMON_BODY hmi_exception_early
addi r3,r1,STACK_FRAME_OVERHEAD
bl hmi_exception_realmode
cmpdi cr0,r3,0
bne 1f
- EXCEPTION_RESTORE_REGS EXC_HV
+ EXCEPTION_RESTORE_REGS hsrr=1
HRFI_TO_USER_OR_KERNEL
1:
@@ -1614,41 +2272,84 @@
* Go to virtual mode and pull the HMI event information from
* firmware.
*/
- EXCEPTION_RESTORE_REGS EXC_HV
- INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ EXCEPTION_RESTORE_REGS hsrr=1
+ GEN_INT_ENTRY hmi_exception, virt=0
+
+ GEN_KVM hmi_exception_early
EXC_COMMON_BEGIN(hmi_exception_common)
- INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0
+ GEN_COMMON hmi_exception
FINISH_NAP
RUNLATCH_ON
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM hmi_exception
+
+
+/**
+ * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsnd doorbell.
+ * Similar to the 0xa00 doorbell but for host rather than guest.
+ */
+INT_DEFINE_BEGIN(h_doorbell)
+ IVEC=0xe80
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_doorbell)
EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20)
- INT_HANDLER h_doorbell, 0xe80, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_doorbell, virt=0, ool=1
EXC_REAL_END(h_doorbell, 0xe80, 0x20)
EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
- INT_HANDLER h_doorbell, 0xe80, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_doorbell, virt=1, ool=1
EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
-INT_KVM_HANDLER h_doorbell, 0xe80, EXC_HV, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(h_doorbell_common)
+ GEN_COMMON h_doorbell
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception)
+ bl doorbell_exception
#else
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+ GEN_KVM h_doorbell
+
+
+/**
+ * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
+ * This is an asynchronous interrupt in response to an "external exception".
+ * Similar to 0x500 but for host only.
+ */
+INT_DEFINE_BEGIN(h_virt_irq)
+ IVEC=0xea0
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_virt_irq)
EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20)
- INT_HANDLER h_virt_irq, 0xea0, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_virt_irq, virt=0, ool=1
EXC_REAL_END(h_virt_irq, 0xea0, 0x20)
EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
- INT_HANDLER h_virt_irq, 0xea0, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_virt_irq, virt=1, ool=1
EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
-INT_KVM_HANDLER h_virt_irq, 0xea0, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ)
+EXC_COMMON_BEGIN(h_virt_irq_common)
+ GEN_COMMON h_virt_irq
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_IRQ
+ b interrupt_return
+
+ GEN_KVM h_virt_irq
EXC_REAL_NONE(0xec0, 0x20)
@@ -1657,25 +2358,69 @@
EXC_VIRT_NONE(0x4ee0, 0x20)
+/*
+ * Interrupt 0xf00 - Performance Monitor Interrupt (PMI, PMU).
+ * This is an asynchronous interrupt in response to a PMU exception.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_PMI_DISABLED mask (NOTE: NOT local_irq_disable()).
+ *
+ * Handling:
+ * This calls into the perf subsystem.
+ *
+ * Like the watchdog soft-nmi, it appears an NMI interrupt to Linux, in that it
+ * runs under local_irq_disable. However it may be soft-masked in
+ * powerpc-specific code.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(performance_monitor)
+ IVEC=0xf00
+ IMASK=IRQS_PMI_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(performance_monitor)
+
EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20)
- INT_HANDLER performance_monitor, 0xf00, ool=1, bitmask=IRQS_PMI_DISABLED, kvm=1
+ GEN_INT_ENTRY performance_monitor, virt=0, ool=1
EXC_REAL_END(performance_monitor, 0xf00, 0x20)
EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
- INT_HANDLER performance_monitor, 0xf00, ool=1, virt=1, bitmask=IRQS_PMI_DISABLED
+ GEN_INT_ENTRY performance_monitor, virt=1, ool=1
EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
-INT_KVM_HANDLER performance_monitor, 0xf00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception)
+EXC_COMMON_BEGIN(performance_monitor_common)
+ GEN_COMMON performance_monitor
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl performance_monitor_exception
+ b interrupt_return
+ GEN_KVM performance_monitor
+
+
+/**
+ * Interrupt 0xf20 - Vector Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a vector (or altivec) instruction with MSR[VEC]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(altivec_unavailable)
+ IVEC=0xf20
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_unavailable)
EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
- INT_HANDLER altivec_unavailable, 0xf20, ool=1, kvm=1
+ GEN_INT_ENTRY altivec_unavailable, virt=0, ool=1
EXC_REAL_END(altivec_unavailable, 0xf20, 0x20)
EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20)
- INT_HANDLER altivec_unavailable, 0xf20, ool=1, virt=1
+ GEN_INT_ENTRY altivec_unavailable, virt=1, ool=1
EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20)
-INT_KVM_HANDLER altivec_unavailable, 0xf20, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(altivec_unavailable_common)
- INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON altivec_unavailable
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
beq 1f
@@ -1689,34 +2434,47 @@
END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
#endif
bl load_up_altivec
- b fast_exception_return
+ b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM altivec_unavailable
+
+
+/**
+ * Interrupt 0xf40 - VSX Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a VSX instruction with MSR[VSX]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(vsx_unavailable)
+ IVEC=0xf40
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(vsx_unavailable)
EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
- INT_HANDLER vsx_unavailable, 0xf40, ool=1, kvm=1
+ GEN_INT_ENTRY vsx_unavailable, virt=0, ool=1
EXC_REAL_END(vsx_unavailable, 0xf40, 0x20)
EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20)
- INT_HANDLER vsx_unavailable, 0xf40, ool=1, virt=1
+ GEN_INT_ENTRY vsx_unavailable, virt=1, ool=1
EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20)
-INT_KVM_HANDLER vsx_unavailable, 0xf40, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(vsx_unavailable_common)
- INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON vsx_unavailable
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
beq 1f
@@ -1732,40 +2490,80 @@
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM vsx_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can be
+ * resolved by the OS (e.g., FSCR, MSR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(facility_unavailable)
+ IVEC=0xf60
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(facility_unavailable)
EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20)
- INT_HANDLER facility_unavailable, 0xf60, ool=1, kvm=1
+ GEN_INT_ENTRY facility_unavailable, virt=0, ool=1
EXC_REAL_END(facility_unavailable, 0xf60, 0x20)
EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
- INT_HANDLER facility_unavailable, 0xf60, ool=1, virt=1
+ GEN_INT_ENTRY facility_unavailable, virt=1, ool=1
EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
-INT_KVM_HANDLER facility_unavailable, 0xf60, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception)
+EXC_COMMON_BEGIN(facility_unavailable_common)
+ GEN_COMMON facility_unavailable
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl facility_unavailable_exception
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM facility_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can only
+ * be resolved in HV mode (e.g., HFSCR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(h_facility_unavailable)
+ IVEC=0xf80
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_facility_unavailable)
EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20)
- INT_HANDLER h_facility_unavailable, 0xf80, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_facility_unavailable, virt=0, ool=1
EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20)
EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
- INT_HANDLER h_facility_unavailable, 0xf80, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_facility_unavailable, virt=1, ool=1
EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
-INT_KVM_HANDLER h_facility_unavailable, 0xf80, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception)
+EXC_COMMON_BEGIN(h_facility_unavailable_common)
+ GEN_COMMON h_facility_unavailable
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl facility_unavailable_exception
+ REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
+ b interrupt_return
+
+ GEN_KVM h_facility_unavailable
EXC_REAL_NONE(0xfa0, 0x20)
@@ -1781,56 +2579,95 @@
EXC_VIRT_NONE(0x5100, 0x100)
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_system_error)
+ IVEC=0x1200
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_system_error)
+
EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
- INT_HANDLER cbe_system_error, 0x1200, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_system_error, virt=0
EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
EXC_VIRT_NONE(0x5200, 0x100)
-INT_KVM_HANDLER cbe_system_error, 0x1200, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception)
+EXC_COMMON_BEGIN(cbe_system_error_common)
+ GEN_COMMON cbe_system_error
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_system_error_exception
+ b interrupt_return
+
+ GEN_KVM cbe_system_error
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1200, 0x100)
EXC_VIRT_NONE(0x5200, 0x100)
#endif
+INT_DEFINE_BEGIN(instruction_breakpoint)
+ IVEC=0x1300
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_SKIP=1
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_breakpoint)
+
EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100)
- INT_HANDLER instruction_breakpoint, 0x1300, kvm=1
+ GEN_INT_ENTRY instruction_breakpoint, virt=0
EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100)
EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
- INT_HANDLER instruction_breakpoint, 0x1300, virt=1
+ GEN_INT_ENTRY instruction_breakpoint, virt=1
EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
-INT_KVM_HANDLER instruction_breakpoint, 0x1300, EXC_STD, PACA_EXGEN, 1
-EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception)
+EXC_COMMON_BEGIN(instruction_breakpoint_common)
+ GEN_COMMON instruction_breakpoint
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl instruction_breakpoint_exception
+ b interrupt_return
+
+ GEN_KVM instruction_breakpoint
EXC_REAL_NONE(0x1400, 0x100)
EXC_VIRT_NONE(0x5400, 0x100)
-EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
- INT_HANDLER denorm_exception_hv, 0x1500, early=2, hsrr=EXC_HV
+/**
+ * Interrupt 0x1500 - Soft Patch Interrupt
+ *
+ * Handling:
+ * This is an implementation specific interrupt which can be used for a
+ * range of exceptions.
+ *
+ * This interrupt handler is unique in that it runs the denormal assist
+ * code even for guests (and even in guest context) without going to KVM,
+ * for speed. POWER9 does not raise denorm exceptions, so this special case
+ * could be phased out in future to reduce special cases.
+ */
+INT_DEFINE_BEGIN(denorm_exception)
+ IVEC=0x1500
+ IHSRR=1
+ IBRANCH_TO_COMMON=0
+ IKVM_REAL=1
+INT_DEFINE_END(denorm_exception)
+
+EXC_REAL_BEGIN(denorm_exception, 0x1500, 0x100)
+ GEN_INT_ENTRY denorm_exception, virt=0
#ifdef CONFIG_PPC_DENORMALISATION
- mfspr r10,SPRN_HSRR1
- andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
bne+ denorm_assist
#endif
- KVMTEST denorm_exception_hv, EXC_HV 0x1500
- INT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV, 1
-EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
-
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=0
+EXC_REAL_END(denorm_exception, 0x1500, 0x100)
#ifdef CONFIG_PPC_DENORMALISATION
EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
- INT_HANDLER denorm_exception, 0x1500, 0, 2, 1, EXC_HV, PACA_EXGEN, 1, 0, 0, 0, 0
- mfspr r10,SPRN_HSRR1
- andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
+ GEN_INT_ENTRY denorm_exception, virt=1
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
bne+ denorm_assist
- INT_VIRT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=1
EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
#else
EXC_VIRT_NONE(0x5500, 0x100)
#endif
-INT_KVM_HANDLER denorm_exception_hv, 0x1500, EXC_HV, PACA_EXGEN, 0
-
#ifdef CONFIG_PPC_DENORMALISATION
TRAMP_REAL_BEGIN(denorm_assist)
BEGIN_FTR_SECTION
@@ -1887,7 +2724,10 @@
mtspr SPRN_HSRR0,r11
mtcrf 0x80,r9
ld r9,PACA_EXGEN+EX_R9(r13)
- RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+ ld r10,PACA_EXGEN+EX_PPR(r13)
+ mtspr SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
BEGIN_FTR_SECTION
ld r10,PACA_EXGEN+EX_CFAR(r13)
mtspr SPRN_CFAR,r10
@@ -1900,43 +2740,88 @@
b .
#endif
-EXC_COMMON(denorm_common, 0x1500, unknown_exception)
+EXC_COMMON_BEGIN(denorm_exception_common)
+ GEN_COMMON denorm_exception
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b interrupt_return
+
+ GEN_KVM denorm_exception
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_maintenance)
+ IVEC=0x1600
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_maintenance)
+
EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
- INT_HANDLER cbe_maintenance, 0x1600, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_maintenance, virt=0
EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
EXC_VIRT_NONE(0x5600, 0x100)
-INT_KVM_HANDLER cbe_maintenance, 0x1600, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception)
+EXC_COMMON_BEGIN(cbe_maintenance_common)
+ GEN_COMMON cbe_maintenance
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_maintenance_exception
+ b interrupt_return
+
+ GEN_KVM cbe_maintenance
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1600, 0x100)
EXC_VIRT_NONE(0x5600, 0x100)
#endif
+INT_DEFINE_BEGIN(altivec_assist)
+ IVEC=0x1700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_assist)
+
EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100)
- INT_HANDLER altivec_assist, 0x1700, kvm=1
+ GEN_INT_ENTRY altivec_assist, virt=0
EXC_REAL_END(altivec_assist, 0x1700, 0x100)
EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
- INT_HANDLER altivec_assist, 0x1700, virt=1
+ GEN_INT_ENTRY altivec_assist, virt=1
EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
-INT_KVM_HANDLER altivec_assist, 0x1700, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(altivec_assist_common)
+ GEN_COMMON altivec_assist
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_ALTIVEC
-EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception)
+ bl altivec_assist_exception
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
#else
-EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+
+ GEN_KVM altivec_assist
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_thermal)
+ IVEC=0x1800
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_thermal)
+
EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
- INT_HANDLER cbe_thermal, 0x1800, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_thermal, virt=0
EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
EXC_VIRT_NONE(0x5800, 0x100)
-INT_KVM_HANDLER cbe_thermal, 0x1800, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception)
+EXC_COMMON_BEGIN(cbe_thermal_common)
+ GEN_COMMON cbe_thermal
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_thermal_exception
+ b interrupt_return
+
+ GEN_KVM cbe_thermal
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1800, 0x100)
EXC_VIRT_NONE(0x5800, 0x100)
@@ -1945,14 +2830,11 @@
#ifdef CONFIG_PPC_WATCHDOG
-#define MASKED_DEC_HANDLER_LABEL 3f
-
-#define MASKED_DEC_HANDLER(_H) \
-3: /* soft-nmi */ \
- std r12,PACA_EXGEN+EX_R12(r13); \
- GET_SCRATCH0(r10); \
- std r10,PACA_EXGEN+EX_R13(r13); \
- INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1
+INT_DEFINE_BEGIN(soft_nmi)
+ IVEC=0x900
+ ISTACK=0
+ IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
+INT_DEFINE_END(soft_nmi)
/*
* Branch to soft_nmi_interrupt using the emergency stack. The emergency
@@ -1964,18 +2846,42 @@
* and run it entirely with interrupts hard disabled.
*/
EXC_COMMON_BEGIN(soft_nmi_common)
+ mfspr r11,SPRN_SRR0
mr r10,r1
ld r1,PACAEMERGSP(r13)
subi r1,r1,INT_FRAME_SIZE
- INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0
- bl save_nvgprs
+ __GEN_COMMON_BODY soft_nmi
+
+ /*
+ * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
+ * system_reset_common)
+ */
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ lbz r10,PACAIRQHAPPENED(r13)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+
addi r3,r1,STACK_FRAME_OVERHEAD
bl soft_nmi_interrupt
- b ret_from_except
-#else /* CONFIG_PPC_WATCHDOG */
-#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */
-#define MASKED_DEC_HANDLER(_H)
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+
+ /*
+ * Restore soft mask settings.
+ */
+ ld r10,RESULT(r1)
+ stb r10,PACAIRQHAPPENED(r13)
+ ld r10,SOFTE(r1)
+ stb r10,PACAIRQSOFTMASK(r13)
+
+ kuap_restore_amr r9, r10
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
+
#endif /* CONFIG_PPC_WATCHDOG */
/*
@@ -1988,13 +2894,12 @@
* - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
* This is called with r10 containing the value to OR to the paca field.
*/
-.macro MASKED_INTERRUPT hsrr
+.macro MASKED_INTERRUPT hsrr=0
.if \hsrr
masked_Hinterrupt:
.else
masked_interrupt:
.endif
- std r11,PACA_EXGEN+EX_R11(r13)
lbz r11,PACAIRQHAPPENED(r13)
or r11,r11,r10
stb r11,PACAIRQHAPPENED(r13)
@@ -2003,34 +2908,38 @@
lis r10,0x7fff
ori r10,r10,0xffff
mtspr SPRN_DEC,r10
- b MASKED_DEC_HANDLER_LABEL
+#ifdef CONFIG_PPC_WATCHDOG
+ b soft_nmi_common
+#else
+ b 2f
+#endif
1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK
beq 2f
+ xori r12,r12,MSR_EE /* clear MSR_EE */
.if \hsrr
- mfspr r10,SPRN_HSRR1
- xori r10,r10,MSR_EE /* clear MSR_EE */
- mtspr SPRN_HSRR1,r10
+ mtspr SPRN_HSRR1,r12
.else
- mfspr r10,SPRN_SRR1
- xori r10,r10,MSR_EE /* clear MSR_EE */
- mtspr SPRN_SRR1,r10
+ mtspr SPRN_SRR1,r12
.endif
ori r11,r11,PACA_IRQ_HARD_DIS
stb r11,PACAIRQHAPPENED(r13)
2: /* done */
+ ld r10,PACA_EXGEN+EX_CTR(r13)
+ mtctr r10
mtcrf 0x80,r9
std r1,PACAR1(r13)
ld r9,PACA_EXGEN+EX_R9(r13)
ld r10,PACA_EXGEN+EX_R10(r13)
ld r11,PACA_EXGEN+EX_R11(r13)
- /* returns to kernel where r13 must be set up, so don't restore it */
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ /* May return to masked low address where r13 is not set up */
.if \hsrr
HRFI_TO_KERNEL
.else
RFI_TO_KERNEL
.endif
b .
- MASKED_DEC_HANDLER(\hsrr\())
.endm
TRAMP_REAL_BEGIN(stf_barrier_fallback)
@@ -2087,6 +2996,25 @@
ld r11,PACA_EXRFI+EX_R11(r13)
blr
+/*
+ * The SCV entry flush happens with interrupts enabled, so it must disable
+ * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10
+ * (containing LR) does not need to be preserved here because scv entry
+ * puts 0 in the pt_regs, CTR can be clobbered for the same reason.
+ */
+TRAMP_REAL_BEGIN(scv_entry_flush_fallback)
+ li r10,0
+ mtmsrd r10,1
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ L1D_DISPLACEMENT_FLUSH
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ li r10,MSR_RI
+ mtmsrd r10,1
+ blr
+
TRAMP_REAL_BEGIN(rfi_flush_fallback)
SET_SCRATCH0(r13);
GET_PACA(r13);
@@ -2123,6 +3051,47 @@
GET_SCRATCH0(r13);
hrfid
+TRAMP_REAL_BEGIN(rfscv_flush_fallback)
+ /* system call volatile */
+ mr r7,r13
+ GET_PACA(r13);
+ mr r8,r1
+ ld r1,PACAKSAVE(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SIZE(r13)
+ srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+ mtctr r11
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+
+ /*
+ * The load adresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+1:
+ ld r11,(0x80 + 8)*0(r10)
+ ld r11,(0x80 + 8)*1(r10)
+ ld r11,(0x80 + 8)*2(r10)
+ ld r11,(0x80 + 8)*3(r10)
+ ld r11,(0x80 + 8)*4(r10)
+ ld r11,(0x80 + 8)*5(r10)
+ ld r11,(0x80 + 8)*6(r10)
+ ld r11,(0x80 + 8)*7(r10)
+ addi r10,r10,0x80*8
+ bdnz 1b
+
+ mtctr r9
+ li r9,0
+ li r10,0
+ li r11,0
+ mr r1,r8
+ mr r13,r7
+ RFSCV
+
USE_TEXT_SECTION()
_GLOBAL(do_uaccess_flush)
@@ -2136,17 +3105,12 @@
_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
EXPORT_SYMBOL(do_uaccess_flush)
-/*
- * Real mode exceptions actually use this too, but alternate
- * instruction code patches (which end up in the common .text area)
- * cannot reach these if they are put there.
- */
-USE_FIXED_SECTION(virt_trampolines)
- MASKED_INTERRUPT EXC_STD
- MASKED_INTERRUPT EXC_HV
+
+MASKED_INTERRUPT
+MASKED_INTERRUPT hsrr=1
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
+kvmppc_skip_interrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
@@ -2158,7 +3122,7 @@
RFI_TO_KERNEL
b .
-TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
+kvmppc_skip_Hinterrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
@@ -2171,16 +3135,6 @@
b .
#endif
-/*
- * Ensure that any handlers that get invoked from the exception prologs
- * above are below the first 64KB (0x10000) of the kernel image because
- * the prologs assemble the addresses of these handlers using the
- * LOAD_HANDLER macro, which uses an ori instruction.
- */
-
-/*** Common interrupt handlers ***/
-
-
/*
* Relocation-on interrupts: A subset of the interrupts can be delivered
* with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering
@@ -2202,6 +3156,10 @@
USE_FIXED_SECTION(virt_trampolines)
/*
+ * All code below __end_interrupts is treated as soft-masked. If
+ * any code runs here with MSR[EE]=1, it must then cope with pending
+ * soft interrupt being raised (i.e., by ensuring it is replayed).
+ *
* The __end_interrupts marker must be past the out-of-line (OOL)
* handlers, so that they are copied to real address 0x100 when running
* a relocatable kernel. This ensures they can be reached from the short
@@ -2214,11 +3172,20 @@
DEFINE_FIXED_SYMBOL(__end_interrupts)
#ifdef CONFIG_PPC_970_NAP
+ /*
+ * Called by exception entry code if _TLF_NAPPING was set, this clears
+ * the NAPPING flag, and redirects the exception exit to
+ * power4_fixup_nap_return.
+ */
+ .globl power4_fixup_nap
EXC_COMMON_BEGIN(power4_fixup_nap)
andc r9,r9,r10
std r9,TI_LOCAL_FLAGS(r11)
- ld r10,_LINK(r1) /* make idle task do the */
- std r10,_NIP(r1) /* equivalent of a blr */
+ LOAD_REG_ADDR(r10, power4_idle_nap_return)
+ std r10,_NIP(r1)
+ blr
+
+power4_idle_nap_return:
blr
#endif
@@ -2268,10 +3235,18 @@
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r5,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
+
+ /*
+ * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+ * don't call hash_page, just fail the fault. This is required to
+ * prevent re-entrancy problems in the hash code, namely perf
+ * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+ * hash fault. See the comment in hash_preload().
+ */
ld r11, PACA_THREAD_INFO(r13)
- lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
- andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
- bne 77f /* then don't call hash_page now */
+ lwz r0,TI_PREEMPT(r11)
+ andis. r0,r0,NMI_MASK@h
+ bne 77f
/*
* r3 contains the trap number
@@ -2285,7 +3260,7 @@
cmpdi r3,0 /* see if __hash_page succeeded */
/* Success */
- beq fast_exc_return_irq /* Return from exception on success */
+ beq interrupt_return /* Return from exception on success */
/* Error */
blt- 13f
@@ -2302,39 +3277,36 @@
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_page_fault
cmpdi r3,0
- beq+ ret_from_except_lite
- bl save_nvgprs
+ beq+ interrupt_return
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
bl bad_page_fault
- b ret_from_except
+ b interrupt_return
/* We have a data breakpoint exception - handle it */
handle_dabr_fault:
- bl save_nvgprs
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_break
/*
* do_break() may have changed the NV GPRS while handling a breakpoint.
- * If so, we need to restore them with their updated values. Don't use
- * ret_from_except_lite here.
+ * If so, we need to restore them with their updated values.
*/
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
#ifdef CONFIG_PPC_BOOK3S_64
/* We have a page fault that hash_page could handle but HV refused
* the PTE insertion
*/
-13: bl save_nvgprs
- mr r5,r3
+13: mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
bl low_hash_fault
- b ret_from_except
+ b interrupt_return
#endif
/*
@@ -2344,74 +3316,7 @@
* were soft-disabled. We want to invoke the exception handler for
* the access, or panic if there isn't a handler.
*/
-77: bl save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
+77: addi r3,r1,STACK_FRAME_OVERHEAD
li r5,SIGSEGV
bl bad_page_fault
- b ret_from_except
-
-/*
- * When doorbell is triggered from system reset wakeup, the message is
- * not cleared, so it would fire again when EE is enabled.
- *
- * When coming from local_irq_enable, there may be the same problem if
- * we were hard disabled.
- *
- * Execute msgclr to clear pending exceptions before handling it.
- */
-h_doorbell_common_msgclr:
- LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
- PPC_MSGCLR(3)
- b h_doorbell_common
-
-doorbell_super_common_msgclr:
- LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
- PPC_MSGCLRP(3)
- b doorbell_super_common
-
-/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
- * which kind of interrupt. MSR:EE is already off. We generate a
- * stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- *
- * Note that we don't specify LR as the NIP (return address) for
- * the interrupt because that would unbalance the return branch
- * predictor.
- */
-_GLOBAL(__replay_interrupt)
- /* We are going to jump to the exception common code which
- * will retrieve various register values from the PACA which
- * we don't give a damn about, so we don't bother storing them.
- */
- mfmsr r12
- LOAD_REG_ADDR(r11, replay_interrupt_return)
- mfcr r9
- ori r12,r12,MSR_EE
- cmpwi r3,0x900
- beq decrementer_common
- cmpwi r3,0x500
-BEGIN_FTR_SECTION
- beq h_virt_irq_common
-FTR_SECTION_ELSE
- beq hardware_interrupt_common
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
- cmpwi r3,0xf00
- beq performance_monitor_common
-BEGIN_FTR_SECTION
- cmpwi r3,0xa00
- beq h_doorbell_common_msgclr
- cmpwi r3,0xe60
- beq hmi_exception_common
-FTR_SECTION_ELSE
- cmpwi r3,0xa00
- beq doorbell_super_common_msgclr
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
-replay_interrupt_return:
- blr
-
-_ASM_NOKPROBE_SYMBOL(__replay_interrupt)
+ b interrupt_return
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 0455dc1..c3bb800 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -32,12 +32,25 @@
#include <asm/fadump-internal.h>
#include <asm/setup.h>
+/*
+ * The CPU who acquired the lock to trigger the fadump crash should
+ * wait for other CPUs to enter.
+ *
+ * The timeout is in milliseconds.
+ */
+#define CRASH_TIMEOUT 500
+
static struct fw_dump fw_dump;
static void __init fadump_reserve_crash_area(u64 base);
+struct kobject *fadump_kobj;
+
#ifndef CONFIG_PRESERVE_FA_DUMP
+
+static atomic_t cpus_in_fadump;
static DEFINE_MUTEX(fadump_mutex);
+
struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false };
#define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */
@@ -178,13 +191,13 @@
*/
static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
{
- struct memblock_region *reg;
+ phys_addr_t reg_start, reg_end;
bool ret = false;
- u64 start, end;
+ u64 i, start, end;
- for_each_memblock(memory, reg) {
- start = max_t(u64, d_start, reg->base);
- end = min_t(u64, d_end, (reg->base + reg->size));
+ for_each_mem_range(i, ®_start, ®_end) {
+ start = max_t(u64, d_start, reg_start);
+ end = min_t(u64, d_end, reg_end);
if (d_start < end) {
/* Memory hole from d_start to start */
if (start > d_start)
@@ -409,34 +422,34 @@
static int __init fadump_get_boot_mem_regions(void)
{
- unsigned long base, size, cur_size, hole_size, last_end;
+ unsigned long size, cur_size, hole_size, last_end;
unsigned long mem_size = fw_dump.boot_memory_size;
- struct memblock_region *reg;
+ phys_addr_t reg_start, reg_end;
int ret = 1;
+ u64 i;
fw_dump.boot_mem_regs_cnt = 0;
last_end = 0;
hole_size = 0;
cur_size = 0;
- for_each_memblock(memory, reg) {
- base = reg->base;
- size = reg->size;
- hole_size += (base - last_end);
+ for_each_mem_range(i, ®_start, ®_end) {
+ size = reg_end - reg_start;
+ hole_size += (reg_start - last_end);
if ((cur_size + size) >= mem_size) {
size = (mem_size - cur_size);
- ret = add_boot_mem_regions(base, size);
+ ret = add_boot_mem_regions(reg_start, size);
break;
}
mem_size -= size;
cur_size += size;
- ret = add_boot_mem_regions(base, size);
+ ret = add_boot_mem_regions(reg_start, size);
if (!ret)
break;
- last_end = base + size;
+ last_end = reg_end;
}
fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size);
@@ -666,8 +679,11 @@
void crash_fadump(struct pt_regs *regs, const char *str)
{
+ unsigned int msecs;
struct fadump_crash_info_header *fdh = NULL;
int old_cpu, this_cpu;
+ /* Do not include first CPU */
+ unsigned int ncpus = num_online_cpus() - 1;
if (!should_fadump_crash())
return;
@@ -683,6 +699,8 @@
old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu);
if (old_cpu != -1) {
+ atomic_inc(&cpus_in_fadump);
+
/*
* We can't loop here indefinitely. Wait as long as fadump
* is in force. If we race with fadump un-registration this
@@ -706,6 +724,16 @@
fdh->online_mask = *cpu_online_mask;
+ /*
+ * If we came in via system reset, wait a while for the secondary
+ * CPUs to enter.
+ */
+ if (TRAP(&(fdh->regs)) == 0x100) {
+ msecs = CRASH_TIMEOUT;
+ while ((atomic_read(&cpus_in_fadump) < ncpus) && (--msecs > 0))
+ mdelay(1);
+ }
+
fw_dump.ops->fadump_trigger(fdh, str);
}
@@ -726,10 +754,8 @@
void fadump_update_elfcore_header(char *bufp)
{
- struct elfhdr *elf;
struct elf_phdr *phdr;
- elf = (struct elfhdr *)bufp;
bufp += sizeof(struct elfhdr);
/* First note is a place holder for cpu notes info. */
@@ -957,9 +983,8 @@
*/
static int fadump_setup_crash_memory_ranges(void)
{
- struct memblock_region *reg;
- u64 start, end;
- int i, ret;
+ u64 i, start, end;
+ int ret;
pr_debug("Setup crash memory ranges.\n");
crash_mrange_info.mem_range_cnt = 0;
@@ -977,10 +1002,7 @@
return ret;
}
- for_each_memblock(memory, reg) {
- start = (u64)reg->base;
- end = start + (u64)reg->size;
-
+ for_each_mem_range(i, &start, &end) {
/*
* skip the memory chunk that is already added
* (0 through boot_memory_top).
@@ -1214,14 +1236,17 @@
*/
static void fadump_release_reserved_area(u64 start, u64 end)
{
+ unsigned long reg_spfn, reg_epfn;
u64 tstart, tend, spfn, epfn;
- struct memblock_region *reg;
+ int i;
spfn = PHYS_PFN(start);
epfn = PHYS_PFN(end);
- for_each_memblock(memory, reg) {
- tstart = max_t(u64, spfn, memblock_region_memory_base_pfn(reg));
- tend = min_t(u64, epfn, memblock_region_memory_end_pfn(reg));
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, ®_spfn, ®_epfn, NULL) {
+ tstart = max_t(u64, spfn, reg_spfn);
+ tend = min_t(u64, epfn, reg_epfn);
+
if (tstart < tend) {
fadump_free_reserved_memory(tstart, tend);
@@ -1394,9 +1419,9 @@
fw_dump.ops->fadump_init_mem_struct(&fw_dump);
}
-static ssize_t fadump_release_memory_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
+static ssize_t release_mem_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
int input = -1;
@@ -1421,23 +1446,40 @@
return count;
}
-static ssize_t fadump_enabled_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
+/* Release the reserved memory and disable the FADump */
+static void unregister_fadump(void)
+{
+ fadump_cleanup();
+ fadump_release_memory(fw_dump.reserve_dump_area_start,
+ fw_dump.reserve_dump_area_size);
+ fw_dump.fadump_enabled = 0;
+ kobject_put(fadump_kobj);
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
}
-static ssize_t fadump_register_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
+static ssize_t mem_reserved_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%ld\n", fw_dump.reserve_dump_area_size);
+}
+
+static ssize_t registered_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", fw_dump.dump_registered);
}
-static ssize_t fadump_register_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
+static ssize_t registered_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
int ret = 0;
int input = -1;
@@ -1489,45 +1531,82 @@
return 0;
}
-static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
- 0200, NULL,
- fadump_release_memory_store);
-static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
- 0444, fadump_enabled_show,
- NULL);
-static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
- 0644, fadump_register_show,
- fadump_register_store);
+static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
+static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
+static struct kobj_attribute register_attr = __ATTR_RW(registered);
+static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
+
+static struct attribute *fadump_attrs[] = {
+ &enable_attr.attr,
+ ®ister_attr.attr,
+ &mem_reserved_attr.attr,
+ NULL,
+};
+
+ATTRIBUTE_GROUPS(fadump);
DEFINE_SHOW_ATTRIBUTE(fadump_region);
static void fadump_init_files(void)
{
- struct dentry *debugfs_file;
int rc = 0;
- rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
- if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_enabled (%d)\n", rc);
+ fadump_kobj = kobject_create_and_add("fadump", kernel_kobj);
+ if (!fadump_kobj) {
+ pr_err("failed to create fadump kobject\n");
+ return;
+ }
- rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
- if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_registered (%d)\n", rc);
-
- debugfs_file = debugfs_create_file("fadump_region", 0444,
- powerpc_debugfs_root, NULL,
- &fadump_region_fops);
- if (!debugfs_file)
- printk(KERN_ERR "fadump: unable to create debugfs file"
- " fadump_region\n");
+ debugfs_create_file("fadump_region", 0444, powerpc_debugfs_root, NULL,
+ &fadump_region_fops);
if (fw_dump.dump_active) {
- rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+ rc = sysfs_create_file(fadump_kobj, &release_attr.attr);
if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_release_mem (%d)\n", rc);
+ pr_err("unable to create release_mem sysfs file (%d)\n",
+ rc);
+ }
+
+ rc = sysfs_create_groups(fadump_kobj, fadump_groups);
+ if (rc) {
+ pr_err("sysfs group creation failed (%d), unregistering FADump",
+ rc);
+ unregister_fadump();
+ return;
+ }
+
+ /*
+ * The FADump sysfs are moved from kernel_kobj to fadump_kobj need to
+ * create symlink at old location to maintain backward compatibility.
+ *
+ * - fadump_enabled -> fadump/enabled
+ * - fadump_registered -> fadump/registered
+ * - fadump_release_mem -> fadump/release_mem
+ */
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "enabled", "fadump_enabled");
+ if (rc) {
+ pr_err("unable to create fadump_enabled symlink (%d)", rc);
+ return;
+ }
+
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "registered",
+ "fadump_registered");
+ if (rc) {
+ pr_err("unable to create fadump_registered symlink (%d)", rc);
+ sysfs_remove_link(kernel_kobj, "fadump_enabled");
+ return;
+ }
+
+ if (fw_dump.dump_active) {
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj,
+ fadump_kobj,
+ "release_mem",
+ "fadump_release_mem");
+ if (rc)
+ pr_err("unable to create fadump_release_mem symlink (%d)",
+ rc);
}
return;
}
@@ -1537,16 +1616,15 @@
*/
int __init setup_fadump(void)
{
- if (!fw_dump.fadump_enabled)
+ if (!fw_dump.fadump_supported)
return 0;
- if (!fw_dump.fadump_supported) {
- printk(KERN_ERR "Firmware-assisted dump is not supported on"
- " this hardware\n");
- return 0;
- }
-
+ fadump_init_files();
fadump_show_config();
+
+ if (!fw_dump.fadump_enabled)
+ return 1;
+
/*
* If dump data is available then see if it is valid and prepare for
* saving it to the disk.
@@ -1563,7 +1641,13 @@
else if (fw_dump.reserve_dump_area_size)
fw_dump.ops->fadump_init_mem_struct(&fw_dump);
- fadump_init_files();
+ /*
+ * In case of panic, fadump is triggered via ppc_panic_event()
+ * panic notifier. Setting crash_kexec_post_notifiers to 'true'
+ * lets panic() function take crash friendly path before panic
+ * notifiers are invoked.
+ */
+ crash_kexec_post_notifiers = true;
return 1;
}
@@ -1605,12 +1689,10 @@
/* Preserve everything above the base address */
static void __init fadump_reserve_crash_area(u64 base)
{
- struct memblock_region *reg;
- u64 mstart, msize;
+ u64 i, mstart, mend, msize;
- for_each_memblock(memory, reg) {
- mstart = reg->base;
- msize = reg->size;
+ for_each_mem_range(i, &mstart, &mend) {
+ msize = mend - mstart;
if ((mstart + msize) < base)
continue;
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index cc4a5e3..20328f7 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -11,8 +11,31 @@
#include <linux/export.h>
#include <linux/cache.h>
+#include <linux/of.h>
#include <asm/firmware.h>
+#include <asm/kvm_guest.h>
+#ifdef CONFIG_PPC64
unsigned long powerpc_firmware_features __read_mostly;
EXPORT_SYMBOL_GPL(powerpc_firmware_features);
+#endif
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
+DEFINE_STATIC_KEY_FALSE(kvm_guest);
+int __init check_kvm_guest(void)
+{
+ struct device_node *hyper_node;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return 0;
+
+ if (of_device_is_compatible(hyper_node, "linux,kvm"))
+ static_branch_enable(&kvm_guest);
+
+ of_node_put(hyper_node);
+ return 0;
+}
+core_initcall(check_kvm_guest); // before kvm_guest_init()
+#endif
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 0bb991d..3ff9a8f 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -12,7 +12,6 @@
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
@@ -88,12 +87,14 @@
oris r5,r5,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- SYNC
MTMSRD(r5) /* enable use of fpu now */
isync
/* enable use of FP after return */
#ifdef CONFIG_PPC32
mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
+#ifdef CONFIG_VMAP_STACK
+ tovirt(r5, r5)
+#endif
lwz r4,THREAD_FPEXC_MODE(r5)
ori r9,r9,MSR_FP /* enable FP for current */
or r9,r9,r4
@@ -105,9 +106,7 @@
or r12,r12,r4
std r12,_MSR(r1)
#endif
- /* Don't care if r4 overflows, this is desired behaviour */
- lbz r4,THREAD_LOAD_FP(r5)
- addi r4,r4,1
+ li r4,1
stb r4,THREAD_LOAD_FP(r5)
addi r10,r5,THREAD_FPSTATE
lfd fr0,FPSTATE_FPSCR(r10)
@@ -116,6 +115,7 @@
/* restore registers and return */
/* we haven't used ctr or xer or lr */
blr
+_ASM_NOKPROBE_SYMBOL(load_up_fpu)
/*
* save_fpu(tsk)
@@ -133,18 +133,3 @@
mffs fr0
stfd fr0,FPSTATE_FPSCR(r6)
blr
-
-/*
- * These are used in the alignment trap handler when emulating
- * single-precision loads and stores.
- */
-
-_GLOBAL(cvt_fd)
- lfs 0,0(r3)
- stfd 0,0(r4)
- blr
-
-_GLOBAL(cvt_df)
- lfd 0,0(r3)
- stfs 0,0(r4)
- blr
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index ea06528..8bccce6 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -153,35 +153,24 @@
tlbivax 0,r9
TLBSYNC
-/*
- * The mapping only needs to be cache-coherent on SMP, except on
- * Freescale e500mc derivatives where it's also needed for coherent DMA.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
-
#if defined(ENTRY_MAPPING_BOOT_SETUP)
-/* 6. Setup KERNELBASE mapping in TLB1[0] */
+/* 6. Setup kernstart_virt_addr mapping in TLB1[0] */
lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
mtspr SPRN_MAS0,r6
lis r6,(MAS1_VALID|MAS1_IPROT)@h
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
mtspr SPRN_MAS1,r6
- lis r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@h
- ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@l
+ lis r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r6,r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r6,r6,r20
+ ori r6,r6,MAS2_M_IF_NEEDED@l
mtspr SPRN_MAS2,r6
mtspr SPRN_MAS3,r8
tlbwe
-/* 7. Jump to KERNELBASE mapping */
- lis r6,(KERNELBASE & ~0xfff)@h
- ori r6,r6,(KERNELBASE & ~0xfff)@l
- rlwinm r7,r25,0,0x03ffffff
- add r6,r7,r6
+/* 7. Jump to kernstart_virt_addr mapping */
+ mr r6,r20
#elif defined(ENTRY_MAPPING_KEXEC_SETUP)
/*
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 8abc778..abb057a 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -10,47 +10,112 @@
* We assume sprg3 has the physical address of the current
* task's thread_struct.
*/
-
-.macro EXCEPTION_PROLOG
- mtspr SPRN_SPRG_SCRATCH0,r10
- mtspr SPRN_SPRG_SCRATCH1,r11
- mfcr r10
+.macro EXCEPTION_PROLOG handle_dar_dsisr=0
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=\handle_dar_dsisr
EXCEPTION_PROLOG_1
- EXCEPTION_PROLOG_2
+ EXCEPTION_PROLOG_2 handle_dar_dsisr=\handle_dar_dsisr
.endm
-.macro EXCEPTION_PROLOG_1
- mfspr r11,SPRN_SRR1 /* check whether user or kernel */
- andi. r11,r11,MSR_PR
- tophys(r11,r1) /* use tophys(r1) if kernel */
+.macro EXCEPTION_PROLOG_0 handle_dar_dsisr=0
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
+#ifdef CONFIG_VMAP_STACK
+ mfspr r10, SPRN_SPRG_THREAD
+ .if \handle_dar_dsisr
+ mfspr r11, SPRN_DAR
+ stw r11, DAR(r10)
+ mfspr r11, SPRN_DSISR
+ stw r11, DSISR(r10)
+ .endif
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+#endif
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+#ifdef CONFIG_VMAP_STACK
+ stw r11, SRR1(r10)
+#endif
+ mfcr r10
+ andi. r11, r11, MSR_PR
+.endm
+
+.macro EXCEPTION_PROLOG_1 for_rtas=0
+#ifdef CONFIG_VMAP_STACK
+ mr r11, r1
+ subi r1, r1, INT_FRAME_SIZE /* use r1 if kernel */
+ beq 1f
+ mfspr r1,SPRN_SPRG_THREAD
+ lwz r1,TASK_STACK-THREAD(r1)
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+#else
+ subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */
beq 1f
mfspr r11,SPRN_SPRG_THREAD
lwz r11,TASK_STACK-THREAD(r11)
- addi r11,r11,THREAD_SIZE
- tophys(r11,r11)
-1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
+ addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+#endif
+1:
+ tophys_novmstack r11, r11
+#ifdef CONFIG_VMAP_STACK
+ mtcrf 0x3f, r1
+ bt 32 - THREAD_ALIGN_SHIFT, stack_overflow
+#endif
.endm
-.macro EXCEPTION_PROLOG_2
+.macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0
+#ifdef CONFIG_VMAP_STACK
+ mtcr r10
+ li r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+ mtmsr r10
+ isync
+#else
stw r10,_CCR(r11) /* save registers */
+#endif
+ mfspr r10, SPRN_SPRG_SCRATCH0
+#ifdef CONFIG_VMAP_STACK
+ stw r11,GPR1(r1)
+ stw r11,0(r1)
+ mr r11, r1
+#else
+ stw r1,GPR1(r11)
+ stw r1,0(r11)
+ tovirt(r1, r11) /* set new kernel sp */
+#endif
stw r12,GPR12(r11)
stw r9,GPR9(r11)
- mfspr r10,SPRN_SPRG_SCRATCH0
stw r10,GPR10(r11)
+#ifdef CONFIG_VMAP_STACK
+ mfcr r10
+ stw r10, _CCR(r11)
+#endif
mfspr r12,SPRN_SPRG_SCRATCH1
stw r12,GPR11(r11)
mflr r10
stw r10,_LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+ mfspr r12, SPRN_SPRG_THREAD
+ tovirt(r12, r12)
+ .if \handle_dar_dsisr
+ lwz r10, DAR(r12)
+ stw r10, _DAR(r11)
+ lwz r10, DSISR(r12)
+ stw r10, _DSISR(r11)
+ .endif
+ lwz r9, SRR1(r12)
+ andi. r10, r9, MSR_PR
+ lwz r12, SRR0(r12)
+#else
mfspr r12,SPRN_SRR0
mfspr r9,SPRN_SRR1
- stw r1,GPR1(r11)
- stw r1,0(r11)
- tovirt(r1,r11) /* set new kernel sp */
+#endif
#ifdef CONFIG_40x
rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
#else
+#ifdef CONFIG_VMAP_STACK
+ li r10, MSR_KERNEL & ~MSR_IR /* can take exceptions */
+#else
li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */
- MTMSRD(r10) /* (except for mach check in rtas) */
+#endif
+ mtmsr r10 /* (except for mach check in rtas) */
#endif
stw r0,GPR0(r11)
lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -62,25 +127,52 @@
.macro SYSCALL_ENTRY trapno
mfspr r12,SPRN_SPRG_THREAD
- mfcr r10
+ mfspr r9, SPRN_SRR1
+#ifdef CONFIG_VMAP_STACK
+ mfspr r11, SPRN_SRR0
+ mtctr r11
+ andi. r11, r9, MSR_PR
+ mr r11, r1
+ lwz r1,TASK_STACK-THREAD(r12)
+ beq- 99f
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+ li r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+ mtmsr r10
+ isync
+ tovirt(r12, r12)
+ stw r11,GPR1(r1)
+ stw r11,0(r1)
+ mr r11, r1
+#else
+ andi. r11, r9, MSR_PR
lwz r11,TASK_STACK-THREAD(r12)
- mflr r9
- addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE
- rlwinm r10,r10,0,4,2 /* Clear SO bit in CR */
- tophys(r11,r11)
- stw r10,_CCR(r11) /* save registers */
- mfspr r10,SPRN_SRR0
- stw r9,_LINK(r11)
- mfspr r9,SPRN_SRR1
+ beq- 99f
+ addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+ tophys(r11, r11)
stw r1,GPR1(r11)
stw r1,0(r11)
- tovirt(r1,r11) /* set new kernel sp */
+ tovirt(r1, r11) /* set new kernel sp */
+#endif
+ mflr r10
+ stw r10, _LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+ mfctr r10
+#else
+ mfspr r10,SPRN_SRR0
+#endif
stw r10,_NIP(r11)
+ mfcr r10
+ rlwinm r10,r10,0,4,2 /* Clear SO bit in CR */
+ stw r10,_CCR(r11) /* save registers */
#ifdef CONFIG_40x
rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
#else
+#ifdef CONFIG_VMAP_STACK
+ LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */
+#else
LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
- MTMSRD(r10) /* (except for mach check in rtas) */
+#endif
+ mtmsr r10 /* (except for mach check in rtas) */
#endif
lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
stw r2,GPR2(r11)
@@ -118,7 +210,7 @@
#endif
3:
- tovirt(r2, r2) /* set r2 to current */
+ tovirt_novmstack r2, r2 /* set r2 to current */
lis r11, transfer_to_syscall@h
ori r11, r11, transfer_to_syscall@l
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -137,8 +229,56 @@
#endif
mtspr SPRN_SRR1,r10
mtspr SPRN_SRR0,r11
- SYNC
RFI /* jump to handler, enable MMU */
+99: b ret_from_kernel_syscall
+.endm
+
+.macro save_dar_dsisr_on_stack reg1, reg2, sp
+#ifndef CONFIG_VMAP_STACK
+ mfspr \reg1, SPRN_DAR
+ mfspr \reg2, SPRN_DSISR
+ stw \reg1, _DAR(\sp)
+ stw \reg2, _DSISR(\sp)
+#endif
+.endm
+
+.macro get_and_save_dar_dsisr_on_stack reg1, reg2, sp
+#ifdef CONFIG_VMAP_STACK
+ lwz \reg1, _DAR(\sp)
+ lwz \reg2, _DSISR(\sp)
+#else
+ save_dar_dsisr_on_stack \reg1, \reg2, \sp
+#endif
+.endm
+
+.macro tovirt_vmstack dst, src
+#ifdef CONFIG_VMAP_STACK
+ tovirt(\dst, \src)
+#else
+ .ifnc \dst, \src
+ mr \dst, \src
+ .endif
+#endif
+.endm
+
+.macro tovirt_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+ tovirt(\dst, \src)
+#else
+ .ifnc \dst, \src
+ mr \dst, \src
+ .endif
+#endif
+.endm
+
+.macro tophys_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+ tophys(\dst, \src)
+#else
+ .ifnc \dst, \src
+ mr \dst, \src
+ .endif
+#endif
.endm
/*
@@ -187,4 +327,23 @@
EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
ret_from_except)
+.macro vmap_stack_overflow_exception
+#ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_SMP
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, TASK_CPU - THREAD(r1)
+ slwi r1, r1, 3
+ addis r1, r1, emergency_ctx-PAGE_OFFSET@ha
+#else
+ lis r1, emergency_ctx-PAGE_OFFSET@ha
+#endif
+ lwz r1, emergency_ctx-PAGE_OFFSET@l(r1)
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+ EXCEPTION_PROLOG_2
+ SAVE_NVGPRS(r11)
+ addi r3, r1, STACK_FRAME_OVERHEAD
+ EXC_XFER_STD(0, stack_overflow_exception)
+#endif
+.endm
+
#endif /* __HEAD_32_H__ */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 585ea19..aeb9bc9 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -26,17 +26,17 @@
*/
#include <linux/init.h>
+#include <linux/pgtable.h>
+#include <linux/sizes.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/export.h>
-#include <asm/asm-405.h>
#include "head_32.h"
@@ -73,7 +73,6 @@
lis r0,start_here@h
ori r0,r0,start_here@l
mtspr SPRN_SRR0,r0
- SYNC
rfi /* enables MMU */
b . /* prevent prefetch past rfi */
@@ -176,135 +175,16 @@
* 0x0300 - Data Storage Exception
* This happens for just a few reasons. U0 set (but we don't do that),
* or zone protection fault (user violation, write to protected page).
- * If this is just an update of modified status, we do that quickly
- * and exit. Otherwise, we call heavywight functions to do the work.
+ * The other Data TLB exceptions bail out to this point
+ * if they can't resolve the lightweight TLB fault.
*/
START_EXCEPTION(0x0300, DataStorage)
- mtspr SPRN_SPRG_SCRATCH0, r10 /* Save some working registers */
- mtspr SPRN_SPRG_SCRATCH1, r11
-#ifdef CONFIG_403GCX
- stw r12, 0(r0)
- stw r9, 4(r0)
- mfcr r11
- mfspr r12, SPRN_PID
- stw r11, 8(r0)
- stw r12, 12(r0)
-#else
- mtspr SPRN_SPRG_SCRATCH3, r12
- mtspr SPRN_SPRG_SCRATCH4, r9
- mfcr r11
- mfspr r12, SPRN_PID
- mtspr SPRN_SPRG_SCRATCH6, r11
- mtspr SPRN_SPRG_SCRATCH5, r12
-#endif
-
- /* First, check if it was a zone fault (which means a user
- * tried to access a kernel or read-protected page - always
- * a SEGV). All other faults here must be stores, so no
- * need to check ESR_DST as well. */
- mfspr r10, SPRN_ESR
- andis. r10, r10, ESR_DIZ@h
- bne 2f
-
- mfspr r10, SPRN_DEAR /* Get faulting address */
-
- /* If we are faulting a kernel address, we have to use the
- * kernel page tables.
- */
- lis r11, PAGE_OFFSET@h
- cmplw r10, r11
- blt+ 3f
- lis r11, swapper_pg_dir@h
- ori r11, r11, swapper_pg_dir@l
- li r9, 0
- mtspr SPRN_PID, r9 /* TLB will have 0 TID */
- b 4f
-
- /* Get the PGD for the current thread.
- */
-3:
- mfspr r11,SPRN_SPRG_THREAD
- lwz r11,PGDIR(r11)
-4:
- tophys(r11, r11)
- rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
- lwz r11, 0(r11) /* Get L1 entry */
- rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */
- beq 2f /* Bail if no table */
-
- rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
- lwz r11, 0(r12) /* Get Linux PTE */
-
- andi. r9, r11, _PAGE_RW /* Is it writeable? */
- beq 2f /* Bail if not */
-
- /* Update 'changed'.
- */
- ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
- stw r11, 0(r12) /* Update Linux page table */
-
- /* Most of the Linux PTE is ready to load into the TLB LO.
- * We set ZSEL, where only the LS-bit determines user access.
- * We set execute, because we don't have the granularity to
- * properly set this at the page level (Linux problem).
- * If shared is set, we cause a zero PID->TID load.
- * Many of these bits are software only. Bits we don't set
- * here we (properly should) assume have the appropriate value.
- */
- li r12, 0x0ce2
- andc r11, r11, r12 /* Make sure 20, 21 are zero */
-
- /* find the TLB index that caused the fault. It has to be here.
- */
- tlbsx r9, 0, r10
-
- tlbwe r11, r9, TLB_DATA /* Load TLB LO */
-
- /* Done...restore registers and get out of here.
- */
-#ifdef CONFIG_403GCX
- lwz r12, 12(r0)
- lwz r11, 8(r0)
- mtspr SPRN_PID, r12
- mtcr r11
- lwz r9, 4(r0)
- lwz r12, 0(r0)
-#else
- mfspr r12, SPRN_SPRG_SCRATCH5
- mfspr r11, SPRN_SPRG_SCRATCH6
- mtspr SPRN_PID, r12
- mtcr r11
- mfspr r9, SPRN_SPRG_SCRATCH4
- mfspr r12, SPRN_SPRG_SCRATCH3
-#endif
- mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r10, SPRN_SPRG_SCRATCH0
- PPC405_ERR77_SYNC
- rfi /* Should sync shadow TLBs */
- b . /* prevent prefetch past rfi */
-
-2:
- /* The bailout. Restore registers to pre-exception conditions
- * and call the heavyweights to help us out.
- */
-#ifdef CONFIG_403GCX
- lwz r12, 12(r0)
- lwz r11, 8(r0)
- mtspr SPRN_PID, r12
- mtcr r11
- lwz r9, 4(r0)
- lwz r12, 0(r0)
-#else
- mfspr r12, SPRN_SPRG_SCRATCH5
- mfspr r11, SPRN_SPRG_SCRATCH6
- mtspr SPRN_PID, r12
- mtcr r11
- mfspr r9, SPRN_SPRG_SCRATCH4
- mfspr r12, SPRN_SPRG_SCRATCH3
-#endif
- mfspr r11, SPRN_SPRG_SCRATCH1
- mfspr r10, SPRN_SPRG_SCRATCH0
- b DataAccess
+ EXCEPTION_PROLOG
+ mfspr r5, SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ stw r5, _ESR(r11)
+ mfspr r4, SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ stw r4, _DEAR(r11)
+ EXC_XFER_LITE(0x300, handle_page_fault)
/*
* 0x0400 - Instruction Storage Exception
@@ -313,6 +193,7 @@
START_EXCEPTION(0x0400, InstructionAccess)
EXCEPTION_PROLOG
mr r4,r12 /* Pass SRR0 as arg2 */
+ stw r4, _DEAR(r11)
li r5,0 /* Pass zero as arg3 */
EXC_XFER_LITE(0x400, handle_page_fault)
@@ -343,8 +224,9 @@
/* 0x0C00 - System Call Exception */
START_EXCEPTION(0x0C00, SystemCall)
SYSCALL_ENTRY 0xc00
+/* Trap_0D is commented out to get more space for system call exception */
- EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD)
+/* EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD) */
EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_STD)
EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_STD)
@@ -370,21 +252,11 @@
START_EXCEPTION(0x1100, DTLBMiss)
mtspr SPRN_SPRG_SCRATCH0, r10 /* Save some working registers */
mtspr SPRN_SPRG_SCRATCH1, r11
-#ifdef CONFIG_403GCX
- stw r12, 0(r0)
- stw r9, 4(r0)
- mfcr r11
- mfspr r12, SPRN_PID
- stw r11, 8(r0)
- stw r12, 12(r0)
-#else
mtspr SPRN_SPRG_SCRATCH3, r12
mtspr SPRN_SPRG_SCRATCH4, r9
- mfcr r11
- mfspr r12, SPRN_PID
- mtspr SPRN_SPRG_SCRATCH6, r11
- mtspr SPRN_SPRG_SCRATCH5, r12
-#endif
+ mfcr r12
+ mfspr r9, SPRN_PID
+ mtspr SPRN_SPRG_SCRATCH5, r9
mfspr r10, SPRN_DEAR /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -407,28 +279,30 @@
4:
tophys(r11, r11)
rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
- lwz r12, 0(r11) /* Get L1 entry */
- andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */
+ lwz r11, 0(r11) /* Get L1 entry */
+ andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
beq 2f /* Bail if no table */
- rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
- lwz r11, 0(r12) /* Get Linux PTE */
- andi. r9, r11, _PAGE_PRESENT
- beq 5f
+ rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r11) /* Get Linux PTE */
+ li r9, _PAGE_PRESENT | _PAGE_ACCESSED
+ andc. r9, r9, r11 /* Check permission */
+ bne 5f
- ori r11, r11, _PAGE_ACCESSED
- stw r11, 0(r12)
+ rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
+ and r9, r9, r11 /* hwwrite = dirty & rw */
+ rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
/* Create TLB tag. This is the faulting address plus a static
* set of bits. These are size, valid, E, U0.
*/
- li r12, 0x00c0
- rlwimi r10, r12, 0, 20, 31
+ li r9, 0x00c0
+ rlwimi r10, r9, 0, 20, 31
b finish_tlb_load
2: /* Check for possible large-page pmd entry */
- rlwinm. r9, r12, 2, 22, 24
+ rlwinm. r9, r11, 2, 22, 24
beq 5f
/* Create TLB tag. This is the faulting address, plus a static
@@ -436,7 +310,6 @@
*/
ori r9, r9, 0x40
rlwimi r10, r9, 0, 20, 31
- mr r11, r12
b finish_tlb_load
@@ -444,24 +317,14 @@
/* The bailout. Restore registers to pre-exception conditions
* and call the heavyweights to help us out.
*/
-#ifdef CONFIG_403GCX
- lwz r12, 12(r0)
- lwz r11, 8(r0)
- mtspr SPRN_PID, r12
- mtcr r11
- lwz r9, 4(r0)
- lwz r12, 0(r0)
-#else
- mfspr r12, SPRN_SPRG_SCRATCH5
- mfspr r11, SPRN_SPRG_SCRATCH6
- mtspr SPRN_PID, r12
- mtcr r11
+ mfspr r9, SPRN_SPRG_SCRATCH5
+ mtspr SPRN_PID, r9
+ mtcr r12
mfspr r9, SPRN_SPRG_SCRATCH4
mfspr r12, SPRN_SPRG_SCRATCH3
-#endif
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r10, SPRN_SPRG_SCRATCH0
- b DataAccess
+ b DataStorage
/* 0x1200 - Instruction TLB Miss Exception
* Nearly the same as above, except we get our information from different
@@ -470,21 +333,11 @@
START_EXCEPTION(0x1200, ITLBMiss)
mtspr SPRN_SPRG_SCRATCH0, r10 /* Save some working registers */
mtspr SPRN_SPRG_SCRATCH1, r11
-#ifdef CONFIG_403GCX
- stw r12, 0(r0)
- stw r9, 4(r0)
- mfcr r11
- mfspr r12, SPRN_PID
- stw r11, 8(r0)
- stw r12, 12(r0)
-#else
mtspr SPRN_SPRG_SCRATCH3, r12
mtspr SPRN_SPRG_SCRATCH4, r9
- mfcr r11
- mfspr r12, SPRN_PID
- mtspr SPRN_SPRG_SCRATCH6, r11
- mtspr SPRN_SPRG_SCRATCH5, r12
-#endif
+ mfcr r12
+ mfspr r9, SPRN_PID
+ mtspr SPRN_SPRG_SCRATCH5, r9
mfspr r10, SPRN_SRR0 /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -507,28 +360,30 @@
4:
tophys(r11, r11)
rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
- lwz r12, 0(r11) /* Get L1 entry */
- andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */
+ lwz r11, 0(r11) /* Get L1 entry */
+ andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
beq 2f /* Bail if no table */
- rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
- lwz r11, 0(r12) /* Get Linux PTE */
- andi. r9, r11, _PAGE_PRESENT
- beq 5f
+ rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r11) /* Get Linux PTE */
+ li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+ andc. r9, r9, r11 /* Check permission */
+ bne 5f
- ori r11, r11, _PAGE_ACCESSED
- stw r11, 0(r12)
+ rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
+ and r9, r9, r11 /* hwwrite = dirty & rw */
+ rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
/* Create TLB tag. This is the faulting address plus a static
* set of bits. These are size, valid, E, U0.
*/
- li r12, 0x00c0
- rlwimi r10, r12, 0, 20, 31
+ li r9, 0x00c0
+ rlwimi r10, r9, 0, 20, 31
b finish_tlb_load
2: /* Check for possible large-page pmd entry */
- rlwinm. r9, r12, 2, 22, 24
+ rlwinm. r9, r11, 2, 22, 24
beq 5f
/* Create TLB tag. This is the faulting address, plus a static
@@ -536,7 +391,6 @@
*/
ori r9, r9, 0x40
rlwimi r10, r9, 0, 20, 31
- mr r11, r12
b finish_tlb_load
@@ -544,21 +398,11 @@
/* The bailout. Restore registers to pre-exception conditions
* and call the heavyweights to help us out.
*/
-#ifdef CONFIG_403GCX
- lwz r12, 12(r0)
- lwz r11, 8(r0)
- mtspr SPRN_PID, r12
- mtcr r11
- lwz r9, 4(r0)
- lwz r12, 0(r0)
-#else
- mfspr r12, SPRN_SPRG_SCRATCH5
- mfspr r11, SPRN_SPRG_SCRATCH6
- mtspr SPRN_PID, r12
- mtcr r11
+ mfspr r9, SPRN_SPRG_SCRATCH5
+ mtspr SPRN_PID, r9
+ mtcr r12
mfspr r9, SPRN_SPRG_SCRATCH4
mfspr r12, SPRN_SPRG_SCRATCH3
-#endif
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r10, SPRN_SPRG_SCRATCH0
b InstructionAccess
@@ -567,13 +411,7 @@
EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_STD)
EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
-#ifdef CONFIG_IBM405_ERR51
- /* 405GP errata 51 */
- START_EXCEPTION(0x1700, Trap_17)
- b DTLBMiss
-#else
EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
-#endif
EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_STD)
@@ -634,7 +472,6 @@
lwz r12,GPR12(r11)
lwz r10,crit_r10@l(0)
lwz r11,crit_r11@l(0)
- PPC405_ERR77_SYNC
rfci
b .
@@ -667,17 +504,6 @@
(MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)),
crit_transfer_to_handler, ret_from_crit_exc)
-/*
- * The other Data TLB exceptions bail out to this point
- * if they can't resolve the lightweight TLB fault.
- */
-DataAccess:
- EXCEPTION_PROLOG
- mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
- stw r5,_ESR(r11)
- mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
- EXC_XFER_LITE(0x300, handle_page_fault)
-
/* Other PowerPC processors, namely those derived from the 6xx-series
* have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
* However, for the 4xx-series processors these are neither defined nor
@@ -689,7 +515,7 @@
* miss get to this point to load the TLB.
* r10 - TLB_TAG value
* r11 - Linux PTE
- * r12, r9 - available to use
+ * r9 - available to use
* PID - loaded with proper value when we get here
* Upon exit, we reload everything and RFI.
* Actually, it will fit now, but oh well.....a common place
@@ -698,45 +524,32 @@
tlb_4xx_index:
.long 0
finish_tlb_load:
- /* load the next available TLB index.
- */
- lwz r9, tlb_4xx_index@l(0)
- addi r9, r9, 1
- andi. r9, r9, (PPC40X_TLB_SIZE-1)
- stw r9, tlb_4xx_index@l(0)
-
-6:
/*
* Clear out the software-only bits in the PTE to generate the
* TLB_DATA value. These are the bottom 2 bits of the RPM, the
* top 3 bits of the zone field, and M.
*/
- li r12, 0x0ce2
- andc r11, r11, r12
+ li r9, 0x0ce2
+ andc r11, r11, r9
+
+ /* load the next available TLB index. */
+ lwz r9, tlb_4xx_index@l(0)
+ addi r9, r9, 1
+ andi. r9, r9, PPC40X_TLB_SIZE - 1
+ stw r9, tlb_4xx_index@l(0)
tlbwe r11, r9, TLB_DATA /* Load TLB LO */
tlbwe r10, r9, TLB_TAG /* Load TLB HI */
/* Done...restore registers and get out of here.
*/
-#ifdef CONFIG_403GCX
- lwz r12, 12(r0)
- lwz r11, 8(r0)
- mtspr SPRN_PID, r12
- mtcr r11
- lwz r9, 4(r0)
- lwz r12, 0(r0)
-#else
- mfspr r12, SPRN_SPRG_SCRATCH5
- mfspr r11, SPRN_SPRG_SCRATCH6
- mtspr SPRN_PID, r12
- mtcr r11
+ mfspr r9, SPRN_SPRG_SCRATCH5
+ mtspr SPRN_PID, r9
+ mtcr r12
mfspr r9, SPRN_SPRG_SCRATCH4
mfspr r12, SPRN_SPRG_SCRATCH3
-#endif
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r10, SPRN_SPRG_SCRATCH0
- PPC405_ERR77_SYNC
rfi /* Should sync shadow TLBs */
b . /* prevent prefetch past rfi */
@@ -799,7 +612,7 @@
ori r6, r6, swapper_pg_dir@l
lis r5, abatron_pteptrs@h
ori r5, r5, abatron_pteptrs@l
- stw r5, 0xf0(r0) /* Must match your Abatron config file */
+ stw r5, 0xf0(0) /* Must match your Abatron config file */
tophys(r5,r5)
stw r6, 0(r5)
@@ -814,7 +627,7 @@
b . /* prevent prefetch past rfi */
/* Set up the initial MMU state so we can do the first level of
- * kernel initialization. This maps the first 16 MBytes of memory 1:1
+ * kernel initialization. This maps the first 32 MBytes of memory 1:1
* virtual to physical and more importantly sets the cache mode.
*/
initial_mmu:
@@ -851,6 +664,12 @@
tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
+ li r0,62 /* TLB slot 62 */
+ addis r4,r4,SZ_16M@h
+ addis r3,r3,SZ_16M@h
+ tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
+ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
+
isync
/* Establish the exception vector base
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 51dd01a..8e36718 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -25,10 +25,10 @@
*/
#include <linux/init.h>
+#include <linux/pgtable.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 9019f13..2d6581d 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -300,9 +300,6 @@
rlwimi r3, r3, 30, 2, 30
mtspr SPRN_PIR, r3
1:
-#endif
-
-_GLOBAL(generic_secondary_thread_init)
mr r24,r3
/* turn on 64-bit mode */
@@ -312,13 +309,13 @@
bl relative_toc
tovirt(r2,r2)
-#ifdef CONFIG_PPC_BOOK3E
/* Book3E initialization */
mr r3,r24
bl book3e_secondary_thread_init
-#endif
b generic_secondary_common_init
+#endif /* CONFIG_PPC_BOOK3E */
+
/*
* On pSeries and most other platforms, secondary processors spin
* in the following code.
@@ -537,6 +534,7 @@
b __after_prom_start
#endif /* CONFIG_PPC_BOOK3E */
+__REF
__boot_from_prom:
#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
/* Save parameters */
@@ -574,6 +572,7 @@
/* We never return. We also hit that trap if trying to boot
* from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
trap
+ .previous
__after_prom_start:
#ifdef CONFIG_RELOCATABLE
@@ -970,7 +969,6 @@
RFI
b . /* prevent speculative execution */
- .previous
/* This is where all platforms converge execution */
start_here_common:
@@ -994,6 +992,7 @@
/* Not reached */
0: trap
EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+ .previous
/*
* We put a few things here that have to be page-aligned.
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 6f3e417..a61b4ff 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -16,11 +16,12 @@
#include <linux/init.h>
#include <linux/magic.h>
+#include <linux/pgtable.h>
+#include <linux/sizes.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/cache.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
@@ -31,10 +32,15 @@
#include "head_32.h"
+.macro compare_to_kernel_boundary scratch, addr
#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
/* By simply checking Address >= 0x80000000, we know if its a kernel address */
-#define SIMPLE_KERNEL_ADDRESS 1
+ not. \scratch, \addr
+#else
+ rlwinm \scratch, \addr, 16, 0xfff8
+ cmpli cr0, \scratch, PAGE_OFFSET@h
#endif
+.endm
/*
* We need an ITLB miss handler for kernel addresses if:
@@ -127,56 +133,36 @@
/* Machine check */
. = 0x200
MachineCheck:
- EXCEPTION_PROLOG
- mfspr r4,SPRN_DAR
- stw r4,_DAR(r11)
- li r5,RPN_PATTERN
- mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */
- mfspr r5,SPRN_DSISR
- stw r5,_DSISR(r11)
+ EXCEPTION_PROLOG handle_dar_dsisr=1
+ save_dar_dsisr_on_stack r4, r5, r11
+ li r6, RPN_PATTERN
+ mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */
addi r3,r1,STACK_FRAME_OVERHEAD
EXC_XFER_STD(0x200, machine_check_exception)
-/* Data access exception.
- * This is "never generated" by the MPC8xx.
- */
- . = 0x300
-DataAccess:
-
-/* Instruction access exception.
- * This is "never generated" by the MPC8xx.
- */
- . = 0x400
-InstructionAccess:
-
/* External interrupt */
EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
/* Alignment exception */
. = 0x600
Alignment:
- EXCEPTION_PROLOG
- mfspr r4,SPRN_DAR
- stw r4,_DAR(r11)
- li r5,RPN_PATTERN
- mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */
- mfspr r5,SPRN_DSISR
- stw r5,_DSISR(r11)
+ EXCEPTION_PROLOG handle_dar_dsisr=1
+ save_dar_dsisr_on_stack r4, r5, r11
+ li r6, RPN_PATTERN
+ mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */
addi r3,r1,STACK_FRAME_OVERHEAD
- EXC_XFER_STD(0x600, alignment_exception)
+ b .Lalignment_exception_ool
/* Program check exception */
EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
-/* No FPU on MPC8xx. This exception is not supposed to happen.
-*/
- EXCEPTION(0x800, FPUnavailable, unknown_exception, EXC_XFER_STD)
-
/* Decrementer */
EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
- EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD)
+ /* With VMAP_STACK there's not enough room for this at 0x600 */
+ . = 0xa00
+.Lalignment_exception_ool:
+ EXC_XFER_STD(0x600, alignment_exception)
/* System call */
. = 0xc00
@@ -185,25 +171,12 @@
/* Single step - not used on 601 */
EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
- EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_STD)
/* On the MPC8xx, this is a software emulation interrupt. It occurs
* for all unimplemented and illegal instructions.
*/
EXCEPTION(0x1000, SoftEmu, emulation_assist_interrupt, EXC_XFER_STD)
-/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
-#ifdef CONFIG_PERF_EVENTS
- patch_site 0f, patch__dtlbmiss_perf
-0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
- addi r10, r10, 1
- stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
- mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
- rfi
-#endif
-
. = 0x1100
/*
* For the MPC8xx, this is a software tablewalk to load the instruction
@@ -237,48 +210,25 @@
mfspr r10, SPRN_SRR0 /* Get effective address of fault */
INVALIDATE_ADJACENT_PAGES_CPU15(r10)
mtspr SPRN_MD_EPN, r10
- /* Only modules will cause ITLB Misses as we always
- * pin the first 8MB of kernel memory */
#ifdef ITLB_MISS_KERNEL
mfcr r11
-#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
- cmpi cr0, r10, 0 /* Address >= 0x80000000 */
-#else
- rlwinm r10, r10, 16, 0xfff8
- cmpli cr0, r10, PAGE_OFFSET@h
-#ifndef CONFIG_PIN_TLB_TEXT
- /* It is assumed that kernel code fits into the first 32M */
-0: cmpli cr7, r10, (PAGE_OFFSET + 0x2000000)@h
- patch_site 0b, patch__itlbmiss_linmem_top
-#endif
-#endif
+ compare_to_kernel_boundary r10, r10
#endif
mfspr r10, SPRN_M_TWB /* Get level 1 table */
#ifdef ITLB_MISS_KERNEL
-#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
- bge+ 3f
-#else
blt+ 3f
-#endif
-#ifndef CONFIG_PIN_TLB_TEXT
- blt cr7, ITLBMissLinear
-#endif
rlwinm r10, r10, 0, 20, 31
oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
-#endif
- lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
- mtspr SPRN_MI_TWC, r10 /* Set segment attributes */
-
- mtspr SPRN_MD_TWC, r10
- mfspr r10, SPRN_MD_TWC
- lwz r10, 0(r10) /* Get the pte */
-#ifdef ITLB_MISS_KERNEL
mtcr r11
#endif
- rlwinm r11, r10, 32-7, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
+ mtspr SPRN_MD_TWC, r11
+ mfspr r10, SPRN_MD_TWC
+ lwz r10, 0(r10) /* Get the pte */
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
+ mtspr SPRN_MI_TWC, r11
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 20 and 23 must be clear.
* Software indicator bits 22, 24, 25, 26, and 27 must be
@@ -306,58 +256,19 @@
rfi
#endif
-#ifndef CONFIG_PIN_TLB_TEXT
-ITLBMissLinear:
- mtcr r11
-#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23
- patch_site 0f, patch__itlbmiss_linmem_top8
-
- mfspr r10, SPRN_SRR0
-0: subis r11, r10, (PAGE_OFFSET - 0x80000000)@ha
- rlwinm r11, r11, 4, MI_PS8MEG ^ MI_PS512K
- ori r11, r11, MI_PS512K | MI_SVALID
- rlwinm r10, r10, 0, 0x0ff80000 /* 8xx supports max 256Mb RAM */
-#else
- /* Set 8M byte page and mark it valid */
- li r11, MI_PS8MEG | MI_SVALID
- rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
-#endif
- mtspr SPRN_MI_TWC, r11
- ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
- _PAGE_PRESENT
- mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
-
-0: mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
- rfi
- patch_site 0b, patch__itlbmiss_exit_2
-#endif
-
. = 0x1200
DataStoreTLBMiss:
- mtspr SPRN_SPRG_SCRATCH0, r10
- mtspr SPRN_SPRG_SCRATCH1, r11
+ mtspr SPRN_DAR, r10
+ mtspr SPRN_M_TW, r11
mfcr r11
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
mfspr r10, SPRN_MD_EPN
- rlwinm r10, r10, 16, 0xfff8
- cmpli cr0, r10, PAGE_OFFSET@h
-#ifndef CONFIG_PIN_TLB_IMMR
- cmpli cr6, r10, VIRT_IMMR_BASE@h
-#endif
-0: cmpli cr7, r10, (PAGE_OFFSET + 0x2000000)@h
- patch_site 0b, patch__dtlbmiss_linmem_top
-
+ compare_to_kernel_boundary r10, r10
mfspr r10, SPRN_M_TWB /* Get level 1 table */
blt+ 3f
-#ifndef CONFIG_PIN_TLB_IMMR
-0: beq- cr6, DTLBMissIMMR
- patch_site 0b, patch__dtlbmiss_immr_jmp
-#endif
- blt cr7, DTLBMissLinear
rlwinm r10, r10, 0, 20, 31
oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
@@ -368,27 +279,16 @@
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
- /* Insert the Guarded flag into the TWC from the Linux PTE.
+ /* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
* It is bit 27 of both the Linux PTE and the TWC (at least
* I got that right :-). It will be better when we can put
* this into the Linux pgd/pmd and load it in the operation
* above.
*/
- rlwimi r11, r10, 0, _PAGE_GUARDED
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MD_TWC, r11
- /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
- * We also need to know if the insn is a load/store, so:
- * Clear _PAGE_PRESENT and load that which will
- * trap into DTLB Error with store bit set accordinly.
- */
- /* PRESENT=0x1, ACCESSED=0x20
- * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
- * r10 = (r10 & ~PRESENT) | r11;
- */
- rlwinm r11, r10, 32-7, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 24, 25, 26, and 27 must be
* set. All other Linux PTE bits control the behavior
@@ -399,68 +299,23 @@
mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
/* Restore registers */
- mtspr SPRN_DAR, r11 /* Tag DAR */
-0: mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
+0: mfspr r10, SPRN_DAR
+ mtspr SPRN_DAR, r11 /* Tag DAR */
+ mfspr r11, SPRN_M_TW
rfi
patch_site 0b, patch__dtlbmiss_exit_1
-DTLBMissIMMR:
- mtcr r11
- /* Set 512k byte guarded page and mark it valid */
- li r10, MD_PS512K | MD_GUARDED | MD_SVALID
- mtspr SPRN_MD_TWC, r10
- mfspr r10, SPRN_IMMR /* Get current IMMR */
- rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */
- ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
- _PAGE_PRESENT | _PAGE_NO_CACHE
- mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
-
- li r11, RPN_PATTERN
+#ifdef CONFIG_PERF_EVENTS
+ patch_site 0f, patch__dtlbmiss_perf
+0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ addi r10, r10, 1
+ stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ mfspr r10, SPRN_DAR
mtspr SPRN_DAR, r11 /* Tag DAR */
-
-0: mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r11, SPRN_M_TW
rfi
- patch_site 0b, patch__dtlbmiss_exit_2
-
-DTLBMissLinear:
- mtcr r11
- rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
-#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_DATA_SHIFT < 23
- patch_site 0f, patch__dtlbmiss_romem_top8
-
-0: subis r11, r10, (PAGE_OFFSET - 0x80000000)@ha
- rlwinm r11, r11, 0, 0xff800000
- neg r10, r11
- or r11, r11, r10
- rlwinm r11, r11, 4, MI_PS8MEG ^ MI_PS512K
- ori r11, r11, MI_PS512K | MI_SVALID
- mfspr r10, SPRN_MD_EPN
- rlwinm r10, r10, 0, 0x0ff80000 /* 8xx supports max 256Mb RAM */
-#else
- /* Set 8M byte page and mark it valid */
- li r11, MD_PS8MEG | MD_SVALID
#endif
- mtspr SPRN_MD_TWC, r11
-#ifdef CONFIG_STRICT_KERNEL_RWX
- patch_site 0f, patch__dtlbmiss_romem_top
-
-0: subis r11, r10, 0
- rlwimi r10, r11, 11, _PAGE_RO
-#endif
- ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
- _PAGE_PRESENT
- mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
-
- li r11, RPN_PATTERN
- mtspr SPRN_DAR, r11 /* Tag DAR */
-
-0: mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
- rfi
- patch_site 0b, patch__dtlbmiss_exit_3
/* This is an instruction TLB error on the MPC8xx. This could be due
* to many reasons, such as executing guarded memory or illegal instruction
@@ -476,6 +331,7 @@
tlbie r4
/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
.Litlbie:
+ stw r4, _DAR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* This is the data TLB error on the MPC8xx. This could be due to
@@ -484,58 +340,57 @@
*/
. = 0x1400
DataTLBError:
- mtspr SPRN_SPRG_SCRATCH0, r10
- mtspr SPRN_SPRG_SCRATCH1, r11
- mfcr r10
-
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=1
mfspr r11, SPRN_DAR
- cmpwi cr0, r11, RPN_PATTERN
- beq- FixupDAR /* must be a buggy dcbX, icbi insn. */
+ cmpwi cr1, r11, RPN_PATTERN
+ beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */
DARFixed:/* Return from dcbx instruction bug workaround */
+#ifdef CONFIG_VMAP_STACK
+ li r11, RPN_PATTERN
+ mtspr SPRN_DAR, r11 /* Tag DAR, to be used in DTLB Error */
+#endif
EXCEPTION_PROLOG_1
- EXCEPTION_PROLOG_2
- mfspr r5,SPRN_DSISR
- stw r5,_DSISR(r11)
- mfspr r4,SPRN_DAR
+ EXCEPTION_PROLOG_2 handle_dar_dsisr=1
+ get_and_save_dar_dsisr_on_stack r4, r5, r11
andis. r10,r5,DSISR_NOHPTE@h
beq+ .Ldtlbie
tlbie r4
.Ldtlbie:
+#ifndef CONFIG_VMAP_STACK
li r10,RPN_PATTERN
mtspr SPRN_DAR,r10 /* Tag DAR, to be used in DTLB Error */
+#endif
/* 0x300 is DataAccess exception, needed by bad_page_fault() */
EXC_XFER_LITE(0x300, handle_page_fault)
- EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD)
- EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD)
+stack_overflow:
+ vmap_stack_overflow_exception
/* On the MPC8xx, these next four traps are used for development
* support of breakpoints and such. Someday I will get around to
* using them.
*/
- . = 0x1c00
-DataBreakpoint:
- mtspr SPRN_SPRG_SCRATCH0, r10
- mtspr SPRN_SPRG_SCRATCH1, r11
- mfcr r10
- mfspr r11, SPRN_SRR0
- cmplwi cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l
- cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l
- beq- cr0, 11f
- beq- cr7, 11f
+do_databreakpoint:
EXCEPTION_PROLOG_1
- EXCEPTION_PROLOG_2
+ EXCEPTION_PROLOG_2 handle_dar_dsisr=1
addi r3,r1,STACK_FRAME_OVERHEAD
mfspr r4,SPRN_BAR
stw r4,_DAR(r11)
+#ifdef CONFIG_VMAP_STACK
+ lwz r5,_DSISR(r11)
+#else
mfspr r5,SPRN_DSISR
+#endif
EXC_XFER_STD(0x1c00, do_break)
-11:
+
+ . = 0x1c00
+DataBreakpoint:
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+ mfspr r11, SPRN_SRR0
+ cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l
+ cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l
+ cror 4*cr1+eq, 4*cr1+eq, 4*cr7+eq
+ bne cr1, do_databreakpoint
mtcr r10
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
@@ -571,28 +426,22 @@
mfspr r10, SPRN_SRR0
mtspr SPRN_MD_EPN, r10
rlwinm r11, r10, 16, 0xfff8
- cmpli cr0, r11, PAGE_OFFSET@h
+ cmpli cr1, r11, PAGE_OFFSET@h
mfspr r11, SPRN_M_TWB /* Get level 1 table */
- blt+ 3f
- rlwinm r11, r10, 16, 0xfff8
-
-0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h
- patch_site 0b, patch__fixupdar_linmem_top
+ blt+ cr1, 3f
/* create physical page address from effective address */
tophys(r11, r10)
- blt- cr7, 201f
mfspr r11, SPRN_M_TWB /* Get level 1 table */
rlwinm r11, r11, 0, 20, 31
oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
mtspr SPRN_MD_TWC, r11
- mtcr r11
+ mtcrf 0x01, r11
mfspr r11, SPRN_MD_TWC
lwz r11, 0(r11) /* Get the pte */
bt 28,200f /* bit 28 = Large page (8M) */
- bt 29,202f /* bit 29 = Large page (8M or 512K) */
/* concat physical page address(r11) and page offset(r10) */
rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31
201: lwz r11,0(r11)
@@ -601,16 +450,16 @@
* no need to include them here */
xoris r10, r11, 0x7c00 /* check if major OP code is 31 */
rlwinm r10, r10, 0, 21, 5
- cmpwi cr0, r10, 2028 /* Is dcbz? */
- beq+ 142f
- cmpwi cr0, r10, 940 /* Is dcbi? */
- beq+ 142f
- cmpwi cr0, r10, 108 /* Is dcbst? */
- beq+ 144f /* Fix up store bit! */
- cmpwi cr0, r10, 172 /* Is dcbf? */
- beq+ 142f
- cmpwi cr0, r10, 1964 /* Is icbi? */
- beq+ 142f
+ cmpwi cr1, r10, 2028 /* Is dcbz? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 940 /* Is dcbi? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 108 /* Is dcbst? */
+ beq+ cr1, 144f /* Fix up store bit! */
+ cmpwi cr1, r10, 172 /* Is dcbf? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 1964 /* Is icbi? */
+ beq+ cr1, 142f
141: mfspr r10,SPRN_M_TW
b DARFixed /* Nope, go back to normal TLB processing */
@@ -619,11 +468,6 @@
rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
b 201b
-202:
- /* concat physical page address(r11) and page offset(r10) */
- rlwimi r11, r10, 0, 32 - PAGE_SHIFT_512K, 31
- b 201b
-
144: mfspr r10, SPRN_DSISR
rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */
mtspr SPRN_DSISR, r10
@@ -669,8 +513,9 @@
add r10, r10, r30 ;b 151f
add r10, r10, r31
151:
- rlwinm. r11,r11,19,24,28 /* offset into jump table for reg RA */
- beq 152f /* if reg RA is zero, don't add it */
+ rlwinm r11,r11,19,24,28 /* offset into jump table for reg RA */
+ cmpwi cr1, r11, 0
+ beq cr1, 152f /* if reg RA is zero, don't add it */
addi r11, r11, 150b@l /* add start of table */
mtctr r11 /* load ctr with jump address */
rlwinm r11,r11,0,16,10 /* make sure we don't execute this more than once */
@@ -678,7 +523,14 @@
152:
mfdar r11
mtctr r11 /* restore ctr reg from DAR */
+#ifdef CONFIG_VMAP_STACK
+ mfspr r11, SPRN_SPRG_THREAD
+ stw r10, DAR(r11)
+ mfspr r10, SPRN_DSISR
+ stw r10, DSISR(r11)
+#else
mtdar r10 /* save fault EA to DAR */
+#endif
mfspr r10,SPRN_M_TW
b DARFixed /* Go back to normal TLB handling */
@@ -750,6 +602,31 @@
rfi
/* Load up the kernel context */
2:
+#ifdef CONFIG_PIN_TLB_IMMR
+ lis r0, MD_TWAM@h
+ oris r0, r0, 0x1f00
+ mtspr SPRN_MD_CTR, r0
+ LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
+ tlbie r0
+ mtspr SPRN_MD_EPN, r0
+ LOAD_REG_IMMEDIATE(r0, MD_SVALID | MD_PS512K | MD_GUARDED)
+ mtspr SPRN_MD_TWC, r0
+ mfspr r0, SPRN_IMMR
+ rlwinm r0, r0, 0, 0xfff80000
+ ori r0, r0, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
+ _PAGE_NO_CACHE | _PAGE_PRESENT
+ mtspr SPRN_MD_RPN, r0
+ lis r0, (MD_TWAM | MD_RSV4I)@h
+ mtspr SPRN_MD_CTR, r0
+#endif
+#ifndef CONFIG_PIN_TLB_TEXT
+ li r0, 0
+ mtspr SPRN_MI_CTR, r0
+#endif
+#if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR)
+ lis r0, MD_TWAM@h
+ mtspr SPRN_MD_CTR, r0
+#endif
tlbia /* Clear all TLB entries */
sync /* wait for tlbia/tlbie to finish */
@@ -782,17 +659,10 @@
initial_mmu:
li r8, 0
mtspr SPRN_MI_CTR, r8 /* remove PINNED ITLB entries */
- lis r10, MD_RESETVAL@h
-#ifndef CONFIG_8xx_COPYBACK
- oris r10, r10, MD_WTDEF@h
-#endif
+ lis r10, MD_TWAM@h
mtspr SPRN_MD_CTR, r10 /* remove PINNED DTLB entries */
tlbia /* Invalidate all TLB entries */
-#ifdef CONFIG_PIN_TLB_DATA
- oris r10, r10, MD_RSV4I@h
- mtspr SPRN_MD_CTR, r10 /* Set data TLB control */
-#endif
lis r8, MI_APG_INIT@h /* Set protection modes */
ori r8, r8, MI_APG_INIT@l
@@ -801,55 +671,32 @@
ori r8, r8, MD_APG_INIT@l
mtspr SPRN_MD_AP, r8
- /* Map a 512k page for the IMMR to get the processor
- * internal registers (among other things).
- */
-#ifdef CONFIG_PIN_TLB_IMMR
- oris r10, r10, MD_RSV4I@h
- ori r10, r10, 0x1c00
- mtspr SPRN_MD_CTR, r10
-
- mfspr r9, 638 /* Get current IMMR */
- andis. r9, r9, 0xfff8 /* Get 512 kbytes boundary */
-
- lis r8, VIRT_IMMR_BASE@h /* Create vaddr for TLB */
- ori r8, r8, MD_EVALID /* Mark it valid */
- mtspr SPRN_MD_EPN, r8
- li r8, MD_PS512K | MD_GUARDED /* Set 512k byte page */
- ori r8, r8, MD_SVALID /* Make it valid */
- mtspr SPRN_MD_TWC, r8
- mr r8, r9 /* Create paddr for TLB */
- ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */
- mtspr SPRN_MD_RPN, r8
-#endif
-
- /* Now map the lower RAM (up to 32 Mbytes) into the ITLB. */
-#ifdef CONFIG_PIN_TLB_TEXT
+ /* Map the lower RAM (up to 32 Mbytes) into the ITLB and DTLB */
lis r8, MI_RSV4I@h
ori r8, r8, 0x1c00
-#endif
+ oris r12, r10, MD_RSV4I@h
+ ori r12, r12, 0x1c00
li r9, 4 /* up to 4 pages of 8M */
mtctr r9
lis r9, KERNELBASE@h /* Create vaddr for TLB */
- li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */
+ li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
li r11, MI_BOOTINIT /* Create RPN for address 0 */
- lis r12, _einittext@h
- ori r12, r12, _einittext@l
1:
-#ifdef CONFIG_PIN_TLB_TEXT
mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */
addi r8, r8, 0x100
-#endif
-
ori r0, r9, MI_EVALID /* Mark it valid */
mtspr SPRN_MI_EPN, r0
mtspr SPRN_MI_TWC, r10
mtspr SPRN_MI_RPN, r11 /* Store TLB entry */
+ mtspr SPRN_MD_CTR, r12
+ addi r12, r12, 0x100
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r10
+ mtspr SPRN_MD_RPN, r11
addis r9, r9, 0x80
addis r11, r11, 0x80
- cmpl cr0, r9, r12
- bdnzf gt, 1b
+ bdnz 1b
/* Since the cache is enabled according to the information we
* just loaded into the TLB, invalidate and enable the caches here.
@@ -860,17 +707,7 @@
mtspr SPRN_DC_CST, r8
lis r8, IDC_ENABLE@h
mtspr SPRN_IC_CST, r8
-#ifdef CONFIG_8xx_COPYBACK
mtspr SPRN_DC_CST, r8
-#else
- /* For a debug option, I left this here to easily enable
- * the write through cache mode
- */
- lis r8, DC_SFWT@h
- mtspr SPRN_DC_CST, r8
- lis r8, IDC_ENABLE@h
- mtspr SPRN_DC_CST, r8
-#endif
/* Disable debug mode entry on breakpoints */
mfspr r8, SPRN_DER
#ifdef CONFIG_PERF_EVENTS
@@ -881,6 +718,109 @@
mtspr SPRN_DER, r8
blr
+#ifdef CONFIG_PIN_TLB
+_GLOBAL(mmu_pin_tlb)
+ lis r9, (1f - PAGE_OFFSET)@h
+ ori r9, r9, (1f - PAGE_OFFSET)@l
+ mfmsr r10
+ mflr r11
+ li r12, MSR_KERNEL & ~(MSR_IR | MSR_DR | MSR_RI)
+ rlwinm r0, r10, 0, ~MSR_RI
+ rlwinm r0, r0, 0, ~MSR_EE
+ mtmsr r0
+ isync
+ .align 4
+ mtspr SPRN_SRR0, r9
+ mtspr SPRN_SRR1, r12
+ rfi
+1:
+ li r5, 0
+ lis r6, MD_TWAM@h
+ mtspr SPRN_MI_CTR, r5
+ mtspr SPRN_MD_CTR, r6
+ tlbia
+
+#ifdef CONFIG_PIN_TLB_TEXT
+ LOAD_REG_IMMEDIATE(r5, 28 << 8)
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
+ LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
+ LOAD_REG_ADDR(r9, _sinittext)
+ li r0, 4
+ mtctr r0
+
+2: ori r0, r6, MI_EVALID
+ mtspr SPRN_MI_CTR, r5
+ mtspr SPRN_MI_EPN, r0
+ mtspr SPRN_MI_TWC, r7
+ mtspr SPRN_MI_RPN, r8
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r9
+ bdnzt lt, 2b
+ lis r0, MI_RSV4I@h
+ mtspr SPRN_MI_CTR, r0
+#endif
+ LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
+#ifdef CONFIG_PIN_TLB_DATA
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
+ li r8, 0
+#ifdef CONFIG_PIN_TLB_IMMR
+ li r0, 3
+#else
+ li r0, 4
+#endif
+ mtctr r0
+ cmpwi r4, 0
+ beq 4f
+ LOAD_REG_ADDR(r9, _sinittext)
+
+2: ori r0, r6, MD_EVALID
+ ori r12, r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r12
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r9
+ bdnzt lt, 2b
+4:
+2: ori r0, r6, MD_EVALID
+ ori r12, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r12
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r3
+ bdnzt lt, 2b
+#endif
+#ifdef CONFIG_PIN_TLB_IMMR
+ LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
+ LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
+ mfspr r8, SPRN_IMMR
+ rlwinm r8, r8, 0, 0xfff80000
+ ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
+ _PAGE_NO_CACHE | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r8
+#endif
+#if defined(CONFIG_PIN_TLB_IMMR) || defined(CONFIG_PIN_TLB_DATA)
+ lis r0, (MD_RSV4I | MD_TWAM)@h
+ mtspr SPRN_MD_CTR, r0
+#endif
+ mtspr SPRN_SRR1, r10
+ mtspr SPRN_SRR0, r11
+ rfi
+#endif /* CONFIG_PIN_TLB */
/*
* We put a few things here that have to be page-aligned.
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_book3s_32.S
similarity index 87%
rename from arch/powerpc/kernel/head_32.S
rename to arch/powerpc/kernel/head_book3s_32.S
index edaab11..96b4590 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -17,10 +17,10 @@
*/
#include <linux/init.h>
+#include <linux/pgtable.h>
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
@@ -34,16 +34,6 @@
#include "head_32.h"
-/* 601 only have IBAT */
-#ifdef CONFIG_PPC_BOOK3S_601
-#define LOAD_BAT(n, reg, RA, RB) \
- li RA,0; \
- mtspr SPRN_IBAT##n##U,RA; \
- lwz RA,(n*16)+0(reg); \
- lwz RB,(n*16)+4(reg); \
- mtspr SPRN_IBAT##n##U,RA; \
- mtspr SPRN_IBAT##n##L,RB
-#else
#define LOAD_BAT(n, reg, RA, RB) \
/* see the comment for clear_bats() -- Cort */ \
li RA,0; \
@@ -57,11 +47,10 @@
lwz RB,(n*16)+12(reg); \
mtspr SPRN_DBAT##n##U,RA; \
mtspr SPRN_DBAT##n##L,RB
-#endif
__HEAD
.stabs "arch/powerpc/kernel/",N_SO,0,0,0f
- .stabs "head_32.S",N_SO,0,0,0f
+ .stabs "head_book3s_32.S",N_SO,0,0,0f
0:
_ENTRY(_stext);
@@ -166,9 +155,10 @@
bl initial_bats
bl load_segment_registers
-#ifdef CONFIG_KASAN
+BEGIN_MMU_FTR_SECTION
+ bl reloc_offset
bl early_hash_table
-#endif
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
#if defined(CONFIG_BOOTX_TEXT)
bl setup_disp_bat
#endif
@@ -185,10 +175,8 @@
bl reloc_offset
li r24,0 /* cpu# */
bl call_setup_cpu /* Call setup_cpu for this CPU */
-#ifdef CONFIG_PPC_BOOK3S_32
bl reloc_offset
bl init_idle_6xx
-#endif /* CONFIG_PPC_BOOK3S_32 */
/*
@@ -219,7 +207,6 @@
lis r0,start_here@h
ori r0,r0,start_here@l
mtspr SPRN_SRR0,r0
- SYNC
RFI /* enables MMU */
/*
@@ -272,53 +259,111 @@
*/
. = 0x200
DO_KVM 0x200
- mtspr SPRN_SPRG_SCRATCH0,r10
- mtspr SPRN_SPRG_SCRATCH1,r11
- mfcr r10
+MachineCheck:
+ EXCEPTION_PROLOG_0
#ifdef CONFIG_PPC_CHRP
+#ifdef CONFIG_VMAP_STACK
+ mr r11, r1
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, RTAS_SP(r1)
+ cmpwi cr1, r1, 0
+ bne cr1, 7f
+ mr r1, r11
+#else
mfspr r11, SPRN_SPRG_THREAD
lwz r11, RTAS_SP(r11)
cmpwi cr1, r11, 0
bne cr1, 7f
+#endif
#endif /* CONFIG_PPC_CHRP */
- EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_1 for_rtas=1
7: EXCEPTION_PROLOG_2
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_CHRP
- bne cr1,1f
-#endif
- EXC_XFER_STD(0x200, machine_check_exception)
-#ifdef CONFIG_PPC_CHRP
-1: b machine_check_in_rtas
+ beq cr1, machine_check_tramp
+ twi 31, 0, 0
+#else
+ b machine_check_tramp
#endif
/* Data access exception. */
. = 0x300
DO_KVM 0x300
DataAccess:
- EXCEPTION_PROLOG
- mfspr r10,SPRN_DSISR
- stw r10,_DSISR(r11)
-#ifdef CONFIG_PPC_KUAP
- andis. r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
-#else
- andis. r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h
-#endif
- bne 1f /* if not, try to put a PTE */
- mfspr r4,SPRN_DAR /* into the hash table */
- rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mfspr r10, SPRN_SPRG_THREAD
BEGIN_MMU_FTR_SECTION
- bl hash_page
+ stw r11, THR11(r10)
+ mfspr r10, SPRN_DSISR
+ mfcr r11
+#ifdef CONFIG_PPC_KUAP
+ andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+#else
+ andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
+#endif
+ mfspr r10, SPRN_SPRG_THREAD
+ beq hash_page_dsi
+.Lhash_page_dsi_cont:
+ mtcr r11
+ lwz r11, THR11(r10)
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
-1: lwz r5,_DSISR(r11) /* get DSISR value */
- mfspr r4,SPRN_DAR
- EXC_XFER_LITE(0x300, handle_page_fault)
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r11, SPRN_DAR
+ stw r11, DAR(r10)
+ mfspr r11, SPRN_DSISR
+ stw r11, DSISR(r10)
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+ andi. r11, r11, MSR_PR
+ EXCEPTION_PROLOG_1
+ b handle_page_fault_tramp_1
+#else /* CONFIG_VMAP_STACK */
+ EXCEPTION_PROLOG handle_dar_dsisr=1
+ get_and_save_dar_dsisr_on_stack r4, r5, r11
+BEGIN_MMU_FTR_SECTION
+#ifdef CONFIG_PPC_KUAP
+ andis. r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+#else
+ andis. r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
+#endif
+ bne handle_page_fault_tramp_2 /* if not, try to put a PTE */
+ rlwinm r3, r5, 32 - 15, 21, 21 /* DSISR_STORE -> _PAGE_RW */
+ bl hash_page
+ b handle_page_fault_tramp_1
+FTR_SECTION_ELSE
+ b handle_page_fault_tramp_2
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+#endif /* CONFIG_VMAP_STACK */
/* Instruction access exception. */
. = 0x400
DO_KVM 0x400
InstructionAccess:
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r10, SPRN_SPRG_THREAD
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+BEGIN_MMU_FTR_SECTION
+ andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */
+ bne hash_page_isi
+.Lhash_page_isi_cont:
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+ andi. r11, r11, MSR_PR
+
+ EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2
+#else /* CONFIG_VMAP_STACK */
EXCEPTION_PROLOG
andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */
beq 1f /* if so, try to put a PTE */
@@ -327,8 +372,10 @@
BEGIN_MMU_FTR_SECTION
bl hash_page
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif /* CONFIG_VMAP_STACK */
1: mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
+ stw r4, _DAR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
@@ -338,13 +385,10 @@
. = 0x600
DO_KVM 0x600
Alignment:
- EXCEPTION_PROLOG
- mfspr r4,SPRN_DAR
- stw r4,_DAR(r11)
- mfspr r5,SPRN_DSISR
- stw r5,_DSISR(r11)
+ EXCEPTION_PROLOG handle_dar_dsisr=1
+ save_dar_dsisr_on_stack r4, r5, r11
addi r3,r1,STACK_FRAME_OVERHEAD
- EXC_XFER_STD(0x600, alignment_exception)
+ b alignment_exception_tramp
/* Program check exception */
EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
@@ -379,7 +423,6 @@
SystemCall:
SYSCALL_ENTRY 0xc00
-/* Single step - not used on 601 */
EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
@@ -414,13 +457,13 @@
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_IMISS
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SPRG_PGDIR
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
@@ -478,11 +521,11 @@
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_DMISS
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
li r1, _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
@@ -555,11 +598,11 @@
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_DMISS
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
@@ -604,6 +647,10 @@
#define altivec_assist_exception unknown_exception
#endif
+#ifndef CONFIG_TAU_INT
+#define TAUException unknown_exception
+#endif
+
EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD)
EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_STD)
EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
@@ -636,6 +683,99 @@
. = 0x3000
+machine_check_tramp:
+ EXC_XFER_STD(0x200, machine_check_exception)
+
+alignment_exception_tramp:
+ EXC_XFER_STD(0x600, alignment_exception)
+
+handle_page_fault_tramp_1:
+#ifdef CONFIG_VMAP_STACK
+ EXCEPTION_PROLOG_2 handle_dar_dsisr=1
+#endif
+ lwz r4, _DAR(r11)
+ lwz r5, _DSISR(r11)
+ /* fall through */
+handle_page_fault_tramp_2:
+ EXC_XFER_LITE(0x300, handle_page_fault)
+
+#ifdef CONFIG_VMAP_STACK
+.macro save_regs_thread thread
+ stw r0, THR0(\thread)
+ stw r3, THR3(\thread)
+ stw r4, THR4(\thread)
+ stw r5, THR5(\thread)
+ stw r6, THR6(\thread)
+ stw r8, THR8(\thread)
+ stw r9, THR9(\thread)
+ mflr r0
+ stw r0, THLR(\thread)
+ mfctr r0
+ stw r0, THCTR(\thread)
+.endm
+
+.macro restore_regs_thread thread
+ lwz r0, THLR(\thread)
+ mtlr r0
+ lwz r0, THCTR(\thread)
+ mtctr r0
+ lwz r0, THR0(\thread)
+ lwz r3, THR3(\thread)
+ lwz r4, THR4(\thread)
+ lwz r5, THR5(\thread)
+ lwz r6, THR6(\thread)
+ lwz r8, THR8(\thread)
+ lwz r9, THR9(\thread)
+.endm
+
+hash_page_dsi:
+ save_regs_thread r10
+ mfdsisr r3
+ mfdar r4
+ mfsrr0 r5
+ mfsrr1 r9
+ rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ b .Lhash_page_dsi_cont
+
+hash_page_isi:
+ mr r11, r10
+ mfspr r10, SPRN_SPRG_THREAD
+ save_regs_thread r10
+ li r3, 0
+ lwz r4, SRR0(r10)
+ lwz r9, SRR1(r10)
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ mr r10, r11
+ b .Lhash_page_isi_cont
+
+ .globl fast_hash_page_return
+fast_hash_page_return:
+ andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ bne 1f
+
+ /* DSI */
+ mtcr r11
+ lwz r11, THR11(r10)
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ RFI
+
+1: /* ISI */
+ mtcr r11
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ RFI
+
+stack_overflow:
+ vmap_stack_overflow_exception
+#endif
+
AltiVecUnavailable:
EXCEPTION_PROLOG
#ifdef CONFIG_ALTIVEC
@@ -720,7 +860,6 @@
set to map the 0xf0000000 - 0xffffffff region */
mfmsr r0
rlwinm r0,r0,0,28,26 /* clear DR (0x10) */
- SYNC
mtmsr r0
isync
@@ -732,10 +871,8 @@
lis r3,-KERNELBASE@h
mr r4,r24
bl call_setup_cpu /* Call setup_cpu for this CPU */
-#ifdef CONFIG_PPC_BOOK3S_32
lis r3,-KERNELBASE@h
bl init_idle_6xx
-#endif /* CONFIG_PPC_BOOK3S_32 */
/* get current's stack and current */
lis r2,secondary_current@ha
@@ -768,7 +905,6 @@
ori r3,r3,start_secondary@l
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
- SYNC
RFI
#endif /* CONFIG_SMP */
@@ -777,21 +913,9 @@
#endif
/*
- * Those generic dummy functions are kept for CPUs not
- * included in CONFIG_PPC_BOOK3S_32
- */
-#if !defined(CONFIG_PPC_BOOK3S_32)
-_ENTRY(__save_cpu_setup)
- blr
-_ENTRY(__restore_cpu_setup)
- blr
-#endif /* !defined(CONFIG_PPC_BOOK3S_32) */
-
-/*
* Load stuff into the MMU. Intended to be called with
* IR=0 and DR=0.
*/
-#ifdef CONFIG_KASAN
early_hash_table:
sync /* Force all PTE updates to finish */
isync
@@ -802,8 +926,10 @@
lis r6, early_hash - PAGE_OFFSET@h
ori r6, r6, 3 /* 256kB table */
mtspr SPRN_SDR1, r6
+ lis r6, early_hash@h
+ addis r3, r3, Hash@ha
+ stw r6, Hash@l(r3)
blr
-#endif
load_up_mmu:
sync /* Force all PTE updates to finish */
@@ -817,8 +943,7 @@
lwz r6,_SDR1@l(r6)
mtspr SPRN_SDR1,r6
-/* Load the BAT registers with the values set up by MMU_init.
- MMU_init takes care of whether we're on a 601 or not. */
+/* Load the BAT registers with the values set up by MMU_init. */
lis r3,BATS@ha
addi r3,r3,BATS@l
tophys(r3,r3)
@@ -893,11 +1018,7 @@
bl machine_init
bl __save_cpu_setup
bl MMU_init
-#ifdef CONFIG_KASAN
-BEGIN_MMU_FTR_SECTION
bl MMU_init_hw_patch
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
-#endif
/*
* Go back to running unmapped so we can load up new values
@@ -908,9 +1029,10 @@
ori r4,r4,2f@l
tophys(r4,r4)
li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+
+ .align 4
mtspr SPRN_SRR0,r4
mtspr SPRN_SRR1,r3
- SYNC
RFI
/* Load up the kernel context */
2: bl load_up_mmu
@@ -922,7 +1044,7 @@
*/
lis r5, abatron_pteptrs@h
ori r5, r5, abatron_pteptrs@l
- stw r5, 0xf0(r0) /* This much match your Abatron config */
+ stw r5, 0xf0(0) /* This much match your Abatron config */
lis r6, swapper_pg_dir@h
ori r6, r6, swapper_pg_dir@l
tophys(r5, r5)
@@ -935,7 +1057,6 @@
ori r3,r3,start_kernel@l
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
- SYNC
RFI
/*
@@ -995,7 +1116,6 @@
clear_bats:
li r10,0
-#ifndef CONFIG_PPC_BOOK3S_601
mtspr SPRN_DBAT0U,r10
mtspr SPRN_DBAT0L,r10
mtspr SPRN_DBAT1U,r10
@@ -1004,7 +1124,6 @@
mtspr SPRN_DBAT2L,r10
mtspr SPRN_DBAT3U,r10
mtspr SPRN_DBAT3L,r10
-#endif
mtspr SPRN_IBAT0U,r10
mtspr SPRN_IBAT0L,r10
mtspr SPRN_IBAT1U,r10
@@ -1049,9 +1168,10 @@
rlwinm r0, r6, 0, ~MSR_RI
rlwinm r0, r0, 0, ~MSR_EE
mtmsr r0
+
+ .align 4
mtspr SPRN_SRR0, r4
mtspr SPRN_SRR1, r3
- SYNC
RFI
1: bl clear_bats
lis r3, BATS@ha
@@ -1071,7 +1191,6 @@
mtmsr r3
mtspr SPRN_SRR0, r7
mtspr SPRN_SRR1, r6
- SYNC
RFI
flush_tlbs:
@@ -1088,31 +1207,16 @@
andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */
beqlr
andc r3,r3,r0
+
+ .align 4
mtspr SPRN_SRR0,r4
mtspr SPRN_SRR1,r3
sync
RFI
-/*
- * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET
- * (we keep one for debugging) and on others, we use one 256M BAT.
- */
+/* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */
initial_bats:
lis r11,PAGE_OFFSET@h
-#ifdef CONFIG_PPC_BOOK3S_601
- ori r11,r11,4 /* set up BAT registers for 601 */
- li r8,0x7f /* valid, block length = 8MB */
- mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */
- mtspr SPRN_IBAT0L,r8 /* lower BAT register */
- addis r11,r11,0x800000@h
- addis r8,r8,0x800000@h
- mtspr SPRN_IBAT1U,r11
- mtspr SPRN_IBAT1L,r8
- addis r11,r11,0x800000@h
- addis r8,r8,0x800000@h
- mtspr SPRN_IBAT2U,r11
- mtspr SPRN_IBAT2L,r8
-#else
tophys(r8,r11)
#ifdef CONFIG_SMP
ori r8,r8,0x12 /* R/W access, M=1 */
@@ -1121,11 +1225,10 @@
#endif /* CONFIG_SMP */
ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */
- mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */
+ mtspr SPRN_DBAT0L,r8 /* N.B. 6xx have valid */
mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */
mtspr SPRN_IBAT0L,r8
mtspr SPRN_IBAT0U,r11
-#endif
isync
blr
@@ -1143,13 +1246,8 @@
beqlr
lwz r11,0(r8)
lwz r8,4(r8)
-#ifndef CONFIG_PPC_BOOK3S_601
mtspr SPRN_DBAT3L,r8
mtspr SPRN_DBAT3U,r11
-#else
- mtspr SPRN_IBAT3L,r8
- mtspr SPRN_IBAT3U,r11
-#endif
blr
#endif /* CONFIG_BOOTX_TEXT */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 2ae635d..71c359d 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -104,16 +104,18 @@
#ifdef CONFIG_KVM_BOOKE_HV
ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
#endif
+ mfspr r9, SPRN_SRR1
BOOKE_CLEAR_BTB(r11)
+ andi. r11, r9, MSR_PR
lwz r11, TASK_STACK - THREAD(r10)
rlwinm r12,r12,0,4,2 /* Clear SO bit in CR */
+ beq- 99f
ALLOC_STACK_FRAME(r11, THREAD_SIZE - INT_FRAME_SIZE)
stw r12, _CCR(r11) /* save various registers */
mflr r12
stw r12,_LINK(r11)
mfspr r12,SPRN_SRR0
stw r1, GPR1(r11)
- mfspr r9,SPRN_SRR1
stw r1, 0(r11)
mr r1, r11
stw r12,_NIP(r11)
@@ -174,8 +176,8 @@
#endif
mtspr SPRN_SRR1,r10
mtspr SPRN_SRR0,r11
- SYNC
RFI /* jump to handler, enable MMU */
+99: b ret_from_kernel_syscall
.endm
/* To handle the additional exception priority levels on 40x and Book-E
@@ -467,6 +469,7 @@
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \
+ stw r4, _DEAR(r11); \
EXC_XFER_LITE(0x0300, handle_page_fault)
#define INSTRUCTION_STORAGE_EXCEPTION \
@@ -475,6 +478,7 @@
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mr r4,r12; /* Pass SRR0 as arg2 */ \
+ stw r4, _DEAR(r11); \
li r5,0; /* Pass zero as arg3 */ \
EXC_XFER_LITE(0x0400, handle_page_fault)
@@ -529,7 +533,7 @@
};
/* ensure this structure is always sized to a multiple of the stack alignment */
-#define STACK_EXC_LVL_FRAME_SIZE _ALIGN_UP(sizeof (struct exception_regs), 16)
+#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16)
#endif /* __ASSEMBLY__ */
#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 519d495..586a6ac 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -28,10 +28,10 @@
#include <linux/init.h>
#include <linux/threads.h>
+#include <linux/pgtable.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
@@ -155,6 +155,8 @@
*/
_ENTRY(__early_start)
+ LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr)
+ lwz r20,0(r20)
#define ENTRY_MAPPING_BOOT_SETUP
#include "fsl_booke_entry_mapping.S"
@@ -277,8 +279,8 @@
ori r6, r6, swapper_pg_dir@l
lis r5, abatron_pteptrs@h
ori r5, r5, abatron_pteptrs@l
- lis r4, KERNELBASE@h
- ori r4, r4, KERNELBASE@l
+ lis r3, kernstart_virt_addr@ha
+ lwz r4, kernstart_virt_addr@l(r3)
stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
stw r6, 0(r5)
@@ -376,6 +378,7 @@
mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
andis. r10,r5,(ESR_ILK|ESR_DLK)@h
bne 1f
+ stw r4, _DEAR(r11)
EXC_XFER_LITE(0x0300, handle_page_fault)
1:
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -1067,7 +1070,12 @@
mr r5,r25 /* phys kernel start */
rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */
subf r4,r5,r4 /* memstart_addr - phys kernel start */
- li r5,0 /* no device tree */
+ lis r7,KERNELBASE@h
+ ori r7,r7,KERNELBASE@l
+ cmpw r20,r7 /* if kernstart_virt_addr != KERNELBASE, randomized */
+ beq 2f
+ li r4,0
+2: li r5,0 /* no device tree */
li r6,0 /* not boot cpu */
bl restore_to_as0
@@ -1115,6 +1123,54 @@
#endif
/*
+ * Create a 64M tlb by address and entry
+ * r3 - entry
+ * r4 - virtual address
+ * r5/r6 - physical address
+ */
+_GLOBAL(create_kaslr_tlb_entry)
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7 /* Write MAS0 */
+
+ lis r3,(MAS1_VALID|MAS1_IPROT)@h
+ ori r3,r3,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
+ mtspr SPRN_MAS1,r3 /* Write MAS1 */
+
+ lis r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r3,r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r3,r3,r4
+ ori r3,r3,MAS2_M_IF_NEEDED@l
+ mtspr SPRN_MAS2,r3 /* Write MAS2(EPN) */
+
+#ifdef CONFIG_PHYS_64BIT
+ ori r8,r6,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+ mtspr SPRN_MAS7,r5
+#else
+ ori r8,r5,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+#endif
+
+ tlbwe /* Write TLB */
+ isync
+ sync
+ blr
+
+/*
+ * Return to the start of the relocated kernel and run again
+ * r3 - virtual address of fdt
+ * r4 - entry of the kernel
+ */
+_GLOBAL(reloc_kernel_entry)
+ mfmsr r7
+ rlwinm r7, r7, 0, ~(MSR_IS | MSR_DS)
+
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r7
+ rfi
+
+/*
* Create a tlb entry with the same effective and physical address as
* the tlb entry used by the current running code. But set the TS to 1.
* Then switch to the address space 1. It will return with the r3 set to
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 1007ec3..f4e8f21 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -24,13 +24,14 @@
#include <asm/debug.h>
#include <asm/debugfs.h>
#include <asm/hvcall.h>
+#include <asm/inst.h>
#include <linux/uaccess.h>
/*
* Stores the breakpoints currently in use on each breakpoint address
* register for every cpu
*/
-static DEFINE_PER_CPU(struct perf_event *, bp_per_reg);
+static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM_MAX]);
/*
* Returns total number of data or instruction breakpoints available.
@@ -38,10 +39,21 @@
int hw_breakpoint_slots(int type)
{
if (type == TYPE_DATA)
- return HBP_NUM;
+ return nr_wp_slots();
return 0; /* no instruction breakpoints available */
}
+static bool single_step_pending(void)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (current->thread.last_hit_ubp[i])
+ return true;
+ }
+ return false;
+}
+
/*
* Install a perf counter breakpoint.
*
@@ -54,16 +66,26 @@
int arch_install_hw_breakpoint(struct perf_event *bp)
{
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
+ struct perf_event **slot;
+ int i;
- *slot = bp;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ slot = this_cpu_ptr(&bp_per_reg[i]);
+ if (!*slot) {
+ *slot = bp;
+ break;
+ }
+ }
+
+ if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
+ return -EBUSY;
/*
* Do not install DABR values if the instruction must be single-stepped.
* If so, DABR will be populated in single_step_dabr_instruction().
*/
- if (current->thread.last_hit_ubp != bp)
- __set_breakpoint(info);
+ if (!single_step_pending())
+ __set_breakpoint(i, info);
return 0;
}
@@ -79,15 +101,248 @@
*/
void arch_uninstall_hw_breakpoint(struct perf_event *bp)
{
- struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
+ struct arch_hw_breakpoint null_brk = {0};
+ struct perf_event **slot;
+ int i;
- if (*slot != bp) {
- WARN_ONCE(1, "Can't find the breakpoint");
- return;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ slot = this_cpu_ptr(&bp_per_reg[i]);
+ if (*slot == bp) {
+ *slot = NULL;
+ break;
+ }
}
- *slot = NULL;
- hw_breakpoint_disable();
+ if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
+ return;
+
+ __set_breakpoint(i, &null_brk);
+}
+
+static bool is_ptrace_bp(struct perf_event *bp)
+{
+ return bp->overflow_handler == ptrace_triggered;
+}
+
+struct breakpoint {
+ struct list_head list;
+ struct perf_event *bp;
+ bool ptrace_bp;
+};
+
+static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]);
+static LIST_HEAD(task_bps);
+
+static struct breakpoint *alloc_breakpoint(struct perf_event *bp)
+{
+ struct breakpoint *tmp;
+
+ tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return ERR_PTR(-ENOMEM);
+ tmp->bp = bp;
+ tmp->ptrace_bp = is_ptrace_bp(bp);
+ return tmp;
+}
+
+static bool bp_addr_range_overlap(struct perf_event *bp1, struct perf_event *bp2)
+{
+ __u64 bp1_saddr, bp1_eaddr, bp2_saddr, bp2_eaddr;
+
+ bp1_saddr = ALIGN_DOWN(bp1->attr.bp_addr, HW_BREAKPOINT_SIZE);
+ bp1_eaddr = ALIGN(bp1->attr.bp_addr + bp1->attr.bp_len, HW_BREAKPOINT_SIZE);
+ bp2_saddr = ALIGN_DOWN(bp2->attr.bp_addr, HW_BREAKPOINT_SIZE);
+ bp2_eaddr = ALIGN(bp2->attr.bp_addr + bp2->attr.bp_len, HW_BREAKPOINT_SIZE);
+
+ return (bp1_saddr < bp2_eaddr && bp1_eaddr > bp2_saddr);
+}
+
+static bool alternate_infra_bp(struct breakpoint *b, struct perf_event *bp)
+{
+ return is_ptrace_bp(bp) ? !b->ptrace_bp : b->ptrace_bp;
+}
+
+static bool can_co_exist(struct breakpoint *b, struct perf_event *bp)
+{
+ return !(alternate_infra_bp(b, bp) && bp_addr_range_overlap(b->bp, bp));
+}
+
+static int task_bps_add(struct perf_event *bp)
+{
+ struct breakpoint *tmp;
+
+ tmp = alloc_breakpoint(bp);
+ if (IS_ERR(tmp))
+ return PTR_ERR(tmp);
+
+ list_add(&tmp->list, &task_bps);
+ return 0;
+}
+
+static void task_bps_remove(struct perf_event *bp)
+{
+ struct list_head *pos, *q;
+
+ list_for_each_safe(pos, q, &task_bps) {
+ struct breakpoint *tmp = list_entry(pos, struct breakpoint, list);
+
+ if (tmp->bp == bp) {
+ list_del(&tmp->list);
+ kfree(tmp);
+ break;
+ }
+ }
+}
+
+/*
+ * If any task has breakpoint from alternate infrastructure,
+ * return true. Otherwise return false.
+ */
+static bool all_task_bps_check(struct perf_event *bp)
+{
+ struct breakpoint *tmp;
+
+ list_for_each_entry(tmp, &task_bps, list) {
+ if (!can_co_exist(tmp, bp))
+ return true;
+ }
+ return false;
+}
+
+/*
+ * If same task has breakpoint from alternate infrastructure,
+ * return true. Otherwise return false.
+ */
+static bool same_task_bps_check(struct perf_event *bp)
+{
+ struct breakpoint *tmp;
+
+ list_for_each_entry(tmp, &task_bps, list) {
+ if (tmp->bp->hw.target == bp->hw.target &&
+ !can_co_exist(tmp, bp))
+ return true;
+ }
+ return false;
+}
+
+static int cpu_bps_add(struct perf_event *bp)
+{
+ struct breakpoint **cpu_bp;
+ struct breakpoint *tmp;
+ int i = 0;
+
+ tmp = alloc_breakpoint(bp);
+ if (IS_ERR(tmp))
+ return PTR_ERR(tmp);
+
+ cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!cpu_bp[i]) {
+ cpu_bp[i] = tmp;
+ break;
+ }
+ }
+ return 0;
+}
+
+static void cpu_bps_remove(struct perf_event *bp)
+{
+ struct breakpoint **cpu_bp;
+ int i = 0;
+
+ cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!cpu_bp[i])
+ continue;
+
+ if (cpu_bp[i]->bp == bp) {
+ kfree(cpu_bp[i]);
+ cpu_bp[i] = NULL;
+ break;
+ }
+ }
+}
+
+static bool cpu_bps_check(int cpu, struct perf_event *bp)
+{
+ struct breakpoint **cpu_bp;
+ int i;
+
+ cpu_bp = per_cpu_ptr(cpu_bps, cpu);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp))
+ return true;
+ }
+ return false;
+}
+
+static bool all_cpu_bps_check(struct perf_event *bp)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ if (cpu_bps_check(cpu, bp))
+ return true;
+ }
+ return false;
+}
+
+/*
+ * We don't use any locks to serialize accesses to cpu_bps or task_bps
+ * because are already inside nr_bp_mutex.
+ */
+int arch_reserve_bp_slot(struct perf_event *bp)
+{
+ int ret;
+
+ /* ptrace breakpoint */
+ if (is_ptrace_bp(bp)) {
+ if (all_cpu_bps_check(bp))
+ return -ENOSPC;
+
+ if (same_task_bps_check(bp))
+ return -ENOSPC;
+
+ return task_bps_add(bp);
+ }
+
+ /* perf breakpoint */
+ if (is_kernel_addr(bp->attr.bp_addr))
+ return 0;
+
+ if (bp->hw.target && bp->cpu == -1) {
+ if (same_task_bps_check(bp))
+ return -ENOSPC;
+
+ return task_bps_add(bp);
+ } else if (!bp->hw.target && bp->cpu != -1) {
+ if (all_task_bps_check(bp))
+ return -ENOSPC;
+
+ return cpu_bps_add(bp);
+ }
+
+ if (same_task_bps_check(bp))
+ return -ENOSPC;
+
+ ret = cpu_bps_add(bp);
+ if (ret)
+ return ret;
+ ret = task_bps_add(bp);
+ if (ret)
+ cpu_bps_remove(bp);
+
+ return ret;
+}
+
+void arch_release_bp_slot(struct perf_event *bp)
+{
+ if (!is_kernel_addr(bp->attr.bp_addr)) {
+ if (bp->hw.target)
+ task_bps_remove(bp);
+ if (bp->cpu != -1)
+ cpu_bps_remove(bp);
+ }
}
/*
@@ -102,8 +357,14 @@
* restoration variables to prevent dangling pointers.
* FIXME, this should not be using bp->ctx at all! Sayeth peterz.
*/
- if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L))
- bp->ctx->task->thread.last_hit_ubp = NULL;
+ if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) {
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (bp->ctx->task->thread.last_hit_ubp[i] == bp)
+ bp->ctx->task->thread.last_hit_ubp[i] = NULL;
+ }
+ }
}
/*
@@ -127,15 +388,62 @@
}
/*
+ * Watchpoint match range is always doubleword(8 bytes) aligned on
+ * powerpc. If the given range is crossing doubleword boundary, we
+ * need to increase the length such that next doubleword also get
+ * covered. Ex,
+ *
+ * address len = 6 bytes
+ * |=========.
+ * |------------v--|------v--------|
+ * | | | | | | | | | | | | | | | | |
+ * |---------------|---------------|
+ * <---8 bytes--->
+ *
+ * In this case, we should configure hw as:
+ * start_addr = address & ~(HW_BREAKPOINT_SIZE - 1)
+ * len = 16 bytes
+ *
+ * @start_addr is inclusive but @end_addr is exclusive.
+ */
+static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
+{
+ u16 max_len = DABR_MAX_LEN;
+ u16 hw_len;
+ unsigned long start_addr, end_addr;
+
+ start_addr = ALIGN_DOWN(hw->address, HW_BREAKPOINT_SIZE);
+ end_addr = ALIGN(hw->address + hw->len, HW_BREAKPOINT_SIZE);
+ hw_len = end_addr - start_addr;
+
+ if (dawr_enabled()) {
+ max_len = DAWR_MAX_LEN;
+ /* DAWR region can't cross 512 bytes boundary on p10 predecessors */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31) &&
+ (ALIGN_DOWN(start_addr, SZ_512) != ALIGN_DOWN(end_addr - 1, SZ_512)))
+ return -EINVAL;
+ } else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ /* 8xx can setup a range without limitation */
+ max_len = U16_MAX;
+ }
+
+ if (hw_len > max_len)
+ return -EINVAL;
+
+ hw->hw_len = hw_len;
+ return 0;
+}
+
+/*
* Validate the arch-specific HW Breakpoint register settings
*/
int hw_breakpoint_arch_parse(struct perf_event *bp,
const struct perf_event_attr *attr,
struct arch_hw_breakpoint *hw)
{
- int ret = -EINVAL, length_max;
+ int ret = -EINVAL;
- if (!bp)
+ if (!bp || !attr->bp_len)
return ret;
hw->type = HW_BRK_TYPE_TRANSLATE;
@@ -155,26 +463,10 @@
hw->address = attr->bp_addr;
hw->len = attr->bp_len;
- /*
- * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
- * and breakpoint addresses are aligned to nearest double-word
- * HW_BREAKPOINT_ALIGN by rounding off to the lower address, the
- * 'symbolsize' should satisfy the check below.
- */
if (!ppc_breakpoint_available())
return -ENODEV;
- length_max = 8; /* DABR */
- if (dawr_enabled()) {
- length_max = 512 ; /* 64 doublewords */
- /* DAWR region can't cross 512 boundary */
- if ((attr->bp_addr >> 9) !=
- ((attr->bp_addr + attr->bp_len - 1) >> 9))
- return -EINVAL;
- }
- if (hw->len >
- (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
- return -EINVAL;
- return 0;
+
+ return hw_breakpoint_validate_len(hw);
}
/*
@@ -185,75 +477,93 @@
void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
{
struct arch_hw_breakpoint *info;
+ int i;
- if (likely(!tsk->thread.last_hit_ubp))
- return;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (unlikely(tsk->thread.last_hit_ubp[i]))
+ goto reset;
+ }
+ return;
- info = counter_arch_bp(tsk->thread.last_hit_ubp);
+reset:
regs->msr &= ~MSR_SE;
- __set_breakpoint(info);
- tsk->thread.last_hit_ubp = NULL;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ info = counter_arch_bp(__this_cpu_read(bp_per_reg[i]));
+ __set_breakpoint(i, info);
+ tsk->thread.last_hit_ubp[i] = NULL;
+ }
}
-static bool is_larx_stcx_instr(struct pt_regs *regs, unsigned int instr)
+static bool is_larx_stcx_instr(int type)
{
- int ret, type;
- struct instruction_op op;
-
- ret = analyse_instr(&op, regs, instr);
- type = GETTYPE(op.type);
- return (!ret && (type == LARX || type == STCX));
+ return type == LARX || type == STCX;
}
/*
- * Handle debug exception notifications.
+ * We've failed in reliably handling the hw-breakpoint. Unregister
+ * it and throw a warning message to let the user know about it.
*/
-static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp,
- unsigned long addr)
+static void handler_error(struct perf_event *bp, struct arch_hw_breakpoint *info)
{
- unsigned int instr = 0;
+ WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.",
+ info->address);
+ perf_event_disable_inatomic(bp);
+}
- if (__get_user_inatomic(instr, (unsigned int *)regs->nip))
- goto fail;
+static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info)
+{
+ printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n",
+ info->address);
+ perf_event_disable_inatomic(bp);
+}
- if (is_larx_stcx_instr(regs, instr)) {
- printk_ratelimited("Breakpoint hit on instruction that can't be emulated."
- " Breakpoint at 0x%lx will be disabled.\n", addr);
- goto disable;
- }
+static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
+ struct arch_hw_breakpoint **info, int *hit,
+ struct ppc_inst instr)
+{
+ int i;
+ int stepped;
/* Do not emulate user-space instructions, instead single-step them */
if (user_mode(regs)) {
- current->thread.last_hit_ubp = bp;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ current->thread.last_hit_ubp[i] = bp[i];
+ info[i] = NULL;
+ }
regs->msr |= MSR_SE;
return false;
}
- if (!emulate_step(regs, instr))
- goto fail;
-
+ stepped = emulate_step(regs, instr);
+ if (!stepped) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ handler_error(bp[i], info[i]);
+ info[i] = NULL;
+ }
+ return false;
+ }
return true;
-
-fail:
- /*
- * We've failed in reliably handling the hw-breakpoint. Unregister
- * it and throw a warning message to let the user know about it.
- */
- WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
- "0x%lx will be disabled.", addr);
-
-disable:
- perf_event_disable_inatomic(bp);
- return false;
}
int hw_breakpoint_handler(struct die_args *args)
{
+ bool err = false;
int rc = NOTIFY_STOP;
- struct perf_event *bp;
+ struct perf_event *bp[HBP_NUM_MAX] = { NULL };
struct pt_regs *regs = args->regs;
- struct arch_hw_breakpoint *info;
- unsigned long dar = regs->dar;
+ struct arch_hw_breakpoint *info[HBP_NUM_MAX] = { NULL };
+ int i;
+ int hit[HBP_NUM_MAX] = {0};
+ int nr_hit = 0;
+ bool ptrace_bp = false;
+ struct ppc_inst instr = ppc_inst(0);
+ int type = 0;
+ int size = 0;
+ unsigned long ea;
/* Disable breakpoints during exception handling */
hw_breakpoint_disable();
@@ -266,12 +576,40 @@
*/
rcu_read_lock();
- bp = __this_cpu_read(bp_per_reg);
- if (!bp) {
+ if (!IS_ENABLED(CONFIG_PPC_8xx))
+ wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ bp[i] = __this_cpu_read(bp_per_reg[i]);
+ if (!bp[i])
+ continue;
+
+ info[i] = counter_arch_bp(bp[i]);
+ info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+
+ if (wp_check_constraints(regs, instr, ea, type, size, info[i])) {
+ if (!IS_ENABLED(CONFIG_PPC_8xx) &&
+ ppc_inst_equal(instr, ppc_inst(0))) {
+ handler_error(bp[i], info[i]);
+ info[i] = NULL;
+ err = 1;
+ continue;
+ }
+
+ if (is_ptrace_bp(bp[i]))
+ ptrace_bp = true;
+ hit[i] = 1;
+ nr_hit++;
+ }
+ }
+
+ if (err)
+ goto reset;
+
+ if (!nr_hit) {
rc = NOTIFY_DONE;
goto out;
}
- info = counter_arch_bp(bp);
/*
* Return early after invoking user-callback function without restoring
@@ -279,34 +617,50 @@
* one-shot mode. The ptrace-ed process will receive the SIGTRAP signal
* generated in do_dabr().
*/
- if (bp->overflow_handler == ptrace_triggered) {
- perf_bp_event(bp, regs);
+ if (ptrace_bp) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ perf_bp_event(bp[i], regs);
+ info[i] = NULL;
+ }
rc = NOTIFY_DONE;
- goto out;
+ goto reset;
}
- /*
- * Verify if dar lies within the address range occupied by the symbol
- * being watched to filter extraneous exceptions. If it doesn't,
- * we still need to single-step the instruction, but we don't
- * generate an event.
- */
- info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
- if (!((bp->attr.bp_addr <= dar) &&
- (dar - bp->attr.bp_addr < bp->attr.bp_len)))
- info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ if (!IS_ENABLED(CONFIG_PPC_8xx)) {
+ if (is_larx_stcx_instr(type)) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ larx_stcx_err(bp[i], info[i]);
+ info[i] = NULL;
+ }
+ goto reset;
+ }
- if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info->address))
- goto out;
+ if (!stepping_handler(regs, bp, info, hit, instr))
+ goto reset;
+ }
/*
* As a policy, the callback is invoked in a 'trigger-after-execute'
* fashion
*/
- if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
- perf_bp_event(bp, regs);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ if (!(info[i]->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+ perf_bp_event(bp[i], regs);
+ }
- __set_breakpoint(info);
+reset:
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!info[i])
+ continue;
+ __set_breakpoint(i, info[i]);
+ }
+
out:
rcu_read_unlock();
return rc;
@@ -321,26 +675,43 @@
struct pt_regs *regs = args->regs;
struct perf_event *bp = NULL;
struct arch_hw_breakpoint *info;
+ int i;
+ bool found = false;
- bp = current->thread.last_hit_ubp;
/*
* Check if we are single-stepping as a result of a
* previous HW Breakpoint exception
*/
- if (!bp)
+ for (i = 0; i < nr_wp_slots(); i++) {
+ bp = current->thread.last_hit_ubp[i];
+
+ if (!bp)
+ continue;
+
+ found = true;
+ info = counter_arch_bp(bp);
+
+ /*
+ * We shall invoke the user-defined callback function in the
+ * single stepping handler to confirm to 'trigger-after-execute'
+ * semantics
+ */
+ if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+ perf_bp_event(bp, regs);
+ current->thread.last_hit_ubp[i] = NULL;
+ }
+
+ if (!found)
return NOTIFY_DONE;
- info = counter_arch_bp(bp);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ bp = __this_cpu_read(bp_per_reg[i]);
+ if (!bp)
+ continue;
- /*
- * We shall invoke the user-defined callback function in the single
- * stepping handler to confirm to 'trigger-after-execute' semantics
- */
- if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
- perf_bp_event(bp, regs);
-
- __set_breakpoint(info);
- current->thread.last_hit_ubp = NULL;
+ info = counter_arch_bp(bp);
+ __set_breakpoint(i, info);
+ }
/*
* If the process was being single-stepped by ptrace, let the
@@ -379,13 +750,32 @@
*/
void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
{
+ int i;
struct thread_struct *t = &tsk->thread;
- unregister_hw_breakpoint(t->ptrace_bps[0]);
- t->ptrace_bps[0] = NULL;
+ for (i = 0; i < nr_wp_slots(); i++) {
+ unregister_hw_breakpoint(t->ptrace_bps[i]);
+ t->ptrace_bps[i] = NULL;
+ }
}
void hw_breakpoint_pmu_read(struct perf_event *bp)
{
/* TODO */
}
+
+void ptrace_triggered(struct perf_event *bp,
+ struct perf_sample_data *data, struct pt_regs *regs)
+{
+ struct perf_event_attr attr;
+
+ /*
+ * Disable the breakpoint request here since ptrace has defined a
+ * one-shot behaviour for breakpoint exceptions in PPC64.
+ * The SIGTRAP signal is generated automatically for us in do_dabr().
+ * We don't have to do anything about that here
+ */
+ attr = bp->attr;
+ attr.disabled = true;
+ modify_user_hw_breakpoint(bp, &attr);
+}
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
new file mode 100644
index 0000000..867ee4a
--- /dev/null
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <asm/hw_breakpoint.h>
+#include <asm/sstep.h>
+#include <asm/cache.h>
+
+static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info)
+{
+ return ((info->address <= dar) && (dar - info->address < info->len));
+}
+
+static bool ea_user_range_overlaps(unsigned long ea, int size,
+ struct arch_hw_breakpoint *info)
+{
+ return ((ea < info->address + info->len) &&
+ (ea + size > info->address));
+}
+
+static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info)
+{
+ unsigned long hw_start_addr, hw_end_addr;
+
+ hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE);
+ hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE);
+
+ return ((hw_start_addr <= dar) && (hw_end_addr > dar));
+}
+
+static bool ea_hw_range_overlaps(unsigned long ea, int size,
+ struct arch_hw_breakpoint *info)
+{
+ unsigned long hw_start_addr, hw_end_addr;
+ unsigned long align_size = HW_BREAKPOINT_SIZE;
+
+ /*
+ * On p10 predecessors, quadword is handle differently then
+ * other instructions.
+ */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16)
+ align_size = HW_BREAKPOINT_SIZE_QUADWORD;
+
+ hw_start_addr = ALIGN_DOWN(info->address, align_size);
+ hw_end_addr = ALIGN(info->address + info->len, align_size);
+
+ return ((ea < hw_end_addr) && (ea + size > hw_start_addr));
+}
+
+/*
+ * If hw has multiple DAWR registers, we also need to check all
+ * dawrx constraint bits to confirm this is _really_ a valid event.
+ * If type is UNKNOWN, but privilege level matches, consider it as
+ * a positive match.
+ */
+static bool check_dawrx_constraints(struct pt_regs *regs, int type,
+ struct arch_hw_breakpoint *info)
+{
+ if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ))
+ return false;
+
+ /*
+ * The Cache Management instructions other than dcbz never
+ * cause a match. i.e. if type is CACHEOP, the instruction
+ * is dcbz, and dcbz is treated as Store.
+ */
+ if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE))
+ return false;
+
+ if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL))
+ return false;
+
+ if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER))
+ return false;
+
+ return true;
+}
+
+/*
+ * Return true if the event is valid wrt dawr configuration,
+ * including extraneous exception. Otherwise return false.
+ */
+bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr,
+ unsigned long ea, int type, int size,
+ struct arch_hw_breakpoint *info)
+{
+ bool in_user_range = dar_in_user_range(regs->dar, info);
+ bool dawrx_constraints;
+
+ /*
+ * 8xx supports only one breakpoint and thus we can
+ * unconditionally return true.
+ */
+ if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ if (!in_user_range)
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ return true;
+ }
+
+ if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ !dar_in_hw_range(regs->dar, info))
+ return false;
+
+ return true;
+ }
+
+ dawrx_constraints = check_dawrx_constraints(regs, type, info);
+
+ if (type == UNKNOWN) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ !dar_in_hw_range(regs->dar, info))
+ return false;
+
+ return dawrx_constraints;
+ }
+
+ if (ea_user_range_overlaps(ea, size, info))
+ return dawrx_constraints;
+
+ if (ea_hw_range_overlaps(ea, size, info)) {
+ if (dawrx_constraints) {
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ return true;
+ }
+ }
+ return false;
+}
+
+static int cache_op_size(void)
+{
+#ifdef __powerpc64__
+ return ppc64_caches.l1d.block_size;
+#else
+ return L1_CACHE_BYTES;
+#endif
+}
+
+void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr,
+ int *type, int *size, unsigned long *ea)
+{
+ struct instruction_op op;
+
+ if (__get_user_instr_inatomic(*instr, (void __user *)regs->nip))
+ return;
+
+ analyse_instr(&op, regs, *instr);
+ *type = GETTYPE(op.type);
+ *ea = op.ea;
+#ifdef __powerpc64__
+ if (!(regs->msr & MSR_64BIT))
+ *ea &= 0xffffffffUL;
+#endif
+
+ *size = GETSIZE(op.type);
+ if (*type == CACHEOP) {
+ *size = cache_op_size();
+ *ea &= ~(*size - 1);
+ } else if (*type == LOAD_VMX || *type == STORE_VMX) {
+ *ea &= ~(*size - 1);
+ }
+}
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index a36fd05..1f83553 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -41,14 +41,6 @@
}
__setup("powersave=off", powersave_off);
-#ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead(void)
-{
- sched_preempt_enable_no_resched();
- cpu_die();
-}
-#endif
-
void arch_cpu_idle(void)
{
ppc64_runlatch_off();
@@ -60,9 +52,9 @@
* interrupts enabled, some don't.
*/
if (irqs_disabled())
- local_irq_enable();
+ raw_local_irq_enable();
} else {
- local_irq_enable();
+ raw_local_irq_enable();
/*
* Go into low thread priority and possibly
* low power mode.
@@ -77,6 +69,31 @@
int powersave_nap;
+#ifdef CONFIG_PPC_970_NAP
+void power4_idle(void)
+{
+ if (!cpu_has_feature(CPU_FTR_CAN_NAP))
+ return;
+
+ if (!powersave_nap)
+ return;
+
+ if (!prep_irq_for_idle())
+ return;
+
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ asm volatile("DSSALL ; sync" ::: "memory");
+
+ power4_idle_nap();
+
+ /*
+ * power4_idle_nap returns with interrupts enabled (soft and hard).
+ * to our caller with interrupts enabled (soft and hard). Our caller
+ * can cope with either interrupts disabled or enabled upon return.
+ */
+}
+#endif
+
#ifdef CONFIG_SYSCTL
/*
* Register the sysctl to set/clear powersave_nap.
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 0ffdd18..69df840 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -166,7 +166,11 @@
mfspr r9,SPRN_HID0
andis. r9,r9,HID0_NAP@h
beq 1f
+#ifdef CONFIG_VMAP_STACK
+ addis r9, r11, nap_save_msscr0@ha
+#else
addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha
+#endif
lwz r9,nap_save_msscr0@l(r9)
mtspr SPRN_MSSCR0, r9
sync
@@ -174,11 +178,16 @@
1:
END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
BEGIN_FTR_SECTION
+#ifdef CONFIG_VMAP_STACK
+ addis r9, r11, nap_save_hid1@ha
+#else
addis r9,r11,(nap_save_hid1-KERNELBASE)@ha
+#endif
lwz r9,nap_save_hid1@l(r9)
mtspr SPRN_HID1, r9
END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
b transfer_to_handler_cont
+_ASM_NOKPROBE_SYMBOL(power_save_ppc32_restore)
.data
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index d327519..b16aeca 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -15,7 +15,9 @@
#include <asm/asm-offsets.h>
#include <asm/ppc-opcode.h>
#include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
+#ifdef CONFIG_PPC_P7_NAP
/*
* Desired PSSCR in r3
*
@@ -50,28 +52,32 @@
std r1,PACAR1(r13)
mflr r4
mfcr r5
- /* use stack red zone rather than a new frame for saving regs */
- std r2,-8*0(r1)
- std r14,-8*1(r1)
- std r15,-8*2(r1)
- std r16,-8*3(r1)
- std r17,-8*4(r1)
- std r18,-8*5(r1)
- std r19,-8*6(r1)
- std r20,-8*7(r1)
- std r21,-8*8(r1)
- std r22,-8*9(r1)
- std r23,-8*10(r1)
- std r24,-8*11(r1)
- std r25,-8*12(r1)
- std r26,-8*13(r1)
- std r27,-8*14(r1)
- std r28,-8*15(r1)
- std r29,-8*16(r1)
- std r30,-8*17(r1)
- std r31,-8*18(r1)
- std r4,-8*19(r1)
- std r5,-8*20(r1)
+ /*
+ * Use the stack red zone rather than a new frame for saving regs since
+ * in the case of no GPR loss the wakeup code branches directly back to
+ * the caller without deallocating the stack frame first.
+ */
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
/* 168 bytes */
PPC_STOP
b . /* catch bugs */
@@ -87,8 +93,8 @@
*/
_GLOBAL(idle_return_gpr_loss)
ld r1,PACAR1(r13)
- ld r4,-8*19(r1)
- ld r5,-8*20(r1)
+ ld r4,-8*20(r1)
+ ld r5,-8*21(r1)
mtlr r4
mtcr r5
/*
@@ -96,38 +102,40 @@
* from PACATOC. This could be avoided for that less common case
* if KVM saved its r2.
*/
- ld r2,-8*0(r1)
- ld r14,-8*1(r1)
- ld r15,-8*2(r1)
- ld r16,-8*3(r1)
- ld r17,-8*4(r1)
- ld r18,-8*5(r1)
- ld r19,-8*6(r1)
- ld r20,-8*7(r1)
- ld r21,-8*8(r1)
- ld r22,-8*9(r1)
- ld r23,-8*10(r1)
- ld r24,-8*11(r1)
- ld r25,-8*12(r1)
- ld r26,-8*13(r1)
- ld r27,-8*14(r1)
- ld r28,-8*15(r1)
- ld r29,-8*16(r1)
- ld r30,-8*17(r1)
- ld r31,-8*18(r1)
+ ld r2,-8*1(r1)
+ ld r14,-8*2(r1)
+ ld r15,-8*3(r1)
+ ld r16,-8*4(r1)
+ ld r17,-8*5(r1)
+ ld r18,-8*6(r1)
+ ld r19,-8*7(r1)
+ ld r20,-8*8(r1)
+ ld r21,-8*9(r1)
+ ld r22,-8*10(r1)
+ ld r23,-8*11(r1)
+ ld r24,-8*12(r1)
+ ld r25,-8*13(r1)
+ ld r26,-8*14(r1)
+ ld r27,-8*15(r1)
+ ld r28,-8*16(r1)
+ ld r29,-8*17(r1)
+ ld r30,-8*18(r1)
+ ld r31,-8*19(r1)
blr
/*
* This is the sequence required to execute idle instructions, as
* specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
- *
- * The 0(r1) slot is used to save r2 in isa206, so use that here.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
*/
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
- std r2,0(r1); \
+ std r2,-8(r1); \
ptesync; \
- ld r2,0(r1); \
+ ld r2,-8(r1); \
236: cmpd cr0,r2,r2; \
bne 236b; \
IDLE_INST; \
@@ -152,28 +160,32 @@
std r1,PACAR1(r13)
mflr r4
mfcr r5
- /* use stack red zone rather than a new frame for saving regs */
- std r2,-8*0(r1)
- std r14,-8*1(r1)
- std r15,-8*2(r1)
- std r16,-8*3(r1)
- std r17,-8*4(r1)
- std r18,-8*5(r1)
- std r19,-8*6(r1)
- std r20,-8*7(r1)
- std r21,-8*8(r1)
- std r22,-8*9(r1)
- std r23,-8*10(r1)
- std r24,-8*11(r1)
- std r25,-8*12(r1)
- std r26,-8*13(r1)
- std r27,-8*14(r1)
- std r28,-8*15(r1)
- std r29,-8*16(r1)
- std r30,-8*17(r1)
- std r31,-8*18(r1)
- std r4,-8*19(r1)
- std r5,-8*20(r1)
+ /*
+ * Use the stack red zone rather than a new frame for saving regs since
+ * in the case of no GPR loss the wakeup code branches directly back to
+ * the caller without deallocating the stack frame first.
+ */
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
cmpwi r3,PNV_THREAD_NAP
bne 1f
IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
@@ -181,4 +193,22 @@
bne 2f
IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
2: IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+ LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+ ld r9,PACA_THREAD_INFO(r13)
+ ld r8,TI_LOCAL_FLAGS(r9)
+ ori r8,r8,_TLF_NAPPING
+ std r8,TI_LOCAL_FLAGS(r9)
+ /*
+ * NAPPING bit is set, from this point onward power4_fixup_nap
+ * will cause exceptions to return to power4_idle_nap_return.
+ */
+1: sync
+ isync
+ mtmsrd r7
+ isync
+ b 1b
+#endif
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 308f499..72c85b6 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -90,3 +90,4 @@
#endif
b transfer_to_handler_cont
+_ASM_NOKPROBE_SYMBOL(power_save_ppc32_restore)
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
deleted file mode 100644
index 33c6253..0000000
--- a/arch/powerpc/kernel/idle_power4.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This file contains the power_save function for 970-family CPUs.
- */
-
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/feature-fixups.h>
-
-#undef DEBUG
-
- .text
-
-_GLOBAL(power4_idle)
-BEGIN_FTR_SECTION
- blr
-END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
- /* Now check if user or arch enabled NAP mode */
- LOAD_REG_ADDRBASE(r3,powersave_nap)
- lwz r4,ADDROFF(powersave_nap)(r3)
- cmpwi 0,r4,0
- beqlr
-
- /* This sequence is similar to prep_irq_for_idle() */
-
- /* Hard disable interrupts */
- mfmsr r7
- rldicl r0,r7,48,1
- rotldi r0,r0,16
- mtmsrd r0,1
-
- /* Check if something happened while soft-disabled */
- lbz r0,PACAIRQHAPPENED(r13)
- cmpwi cr0,r0,0
- bne- 2f
-
- /*
- * Soft-enable interrupts. This will make power4_fixup_nap return
- * to our caller with interrupts enabled (soft and hard). The caller
- * can cope with either interrupts disabled or enabled upon return.
- */
-#ifdef CONFIG_TRACE_IRQFLAGS
- /* Tell the tracer interrupts are on, because idle responds to them. */
- mflr r0
- std r0,16(r1)
- stdu r1,-128(r1)
- bl trace_hardirqs_on
- addi r1,r1,128
- ld r0,16(r1)
- mtlr r0
- mfmsr r7
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
- li r0,IRQS_ENABLED
- stb r0,PACAIRQSOFTMASK(r13) /* we'll hard-enable shortly */
-BEGIN_FTR_SECTION
- DSSALL
- sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- ld r9, PACA_THREAD_INFO(r13)
- ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
- ori r8,r8,_TLF_NAPPING /* so when we take an exception */
- std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
- ori r7,r7,MSR_EE
- oris r7,r7,MSR_POW@h
-1: sync
- isync
- mtmsrd r7
- isync
- b 1b
-
-2: /* Return if an interrupt had happened while soft disabled */
- /* Set the HARD_DIS flag because interrupts are now hard disabled */
- ori r0,r0,PACA_IRQ_HARD_DIS
- stb r0,PACAIRQHAPPENED(r13)
- blr
diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c
new file mode 100644
index 0000000..957abd5
--- /dev/null
+++ b/arch/powerpc/kernel/ima_arch.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ */
+
+#include <linux/ima.h>
+#include <asm/secure_boot.h>
+
+bool arch_ima_get_secureboot(void)
+{
+ return is_ppc_secureboot_enabled();
+}
+
+/*
+ * The "secure_rules" are enabled only on "secureboot" enabled systems.
+ * These rules verify the file signatures against known good values.
+ * The "appraise_type=imasig|modsig" option allows the known good signature
+ * to be stored as an xattr or as an appended signature.
+ *
+ * To avoid duplicate signature verification as much as possible, the IMA
+ * policy rule for module appraisal is added only if CONFIG_MODULE_SIG
+ * is not enabled.
+ */
+static const char *const secure_rules[] = {
+ "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+#ifndef CONFIG_MODULE_SIG
+ "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+#endif
+ NULL
+};
+
+/*
+ * The "trusted_rules" are enabled only on "trustedboot" enabled systems.
+ * These rules add the kexec kernel image and kernel modules file hashes to
+ * the IMA measurement list.
+ */
+static const char *const trusted_rules[] = {
+ "measure func=KEXEC_KERNEL_CHECK",
+ "measure func=MODULE_CHECK",
+ NULL
+};
+
+/*
+ * The "secure_and_trusted_rules" contains rules for both the secure boot and
+ * trusted boot. The "template=ima-modsig" option includes the appended
+ * signature, when available, in the IMA measurement list.
+ */
+static const char *const secure_and_trusted_rules[] = {
+ "measure func=KEXEC_KERNEL_CHECK template=ima-modsig",
+ "measure func=MODULE_CHECK template=ima-modsig",
+ "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+#ifndef CONFIG_MODULE_SIG
+ "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+#endif
+ NULL
+};
+
+/*
+ * Returns the relevant IMA arch-specific policies based on the system secure
+ * boot state.
+ */
+const char *const *arch_get_ima_policy(void)
+{
+ if (is_ppc_secureboot_enabled()) {
+ if (IS_ENABLED(CONFIG_MODULE_SIG))
+ set_module_sig_enforced();
+
+ if (is_ppc_trustedboot_enabled())
+ return secure_and_trusted_rules;
+ else
+ return secure_rules;
+ } else if (is_ppc_trustedboot_enabled()) {
+ return trusted_rules;
+ }
+
+ return NULL;
+}
diff --git a/arch/powerpc/kernel/ima_kexec.c b/arch/powerpc/kernel/ima_kexec.c
deleted file mode 100644
index 720e50e..0000000
--- a/arch/powerpc/kernel/ima_kexec.c
+++ /dev/null
@@ -1,219 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2016 IBM Corporation
- *
- * Authors:
- * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
- */
-
-#include <linux/slab.h>
-#include <linux/kexec.h>
-#include <linux/of.h>
-#include <linux/memblock.h>
-#include <linux/libfdt.h>
-
-static int get_addr_size_cells(int *addr_cells, int *size_cells)
-{
- struct device_node *root;
-
- root = of_find_node_by_path("/");
- if (!root)
- return -EINVAL;
-
- *addr_cells = of_n_addr_cells(root);
- *size_cells = of_n_size_cells(root);
-
- of_node_put(root);
-
- return 0;
-}
-
-static int do_get_kexec_buffer(const void *prop, int len, unsigned long *addr,
- size_t *size)
-{
- int ret, addr_cells, size_cells;
-
- ret = get_addr_size_cells(&addr_cells, &size_cells);
- if (ret)
- return ret;
-
- if (len < 4 * (addr_cells + size_cells))
- return -ENOENT;
-
- *addr = of_read_number(prop, addr_cells);
- *size = of_read_number(prop + 4 * addr_cells, size_cells);
-
- return 0;
-}
-
-/**
- * ima_get_kexec_buffer - get IMA buffer from the previous kernel
- * @addr: On successful return, set to point to the buffer contents.
- * @size: On successful return, set to the buffer size.
- *
- * Return: 0 on success, negative errno on error.
- */
-int ima_get_kexec_buffer(void **addr, size_t *size)
-{
- int ret, len;
- unsigned long tmp_addr;
- size_t tmp_size;
- const void *prop;
-
- prop = of_get_property(of_chosen, "linux,ima-kexec-buffer", &len);
- if (!prop)
- return -ENOENT;
-
- ret = do_get_kexec_buffer(prop, len, &tmp_addr, &tmp_size);
- if (ret)
- return ret;
-
- *addr = __va(tmp_addr);
- *size = tmp_size;
-
- return 0;
-}
-
-/**
- * ima_free_kexec_buffer - free memory used by the IMA buffer
- */
-int ima_free_kexec_buffer(void)
-{
- int ret;
- unsigned long addr;
- size_t size;
- struct property *prop;
-
- prop = of_find_property(of_chosen, "linux,ima-kexec-buffer", NULL);
- if (!prop)
- return -ENOENT;
-
- ret = do_get_kexec_buffer(prop->value, prop->length, &addr, &size);
- if (ret)
- return ret;
-
- ret = of_remove_property(of_chosen, prop);
- if (ret)
- return ret;
-
- return memblock_free(addr, size);
-
-}
-
-/**
- * remove_ima_buffer - remove the IMA buffer property and reservation from @fdt
- *
- * The IMA measurement buffer is of no use to a subsequent kernel, so we always
- * remove it from the device tree.
- */
-void remove_ima_buffer(void *fdt, int chosen_node)
-{
- int ret, len;
- unsigned long addr;
- size_t size;
- const void *prop;
-
- prop = fdt_getprop(fdt, chosen_node, "linux,ima-kexec-buffer", &len);
- if (!prop)
- return;
-
- ret = do_get_kexec_buffer(prop, len, &addr, &size);
- fdt_delprop(fdt, chosen_node, "linux,ima-kexec-buffer");
- if (ret)
- return;
-
- ret = delete_fdt_mem_rsv(fdt, addr, size);
- if (!ret)
- pr_debug("Removed old IMA buffer reservation.\n");
-}
-
-#ifdef CONFIG_IMA_KEXEC
-/**
- * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA buffer
- *
- * Architectures should use this function to pass on the IMA buffer
- * information to the next kernel.
- *
- * Return: 0 on success, negative errno on error.
- */
-int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
- size_t size)
-{
- image->arch.ima_buffer_addr = load_addr;
- image->arch.ima_buffer_size = size;
-
- return 0;
-}
-
-static int write_number(void *p, u64 value, int cells)
-{
- if (cells == 1) {
- u32 tmp;
-
- if (value > U32_MAX)
- return -EINVAL;
-
- tmp = cpu_to_be32(value);
- memcpy(p, &tmp, sizeof(tmp));
- } else if (cells == 2) {
- u64 tmp;
-
- tmp = cpu_to_be64(value);
- memcpy(p, &tmp, sizeof(tmp));
- } else
- return -EINVAL;
-
- return 0;
-}
-
-/**
- * setup_ima_buffer - add IMA buffer information to the fdt
- * @image: kexec image being loaded.
- * @fdt: Flattened device tree for the next kernel.
- * @chosen_node: Offset to the chosen node.
- *
- * Return: 0 on success, or negative errno on error.
- */
-int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node)
-{
- int ret, addr_cells, size_cells, entry_size;
- u8 value[16];
-
- remove_ima_buffer(fdt, chosen_node);
- if (!image->arch.ima_buffer_size)
- return 0;
-
- ret = get_addr_size_cells(&addr_cells, &size_cells);
- if (ret)
- return ret;
-
- entry_size = 4 * (addr_cells + size_cells);
-
- if (entry_size > sizeof(value))
- return -EINVAL;
-
- ret = write_number(value, image->arch.ima_buffer_addr, addr_cells);
- if (ret)
- return ret;
-
- ret = write_number(value + 4 * addr_cells, image->arch.ima_buffer_size,
- size_cells);
- if (ret)
- return ret;
-
- ret = fdt_setprop(fdt, chosen_node, "linux,ima-kexec-buffer", value,
- entry_size);
- if (ret < 0)
- return -EINVAL;
-
- ret = fdt_add_mem_rsv(fdt, image->arch.ima_buffer_addr,
- image->arch.ima_buffer_size);
- if (ret)
- return -EINVAL;
-
- pr_debug("IMA buffer at 0x%llx, size = 0x%zx\n",
- image->arch.ima_buffer_addr, image->arch.ima_buffer_size);
-
- return 0;
-}
-#endif /* CONFIG_IMA_KEXEC */
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 0276bc8..51bbaae 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -10,10 +10,10 @@
#include <linux/kernel.h>
#include <linux/sched/mm.h> /* for init_mm */
+#include <linux/pgtable.h>
#include <asm/io.h>
#include <asm/machdep.h>
-#include <asm/pgtable.h>
#include <asm/ppc-pci.h>
#include <asm/io-workarounds.h>
#include <asm/pte-walk.h>
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 5ac84ef..9fe4fb3 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -15,23 +15,23 @@
* Here comes the ppc64 implementation of the IOMAP
* interfaces.
*/
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
{
return readb(addr);
}
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
{
return readw(addr);
}
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
{
return readw_be(addr);
}
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
{
return readl(addr);
}
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
{
return readl_be(addr);
}
@@ -41,27 +41,27 @@
EXPORT_SYMBOL(ioread32);
EXPORT_SYMBOL(ioread32be);
#ifdef __powerpc64__
-u64 ioread64(void __iomem *addr)
+u64 ioread64(const void __iomem *addr)
{
return readq(addr);
}
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
{
return readq(addr);
}
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
{
return readq(addr);
}
-u64 ioread64be(void __iomem *addr)
+u64 ioread64be(const void __iomem *addr)
{
return readq_be(addr);
}
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
{
return readq_be(addr);
}
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
{
return readq_be(addr);
}
@@ -139,15 +139,15 @@
* FIXME! We could make these do EEH handling if we really
* wanted. Not clear if we do.
*/
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
{
readsb(addr, dst, count);
}
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
{
readsw(addr, dst, count);
}
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
{
readsl(addr, dst, count);
}
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d7d42bd..6806eef 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -172,7 +172,6 @@
int largealloc = npages > 15;
int pass = 0;
unsigned long align_mask;
- unsigned long boundary_size;
unsigned long flags;
unsigned int pool_nr;
struct iommu_pool *pool;
@@ -236,15 +235,9 @@
}
}
- if (dev)
- boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
- 1 << tbl->it_page_shift);
- else
- boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
- /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
-
n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
- boundary_size >> tbl->it_page_shift, align_mask);
+ dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+ align_mask);
if (n == -1) {
if (likely(pass == 0)) {
/* First try the pool from the start */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index add6749..e8a5484 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -50,10 +50,11 @@
#include <linux/debugfs.h>
#include <linux/of.h>
#include <linux/of_irq.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
#include <linux/uaccess.h>
#include <asm/io.h>
-#include <asm/pgtable.h>
#include <asm/irq.h>
#include <asm/cache.h>
#include <asm/prom.h>
@@ -69,6 +70,7 @@
#include <asm/paca.h>
#include <asm/firmware.h>
#include <asm/lv1call.h>
+#include <asm/dbell.h>
#endif
#define CREATE_TRACE_POINTS
#include <asm/trace.h>
@@ -100,16 +102,10 @@
return happened;
}
-static inline notrace int decrementer_check_overflow(void)
-{
- u64 now = get_tb_or_rtc();
- u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
-
- return now >= *next_tb;
-}
+#ifdef CONFIG_PPC_BOOK3E
/* This is called whenever we are re-enabling interrupts
- * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
+ * and returns either 0 (nothing to do) or 500/900/280 if
* there's an EE, DEC or DBELL to generate.
*
* This is called in two contexts: From arch_local_irq_restore()
@@ -138,34 +134,71 @@
trace_hardirqs_on();
trace_hardirqs_off();
- /*
- * We are always hard disabled here, but PACA_IRQ_HARD_DIS may
- * not be set, which means interrupts have only just been hard
- * disabled as part of the local_irq_restore or interrupt return
- * code. In that case, skip the decrementr check becaus it's
- * expensive to read the TB.
- *
- * HARD_DIS then gets cleared here, but it's reconciled later.
- * Either local_irq_disable will replay the interrupt and that
- * will reconcile state like other hard interrupts. Or interrupt
- * retur will replay the interrupt and in that case it sets
- * PACA_IRQ_HARD_DIS by hand (see comments in entry_64.S).
- */
- if (happened & PACA_IRQ_HARD_DIS) {
+ if (happened & PACA_IRQ_DEC) {
+ local_paca->irq_happened &= ~PACA_IRQ_DEC;
+ return 0x900;
+ }
+
+ if (happened & PACA_IRQ_EE) {
+ local_paca->irq_happened &= ~PACA_IRQ_EE;
+ return 0x500;
+ }
+
+ if (happened & PACA_IRQ_DBELL) {
+ local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+ return 0x280;
+ }
+
+ if (happened & PACA_IRQ_HARD_DIS)
local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
- /*
- * We may have missed a decrementer interrupt if hard disabled.
- * Check the decrementer register in case we had a rollover
- * while hard disabled.
- */
- if (!(happened & PACA_IRQ_DEC)) {
- if (decrementer_check_overflow()) {
- local_paca->irq_happened |= PACA_IRQ_DEC;
- happened |= PACA_IRQ_DEC;
- }
- }
- }
+ /* There should be nothing left ! */
+ BUG_ON(local_paca->irq_happened != 0);
+
+ return 0;
+}
+
+/*
+ * This is specifically called by assembly code to re-enable interrupts
+ * if they are currently disabled. This is typically called before
+ * schedule() or do_signal() when returning to userspace. We do it
+ * in C to avoid the burden of dealing with lockdep etc...
+ *
+ * NOTE: This is called with interrupts hard disabled but not marked
+ * as such in paca->irq_happened, so we need to resync this.
+ */
+void notrace restore_interrupts(void)
+{
+ if (irqs_disabled()) {
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ local_irq_enable();
+ } else
+ __hard_irq_enable();
+}
+
+#endif /* CONFIG_PPC_BOOK3E */
+
+void replay_soft_interrupts(void)
+{
+ struct pt_regs regs;
+
+ /*
+ * Be careful here, calling these interrupt handlers can cause
+ * softirqs to be raised, which they may run when calling irq_exit,
+ * which will cause local_irq_enable() to be run, which can then
+ * recurse into this function. Don't keep any state across
+ * interrupt handler calls which may change underneath us.
+ *
+ * We use local_paca rather than get_paca() to avoid all the
+ * debug_smp_processor_id() business in this low level function.
+ */
+
+ ppc_save_regs(®s);
+ regs.softe = IRQS_ENABLED;
+
+again:
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
/*
* Force the delivery of pending soft-disabled interrupts on PS3.
@@ -181,58 +214,89 @@
* This is a higher priority interrupt than the others, so
* replay it first.
*/
- if (happened & PACA_IRQ_HMI) {
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) {
local_paca->irq_happened &= ~PACA_IRQ_HMI;
- return 0xe60;
+ regs.trap = 0xe60;
+ handle_hmi_exception(®s);
+ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+ hard_irq_disable();
}
- if (happened & PACA_IRQ_DEC) {
+ if (local_paca->irq_happened & PACA_IRQ_DEC) {
local_paca->irq_happened &= ~PACA_IRQ_DEC;
- return 0x900;
+ regs.trap = 0x900;
+ timer_interrupt(®s);
+ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+ hard_irq_disable();
}
- if (happened & PACA_IRQ_PMI) {
- local_paca->irq_happened &= ~PACA_IRQ_PMI;
- return 0xf00;
- }
-
- if (happened & PACA_IRQ_EE) {
+ if (local_paca->irq_happened & PACA_IRQ_EE) {
local_paca->irq_happened &= ~PACA_IRQ_EE;
- return 0x500;
+ regs.trap = 0x500;
+ do_IRQ(®s);
+ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+ hard_irq_disable();
}
-#ifdef CONFIG_PPC_BOOK3E
- /*
- * Check if an EPR external interrupt happened this bit is typically
- * set if we need to handle another "edge" interrupt from within the
- * MPIC "EPR" handler.
- */
- if (happened & PACA_IRQ_EE_EDGE) {
- local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
- return 0x500;
- }
-
- if (happened & PACA_IRQ_DBELL) {
+ if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) {
local_paca->irq_happened &= ~PACA_IRQ_DBELL;
- return 0x280;
+ if (IS_ENABLED(CONFIG_PPC_BOOK3E))
+ regs.trap = 0x280;
+ else
+ regs.trap = 0xa00;
+ doorbell_exception(®s);
+ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+ hard_irq_disable();
}
-#else
- if (happened & PACA_IRQ_DBELL) {
- local_paca->irq_happened &= ~PACA_IRQ_DBELL;
- return 0xa00;
+
+ /* Book3E does not support soft-masking PMI interrupts */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) {
+ local_paca->irq_happened &= ~PACA_IRQ_PMI;
+ regs.trap = 0xf00;
+ performance_monitor_exception(®s);
+ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+ hard_irq_disable();
}
-#endif /* CONFIG_PPC_BOOK3E */
- /* There should be nothing left ! */
- BUG_ON(local_paca->irq_happened != 0);
-
- return 0;
+ if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) {
+ /*
+ * We are responding to the next interrupt, so interrupt-off
+ * latencies should be reset here.
+ */
+ trace_hardirqs_on();
+ trace_hardirqs_off();
+ goto again;
+ }
}
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+static inline void replay_soft_interrupts_irqrestore(void)
+{
+ unsigned long kuap_state = get_kuap();
+
+ /*
+ * Check if anything calls local_irq_enable/restore() when KUAP is
+ * disabled (user access enabled). We handle that case here by saving
+ * and re-locking AMR but we shouldn't get here in the first place,
+ * hence the warning.
+ */
+ kuap_check_amr();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(AMR_KUAP_BLOCKED);
+
+ replay_soft_interrupts();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(kuap_state);
+}
+#else
+#define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
+#endif
+
notrace void arch_local_irq_restore(unsigned long mask)
{
unsigned char irq_happened;
- unsigned int replay;
/* Write the new soft-enabled value */
irq_soft_mask_set(mask);
@@ -254,24 +318,17 @@
*/
irq_happened = get_irq_happened();
if (!irq_happened) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
- WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!(mfmsr() & MSR_EE));
return;
}
- /*
- * We need to hard disable to get a trusted value from
- * __check_irq_replay(). We also need to soft-disable
- * again to avoid warnings in there due to the use of
- * per-cpu variables.
- */
+ /* We need to hard disable to replay. */
if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
- WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!(mfmsr() & MSR_EE));
__hard_irq_disable();
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
} else {
/*
* We should already be hard disabled here. We had bugs
@@ -279,58 +336,38 @@
* warn if we are wrong. Only do that when IRQ tracing
* is enabled as mfmsr() can be costly.
*/
- if (WARN_ON_ONCE(mfmsr() & MSR_EE))
- __hard_irq_disable();
-#endif
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+ __hard_irq_disable();
+ }
+
+ if (irq_happened == PACA_IRQ_HARD_DIS) {
+ local_paca->irq_happened = 0;
+ __hard_irq_enable();
+ return;
+ }
}
+ /*
+ * Disable preempt here, so that the below preempt_enable will
+ * perform resched if required (a replayed interrupt may set
+ * need_resched).
+ */
+ preempt_disable();
irq_soft_mask_set(IRQS_ALL_DISABLED);
trace_hardirqs_off();
- /*
- * Check if anything needs to be re-emitted. We haven't
- * soft-enabled yet to avoid warnings in decrementer_check_overflow
- * accessing per-cpu variables
- */
- replay = __check_irq_replay();
+ replay_soft_interrupts_irqrestore();
+ local_paca->irq_happened = 0;
- /* We can soft-enable now */
trace_hardirqs_on();
irq_soft_mask_set(IRQS_ENABLED);
-
- /*
- * And replay if we have to. This will return with interrupts
- * hard-enabled.
- */
- if (replay) {
- __replay_interrupt(replay);
- return;
- }
-
- /* Finally, let's ensure we are hard enabled */
__hard_irq_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(arch_local_irq_restore);
/*
- * This is specifically called by assembly code to re-enable interrupts
- * if they are currently disabled. This is typically called before
- * schedule() or do_signal() when returning to userspace. We do it
- * in C to avoid the burden of dealing with lockdep etc...
- *
- * NOTE: This is called with interrupts hard disabled but not marked
- * as such in paca->irq_happened, so we need to resync this.
- */
-void notrace restore_interrupts(void)
-{
- if (irqs_disabled()) {
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
- local_irq_enable();
- } else
- __hard_irq_enable();
-}
-
-/*
* This is a helper to use when about to go into idle low-power
* when the latter has the side effect of re-enabling interrupts
* (such as calling H_CEDE under pHyp).
@@ -459,6 +496,19 @@
return;
}
+ if (reason == PACA_IRQ_DBELL) {
+ /*
+ * When doorbell triggers a system reset wakeup, the message
+ * is not cleared, so if the doorbell interrupt is replayed
+ * and the IPI handled, the doorbell interrupt would still
+ * fire when EE is enabled.
+ *
+ * To avoid taking the superfluous doorbell interrupt,
+ * execute a msgclr here before the interrupt is replayed.
+ */
+ ppc_msgclr(PPC_DBELL_MSGTYPE);
+ }
+
/*
* The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
* so this can be called unconditionally with the SRR1 wake
@@ -540,13 +590,14 @@
seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
seq_printf(p, " Machine check exceptions\n");
+#ifdef CONFIG_PPC_BOOK3S_64
if (cpu_has_feature(CPU_FTR_HVMODE)) {
seq_printf(p, "%*s: ", prec, "HMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- per_cpu(irq_stat, j).hmi_exceptions);
+ seq_printf(p, "%10u ", paca_ptrs[j]->hmi_irqs);
seq_printf(p, " Hypervisor Maintenance Interrupts\n");
}
+#endif
seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
@@ -584,7 +635,9 @@
sum += per_cpu(irq_stat, cpu).mce_exceptions;
sum += per_cpu(irq_stat, cpu).spurious_irqs;
sum += per_cpu(irq_stat, cpu).timer_irqs_others;
- sum += per_cpu(irq_stat, cpu).hmi_exceptions;
+#ifdef CONFIG_PPC_BOOK3S_64
+ sum += paca_ptrs[cpu]->hmi_irqs;
+#endif
sum += per_cpu(irq_stat, cpu).sreset_irqs;
#ifdef CONFIG_PPC_WATCHDOG
sum += per_cpu(irq_stat, cpu).soft_nmi_irqs;
@@ -598,17 +651,18 @@
static inline void check_stack_overflow(void)
{
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
long sp;
- sp = current_stack_pointer() & (THREAD_SIZE-1);
+ if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW))
+ return;
+
+ sp = current_stack_pointer & (THREAD_SIZE - 1);
/* check for stack overflow: is there less than 2KB free? */
if (unlikely(sp < 2048)) {
pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
-#endif
}
void __do_irq(struct pt_regs *regs)
@@ -646,7 +700,7 @@
void *cursp, *irqsp, *sirqsp;
/* Switch to the irq stack to handle this */
- cursp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+ cursp = (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
irqsp = hardirq_ctx[raw_smp_processor_id()];
sirqsp = softirq_ctx[raw_smp_processor_id()];
@@ -664,8 +718,28 @@
set_irq_regs(old_regs);
}
+static void *__init alloc_vm_stack(void)
+{
+ return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP,
+ NUMA_NO_NODE, (void *)_RET_IP_);
+}
+
+static void __init vmap_irqstack_init(void)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ softirq_ctx[i] = alloc_vm_stack();
+ hardirq_ctx[i] = alloc_vm_stack();
+ }
+}
+
+
void __init init_IRQ(void)
{
+ if (IS_ENABLED(CONFIG_VMAP_STACK))
+ vmap_irqstack_init();
+
if (ppc_md.init_IRQ)
ppc_md.init_IRQ();
}
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 773671b..2257d24 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -18,6 +18,7 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
+#include <linux/vmalloc.h>
#include <asm/processor.h>
#include <asm/io.h>
@@ -38,6 +39,22 @@
#define ISA_SPACE_MASK 0x1
#define ISA_SPACE_IO 0x1
+static void remap_isa_base(phys_addr_t pa, unsigned long size)
+{
+ WARN_ON_ONCE(ISA_IO_BASE & ~PAGE_MASK);
+ WARN_ON_ONCE(pa & ~PAGE_MASK);
+ WARN_ON_ONCE(size & ~PAGE_MASK);
+
+ if (slab_is_available()) {
+ if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+ pgprot_noncached(PAGE_KERNEL)))
+ unmap_kernel_range(ISA_IO_BASE, size);
+ } else {
+ early_ioremap_range(ISA_IO_BASE, pa, size,
+ pgprot_noncached(PAGE_KERNEL));
+ }
+}
+
static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
unsigned long phb_io_base_phys)
{
@@ -105,15 +122,13 @@
if (size > 0x10000)
size = 0x10000;
- __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
- size, pgprot_noncached(PAGE_KERNEL));
+ remap_isa_base(phb_io_base_phys, size);
return;
inval_range:
printk(KERN_ERR "no ISA IO ranges or unexpected isa range, "
"mapping 64k\n");
- __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
- 0x10000, pgprot_noncached(PAGE_KERNEL));
+ remap_isa_base(phb_io_base_phys, 0x10000);
}
@@ -248,8 +263,7 @@
* and map it
*/
isa_io_base = ISA_IO_BASE;
- __ioremap_at(pbase, (void *)ISA_IO_BASE,
- size, pgprot_noncached(PAGE_KERNEL));
+ remap_isa_base(pbase, size);
pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
}
@@ -297,7 +311,7 @@
isa_bridge_pcidev = NULL;
/* Unmap the ISA area */
- __iounmap_at((void *)ISA_IO_BASE, 0x10000);
+ unmap_kernel_range(ISA_IO_BASE, 0x10000);
}
/**
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index ca37702..1448580 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -6,14 +6,15 @@
#include <linux/kernel.h>
#include <linux/jump_label.h>
#include <asm/code-patching.h>
+#include <asm/inst.h>
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- u32 *addr = (u32 *)(unsigned long)entry->code;
+ struct ppc_inst *addr = (struct ppc_inst *)(unsigned long)entry->code;
if (type == JUMP_LABEL_JMP)
patch_branch(addr, entry->target, 0);
else
- patch_instruction(addr, PPC_INST_NOP);
+ patch_instruction(addr, ppc_inst(PPC_INST_NOP));
}
diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c
deleted file mode 100644
index 3072fd6..0000000
--- a/arch/powerpc/kernel/kexec_elf_64.c
+++ /dev/null
@@ -1,125 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Load ELF vmlinux file for the kexec_file_load syscall.
- *
- * Copyright (C) 2004 Adam Litke (agl@us.ibm.com)
- * Copyright (C) 2004 IBM Corp.
- * Copyright (C) 2005 R Sharada (sharada@in.ibm.com)
- * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com)
- * Copyright (C) 2016 IBM Corporation
- *
- * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c.
- * Heavily modified for the kernel by
- * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
- */
-
-#define pr_fmt(fmt) "kexec_elf: " fmt
-
-#include <linux/elf.h>
-#include <linux/kexec.h>
-#include <linux/libfdt.h>
-#include <linux/module.h>
-#include <linux/of_fdt.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-
-static void *elf64_load(struct kimage *image, char *kernel_buf,
- unsigned long kernel_len, char *initrd,
- unsigned long initrd_len, char *cmdline,
- unsigned long cmdline_len)
-{
- int ret;
- unsigned int fdt_size;
- unsigned long kernel_load_addr;
- unsigned long initrd_load_addr = 0, fdt_load_addr;
- void *fdt;
- const void *slave_code;
- struct elfhdr ehdr;
- struct kexec_elf_info elf_info;
- struct kexec_buf kbuf = { .image = image, .buf_min = 0,
- .buf_max = ppc64_rma_size };
- struct kexec_buf pbuf = { .image = image, .buf_min = 0,
- .buf_max = ppc64_rma_size, .top_down = true,
- .mem = KEXEC_BUF_MEM_UNKNOWN };
-
- ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info);
- if (ret)
- goto out;
-
- ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr);
- if (ret)
- goto out;
-
- pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr);
-
- ret = kexec_load_purgatory(image, &pbuf);
- if (ret) {
- pr_err("Loading purgatory failed.\n");
- goto out;
- }
-
- pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
-
- if (initrd != NULL) {
- kbuf.buffer = initrd;
- kbuf.bufsz = kbuf.memsz = initrd_len;
- kbuf.buf_align = PAGE_SIZE;
- kbuf.top_down = false;
- kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
- ret = kexec_add_buffer(&kbuf);
- if (ret)
- goto out;
- initrd_load_addr = kbuf.mem;
-
- pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr);
- }
-
- fdt_size = fdt_totalsize(initial_boot_params) * 2;
- fdt = kmalloc(fdt_size, GFP_KERNEL);
- if (!fdt) {
- pr_err("Not enough memory for the device tree.\n");
- ret = -ENOMEM;
- goto out;
- }
- ret = fdt_open_into(initial_boot_params, fdt, fdt_size);
- if (ret < 0) {
- pr_err("Error setting up the new device tree.\n");
- ret = -EINVAL;
- goto out;
- }
-
- ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
- if (ret)
- goto out;
-
- fdt_pack(fdt);
-
- kbuf.buffer = fdt;
- kbuf.bufsz = kbuf.memsz = fdt_size;
- kbuf.buf_align = PAGE_SIZE;
- kbuf.top_down = true;
- kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
- ret = kexec_add_buffer(&kbuf);
- if (ret)
- goto out;
- fdt_load_addr = kbuf.mem;
-
- pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr);
-
- slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset;
- ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr,
- fdt_load_addr);
- if (ret)
- pr_err("Error setting up the purgatory.\n");
-
-out:
- kexec_free_elf_info(&elf_info);
-
- /* Make kimage_file_post_load_cleanup free the fdt buffer for us. */
- return ret ? ERR_PTR(ret) : fdt;
-}
-
-const struct kexec_file_ops kexec_elf64_ops = {
- .probe = kexec_elf_probe,
- .load = elf64_load,
-};
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 7dd55eb..4090802 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -26,6 +26,7 @@
#include <asm/debug.h>
#include <asm/code-patching.h>
#include <linux/slab.h>
+#include <asm/inst.h>
/*
* This table contains the mapping between PowerPC hardware trap types, and
@@ -418,13 +419,13 @@
{
int err;
unsigned int instr;
- unsigned int *addr = (unsigned int *)bpt->bpt_addr;
+ struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
- err = probe_kernel_address(addr, instr);
+ err = get_kernel_nofault(instr, (unsigned *) addr);
if (err)
return err;
- err = patch_instruction(addr, BREAK_INSTR);
+ err = patch_instruction(addr, ppc_inst(BREAK_INSTR));
if (err)
return -EFAULT;
@@ -437,9 +438,9 @@
{
int err;
unsigned int instr = *(unsigned int *)bpt->saved_instr;
- unsigned int *addr = (unsigned int *)bpt->bpt_addr;
+ struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
- err = patch_instruction(addr, instr);
+ err = patch_instruction(addr, ppc_inst(instr));
if (err)
return -EFAULT;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index dd01a4a..00fafc8 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -23,6 +23,7 @@
#include <asm/cacheflush.h>
#include <asm/sstep.h>
#include <asm/sections.h>
+#include <asm/inst.h>
#include <linux/uaccess.h>
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -105,7 +106,8 @@
int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
- kprobe_opcode_t insn = *p->addr;
+ struct kprobe *prev;
+ struct ppc_inst insn = ppc_inst_read((struct ppc_inst *)p->addr);
if ((unsigned long)p->addr & 0x03) {
printk("Attempt to register kprobe at an unaligned address\n");
@@ -113,6 +115,18 @@
} else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) {
printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n");
ret = -EINVAL;
+ } else if ((unsigned long)p->addr & ~PAGE_MASK &&
+ ppc_inst_prefixed(ppc_inst_read((struct ppc_inst *)(p->addr - 1)))) {
+ printk("Cannot register a kprobe on the second word of prefixed instruction\n");
+ ret = -EINVAL;
+ }
+ preempt_disable();
+ prev = get_kprobe(p->addr - 1);
+ preempt_enable_no_resched();
+ if (prev &&
+ ppc_inst_prefixed(ppc_inst_read((struct ppc_inst *)prev->ainsn.insn))) {
+ printk("Cannot register a kprobe on the second word of prefixed instruction\n");
+ ret = -EINVAL;
}
/* insn must be on a special executable page on ppc64. This is
@@ -124,11 +138,8 @@
}
if (!ret) {
- memcpy(p->ainsn.insn, p->addr,
- MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
- p->opcode = *p->addr;
- flush_icache_range((unsigned long)p->ainsn.insn,
- (unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
+ patch_instruction((struct ppc_inst *)p->ainsn.insn, insn);
+ p->opcode = ppc_inst_val(insn);
}
p->ainsn.boostable = 0;
@@ -138,13 +149,13 @@
void arch_arm_kprobe(struct kprobe *p)
{
- patch_instruction(p->addr, BREAKPOINT_INSTRUCTION);
+ patch_instruction((struct ppc_inst *)p->addr, ppc_inst(BREAKPOINT_INSTRUCTION));
}
NOKPROBE_SYMBOL(arch_arm_kprobe);
void arch_disarm_kprobe(struct kprobe *p)
{
- patch_instruction(p->addr, p->opcode);
+ patch_instruction((struct ppc_inst *)p->addr, ppc_inst(p->opcode));
}
NOKPROBE_SYMBOL(arch_disarm_kprobe);
@@ -207,6 +218,7 @@
void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *)regs->link;
+ ri->fp = NULL;
/* Replace the return addr with trampoline addr */
regs->link = (unsigned long)kretprobe_trampoline;
@@ -216,7 +228,7 @@
static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
{
int ret;
- unsigned int insn = *p->ainsn.insn;
+ struct ppc_inst insn = ppc_inst_read((struct ppc_inst *)p->ainsn.insn);
/* regs->nip is also adjusted if emulate_step returns 1 */
ret = emulate_step(regs, insn);
@@ -233,7 +245,7 @@
* So, we should never get here... but, its still
* good to catch them, just in case...
*/
- printk("Can't step on instruction %x\n", insn);
+ printk("Can't step on instruction %s\n", ppc_inst_as_str(insn));
BUG();
} else {
/*
@@ -275,64 +287,20 @@
preempt_disable();
kcb = get_kprobe_ctlblk();
- /* Check we're not actually recursing */
- if (kprobe_running()) {
- p = get_kprobe(addr);
- if (p) {
- kprobe_opcode_t insn = *p->ainsn.insn;
- if (kcb->kprobe_status == KPROBE_HIT_SS &&
- is_trap(insn)) {
- /* Turn off 'trace' bits */
- regs->msr &= ~MSR_SINGLESTEP;
- regs->msr |= kcb->kprobe_saved_msr;
- goto no_kprobe;
- }
- /* We have reentered the kprobe_handler(), since
- * another probe was hit while within the handler.
- * We here save the original kprobes variables and
- * just single step on the instruction of the new probe
- * without calling any user handlers.
- */
- save_previous_kprobe(kcb);
- set_current_kprobe(p, regs, kcb);
- kprobes_inc_nmissed_count(p);
- kcb->kprobe_status = KPROBE_REENTER;
- if (p->ainsn.boostable >= 0) {
- ret = try_to_emulate(p, regs);
-
- if (ret > 0) {
- restore_previous_kprobe(kcb);
- preempt_enable_no_resched();
- return 1;
- }
- }
- prepare_singlestep(p, regs);
- return 1;
- } else if (*addr != BREAKPOINT_INSTRUCTION) {
- /* If trap variant, then it belongs not to us */
- kprobe_opcode_t cur_insn = *addr;
-
- if (is_trap(cur_insn))
- goto no_kprobe;
- /* The breakpoint instruction was removed by
- * another cpu right after we hit, no further
- * handling of this interrupt is appropriate
- */
- ret = 1;
- }
- goto no_kprobe;
- }
-
p = get_kprobe(addr);
if (!p) {
- if (*addr != BREAKPOINT_INSTRUCTION) {
+ unsigned int instr;
+
+ if (get_kernel_nofault(instr, addr))
+ goto no_kprobe;
+
+ if (instr != BREAKPOINT_INSTRUCTION) {
/*
* PowerPC has multiple variants of the "trap"
* instruction. If the current instruction is a
* trap variant, it could belong to someone else
*/
- kprobe_opcode_t cur_insn = *addr;
- if (is_trap(cur_insn))
+ if (is_trap(instr))
goto no_kprobe;
/*
* The breakpoint instruction was removed right
@@ -347,6 +315,39 @@
goto no_kprobe;
}
+ /* Check we're not actually recursing */
+ if (kprobe_running()) {
+ kprobe_opcode_t insn = *p->ainsn.insn;
+ if (kcb->kprobe_status == KPROBE_HIT_SS && is_trap(insn)) {
+ /* Turn off 'trace' bits */
+ regs->msr &= ~MSR_SINGLESTEP;
+ regs->msr |= kcb->kprobe_saved_msr;
+ goto no_kprobe;
+ }
+
+ /*
+ * We have reentered the kprobe_handler(), since another probe
+ * was hit while within the handler. We here save the original
+ * kprobes variables and just single step on the instruction of
+ * the new probe without calling any user handlers.
+ */
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p, regs, kcb);
+ kprobes_inc_nmissed_count(p);
+ kcb->kprobe_status = KPROBE_REENTER;
+ if (p->ainsn.boostable >= 0) {
+ ret = try_to_emulate(p, regs);
+
+ if (ret > 0) {
+ restore_previous_kprobe(kcb);
+ preempt_enable_no_resched();
+ return 1;
+ }
+ }
+ prepare_singlestep(p, regs);
+ return 1;
+ }
+
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
set_current_kprobe(p, regs, kcb);
if (p->pre_handler && p->pre_handler(p, regs)) {
@@ -397,50 +398,9 @@
*/
static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
{
- struct kretprobe_instance *ri = NULL;
- struct hlist_head *head, empty_rp;
- struct hlist_node *tmp;
- unsigned long flags, orig_ret_address = 0;
- unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+ unsigned long orig_ret_address;
- INIT_HLIST_HEAD(&empty_rp);
- kretprobe_hash_lock(current, &head, &flags);
-
- /*
- * It is possible to have multiple instances associated with a given
- * task either because an multiple functions in the call path
- * have a return probe installed on them, and/or more than one return
- * return probe was registered for a target function.
- *
- * We can handle this because:
- * - instances are always inserted at the head of the list
- * - when multiple return probes are registered for the same
- * function, the first instance's ret_addr will point to the
- * real return address, and all the rest will point to
- * kretprobe_trampoline
- */
- hlist_for_each_entry_safe(ri, tmp, head, hlist) {
- if (ri->task != current)
- /* another task is sharing our hash bucket */
- continue;
-
- if (ri->rp && ri->rp->handler)
- ri->rp->handler(ri, regs);
-
- orig_ret_address = (unsigned long)ri->ret_addr;
- recycle_rp_inst(ri, &empty_rp);
-
- if (orig_ret_address != trampoline_address)
- /*
- * This is the real return address. Any other
- * instances associated with this task are for
- * other calls deeper on the call stack
- */
- break;
- }
-
- kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
+ orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
/*
* We get here through one of two paths:
* 1. by taking a trap -> kprobe_handler() -> here
@@ -459,13 +419,6 @@
regs->nip = orig_ret_address - 4;
regs->link = orig_ret_address;
- kretprobe_hash_unlock(current, &flags);
-
- hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
- hlist_del(&ri->hlist);
- kfree(ri);
- }
-
return 0;
}
NOKPROBE_SYMBOL(trampoline_probe_handler);
@@ -480,14 +433,16 @@
*/
int kprobe_post_handler(struct pt_regs *regs)
{
+ int len;
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (!cur || user_mode(regs))
return 0;
+ len = ppc_inst_len(ppc_inst_read((struct ppc_inst *)cur->ainsn.insn));
/* make sure we got here for instruction we have a kprobe on */
- if (((unsigned long)cur->ainsn.insn + 4) != regs->nip)
+ if (((unsigned long)cur->ainsn.insn + len) != regs->nip)
return 0;
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
@@ -496,7 +451,7 @@
}
/* Adjust nip to after the single-stepped instruction */
- regs->nip = (unsigned long)cur->addr + 4;
+ regs->nip = (unsigned long)cur->addr + len;
regs->msr |= kcb->kprobe_saved_msr;
/*Restore back the original saved kprobes variables and continue. */
diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S
index 2020d25..225511d 100644
--- a/arch/powerpc/kernel/l2cr_6xx.S
+++ b/arch/powerpc/kernel/l2cr_6xx.S
@@ -256,7 +256,6 @@
sync
/* Restore MSR (restores EE and DR bits to original state) */
- SYNC
mtmsr r7
isync
@@ -377,7 +376,7 @@
1: bdnz 1b
/* Restore MSR (restores EE and DR bits to original state) */
-4: SYNC
+4:
mtmsr r7
isync
blr
@@ -455,5 +454,6 @@
sync
blr
+_ASM_NOKPROBE_SYMBOL(__inval_enable_L1)
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 7cea597..f061e06 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -479,8 +479,10 @@
port->irq = virq;
#ifdef CONFIG_SERIAL_8250_FSL
- if (of_device_is_compatible(np, "fsl,ns16550"))
+ if (of_device_is_compatible(np, "fsl,ns16550")) {
port->handle_irq = fsl8250_handle_irq;
+ port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+ }
#endif
}
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
deleted file mode 100644
index 7a1c11a..0000000
--- a/arch/powerpc/kernel/machine_kexec.c
+++ /dev/null
@@ -1,281 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Code to handle transition of Linux booting another kernel.
- *
- * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com>
- * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
- * Copyright (C) 2005 IBM Corporation.
- */
-
-#include <linux/kexec.h>
-#include <linux/reboot.h>
-#include <linux/threads.h>
-#include <linux/memblock.h>
-#include <linux/of.h>
-#include <linux/irq.h>
-#include <linux/ftrace.h>
-
-#include <asm/kdump.h>
-#include <asm/machdep.h>
-#include <asm/pgalloc.h>
-#include <asm/prom.h>
-#include <asm/sections.h>
-
-void machine_kexec_mask_interrupts(void) {
- unsigned int i;
- struct irq_desc *desc;
-
- for_each_irq_desc(i, desc) {
- struct irq_chip *chip;
-
- chip = irq_desc_get_chip(desc);
- if (!chip)
- continue;
-
- if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
- chip->irq_eoi(&desc->irq_data);
-
- if (chip->irq_mask)
- chip->irq_mask(&desc->irq_data);
-
- if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
- chip->irq_disable(&desc->irq_data);
- }
-}
-
-void machine_crash_shutdown(struct pt_regs *regs)
-{
- default_machine_crash_shutdown(regs);
-}
-
-/*
- * Do what every setup is needed on image and the
- * reboot code buffer to allow us to avoid allocations
- * later.
- */
-int machine_kexec_prepare(struct kimage *image)
-{
- if (ppc_md.machine_kexec_prepare)
- return ppc_md.machine_kexec_prepare(image);
- else
- return default_machine_kexec_prepare(image);
-}
-
-void machine_kexec_cleanup(struct kimage *image)
-{
-}
-
-void arch_crash_save_vmcoreinfo(void)
-{
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
- VMCOREINFO_SYMBOL(node_data);
- VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
-#ifndef CONFIG_NEED_MULTIPLE_NODES
- VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
- VMCOREINFO_SYMBOL(vmemmap_list);
- VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
- VMCOREINFO_SYMBOL(mmu_psize_defs);
- VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
- VMCOREINFO_OFFSET(vmemmap_backing, list);
- VMCOREINFO_OFFSET(vmemmap_backing, phys);
- VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
- VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
- VMCOREINFO_OFFSET(mmu_psize_def, shift);
-#endif
-}
-
-/*
- * Do not allocate memory (or fail in any way) in machine_kexec().
- * We are past the point of no return, committed to rebooting now.
- */
-void machine_kexec(struct kimage *image)
-{
- int save_ftrace_enabled;
-
- save_ftrace_enabled = __ftrace_enabled_save();
- this_cpu_disable_ftrace();
-
- if (ppc_md.machine_kexec)
- ppc_md.machine_kexec(image);
- else
- default_machine_kexec(image);
-
- this_cpu_enable_ftrace();
- __ftrace_enabled_restore(save_ftrace_enabled);
-
- /* Fall back to normal restart if we're still alive. */
- machine_restart(NULL);
- for(;;);
-}
-
-void __init reserve_crashkernel(void)
-{
- unsigned long long crash_size, crash_base, total_mem_sz;
- int ret;
-
- total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
- /* use common parsing */
- ret = parse_crashkernel(boot_command_line, total_mem_sz,
- &crash_size, &crash_base);
- if (ret == 0 && crash_size > 0) {
- crashk_res.start = crash_base;
- crashk_res.end = crash_base + crash_size - 1;
- }
-
- if (crashk_res.end == crashk_res.start) {
- crashk_res.start = crashk_res.end = 0;
- return;
- }
-
- /* We might have got these values via the command line or the
- * device tree, either way sanitise them now. */
-
- crash_size = resource_size(&crashk_res);
-
-#ifndef CONFIG_NONSTATIC_KERNEL
- if (crashk_res.start != KDUMP_KERNELBASE)
- printk("Crash kernel location must be 0x%x\n",
- KDUMP_KERNELBASE);
-
- crashk_res.start = KDUMP_KERNELBASE;
-#else
- if (!crashk_res.start) {
-#ifdef CONFIG_PPC64
- /*
- * On 64bit we split the RMO in half but cap it at half of
- * a small SLB (128MB) since the crash kernel needs to place
- * itself and some stacks to be in the first segment.
- */
- crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
-#else
- crashk_res.start = KDUMP_KERNELBASE;
-#endif
- }
-
- crash_base = PAGE_ALIGN(crashk_res.start);
- if (crash_base != crashk_res.start) {
- printk("Crash kernel base must be aligned to 0x%lx\n",
- PAGE_SIZE);
- crashk_res.start = crash_base;
- }
-
-#endif
- crash_size = PAGE_ALIGN(crash_size);
- crashk_res.end = crashk_res.start + crash_size - 1;
-
- /* The crash region must not overlap the current kernel */
- if (overlaps_crashkernel(__pa(_stext), _end - _stext)) {
- printk(KERN_WARNING
- "Crash kernel can not overlap current kernel\n");
- crashk_res.start = crashk_res.end = 0;
- return;
- }
-
- /* Crash kernel trumps memory limit */
- if (memory_limit && memory_limit <= crashk_res.end) {
- memory_limit = crashk_res.end + 1;
- total_mem_sz = memory_limit;
- printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
- memory_limit);
- }
-
- printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
- "for crashkernel (System RAM: %ldMB)\n",
- (unsigned long)(crash_size >> 20),
- (unsigned long)(crashk_res.start >> 20),
- (unsigned long)(total_mem_sz >> 20));
-
- if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
- memblock_reserve(crashk_res.start, crash_size)) {
- pr_err("Failed to reserve memory for crashkernel!\n");
- crashk_res.start = crashk_res.end = 0;
- return;
- }
-}
-
-int overlaps_crashkernel(unsigned long start, unsigned long size)
-{
- return (start + size) > crashk_res.start && start <= crashk_res.end;
-}
-
-/* Values we need to export to the second kernel via the device tree. */
-static phys_addr_t kernel_end;
-static phys_addr_t crashk_base;
-static phys_addr_t crashk_size;
-static unsigned long long mem_limit;
-
-static struct property kernel_end_prop = {
- .name = "linux,kernel-end",
- .length = sizeof(phys_addr_t),
- .value = &kernel_end,
-};
-
-static struct property crashk_base_prop = {
- .name = "linux,crashkernel-base",
- .length = sizeof(phys_addr_t),
- .value = &crashk_base
-};
-
-static struct property crashk_size_prop = {
- .name = "linux,crashkernel-size",
- .length = sizeof(phys_addr_t),
- .value = &crashk_size,
-};
-
-static struct property memory_limit_prop = {
- .name = "linux,memory-limit",
- .length = sizeof(unsigned long long),
- .value = &mem_limit,
-};
-
-#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
-
-static void __init export_crashk_values(struct device_node *node)
-{
- /* There might be existing crash kernel properties, but we can't
- * be sure what's in them, so remove them. */
- of_remove_property(node, of_find_property(node,
- "linux,crashkernel-base", NULL));
- of_remove_property(node, of_find_property(node,
- "linux,crashkernel-size", NULL));
-
- if (crashk_res.start != 0) {
- crashk_base = cpu_to_be_ulong(crashk_res.start),
- of_add_property(node, &crashk_base_prop);
- crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
- of_add_property(node, &crashk_size_prop);
- }
-
- /*
- * memory_limit is required by the kexec-tools to limit the
- * crash regions to the actual memory used.
- */
- mem_limit = cpu_to_be_ulong(memory_limit);
- of_update_property(node, &memory_limit_prop);
-}
-
-static int __init kexec_setup(void)
-{
- struct device_node *node;
-
- node = of_find_node_by_path("/chosen");
- if (!node)
- return -ENOENT;
-
- /* remove any stale properties so ours can be found */
- of_remove_property(node, of_find_property(node, kernel_end_prop.name, NULL));
-
- /* information needed by userspace when using default_machine_kexec */
- kernel_end = cpu_to_be_ulong(__pa(_end));
- of_add_property(node, &kernel_end_prop);
-
- export_crashk_values(node);
-
- of_node_put(node);
- return 0;
-}
-late_initcall(kexec_setup);
diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c
deleted file mode 100644
index bf9f1f9..0000000
--- a/arch/powerpc/kernel/machine_kexec_32.c
+++ /dev/null
@@ -1,69 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * PPC32 code to handle Linux booting another kernel.
- *
- * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com>
- * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
- * Copyright (C) 2005 IBM Corporation.
- */
-
-#include <linux/kexec.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <asm/cacheflush.h>
-#include <asm/hw_irq.h>
-#include <asm/io.h>
-
-typedef void (*relocate_new_kernel_t)(
- unsigned long indirection_page,
- unsigned long reboot_code_buffer,
- unsigned long start_address) __noreturn;
-
-/*
- * This is a generic machine_kexec function suitable at least for
- * non-OpenFirmware embedded platforms.
- * It merely copies the image relocation code to the control page and
- * jumps to it.
- * A platform specific function may just call this one.
- */
-void default_machine_kexec(struct kimage *image)
-{
- extern const unsigned int relocate_new_kernel_size;
- unsigned long page_list;
- unsigned long reboot_code_buffer, reboot_code_buffer_phys;
- relocate_new_kernel_t rnk;
-
- /* Interrupts aren't acceptable while we reboot */
- local_irq_disable();
-
- /* mask each interrupt so we are in a more sane state for the
- * kexec kernel */
- machine_kexec_mask_interrupts();
-
- page_list = image->head;
-
- /* we need both effective and real address here */
- reboot_code_buffer =
- (unsigned long)page_address(image->control_code_page);
- reboot_code_buffer_phys = virt_to_phys((void *)reboot_code_buffer);
-
- /* copy our kernel relocation code to the control code page */
- memcpy((void *)reboot_code_buffer, relocate_new_kernel,
- relocate_new_kernel_size);
-
- flush_icache_range(reboot_code_buffer,
- reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
- printk(KERN_INFO "Bye!\n");
-
- if (!IS_ENABLED(CONFIG_FSL_BOOKE) && !IS_ENABLED(CONFIG_44x))
- relocate_new_kernel(page_list, reboot_code_buffer_phys, image->start);
-
- /* now call it */
- rnk = (relocate_new_kernel_t) reboot_code_buffer;
- (*rnk)(page_list, reboot_code_buffer_phys, image->start);
-}
-
-int default_machine_kexec_prepare(struct kimage *image)
-{
- return 0;
-}
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
deleted file mode 100644
index 04a7cba..0000000
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ /dev/null
@@ -1,417 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * PPC64 code to handle Linux booting another kernel.
- *
- * Copyright (C) 2004-2005, IBM Corp.
- *
- * Created by: Milton D Miller II
- */
-
-
-#include <linux/kexec.h>
-#include <linux/smp.h>
-#include <linux/thread_info.h>
-#include <linux/init_task.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/cpu.h>
-#include <linux/hardirq.h>
-
-#include <asm/page.h>
-#include <asm/current.h>
-#include <asm/machdep.h>
-#include <asm/cacheflush.h>
-#include <asm/firmware.h>
-#include <asm/paca.h>
-#include <asm/mmu.h>
-#include <asm/sections.h> /* _end */
-#include <asm/prom.h>
-#include <asm/smp.h>
-#include <asm/hw_breakpoint.h>
-#include <asm/asm-prototypes.h>
-#include <asm/svm.h>
-#include <asm/ultravisor.h>
-
-int default_machine_kexec_prepare(struct kimage *image)
-{
- int i;
- unsigned long begin, end; /* limits of segment */
- unsigned long low, high; /* limits of blocked memory range */
- struct device_node *node;
- const unsigned long *basep;
- const unsigned int *sizep;
-
- /*
- * Since we use the kernel fault handlers and paging code to
- * handle the virtual mode, we must make sure no destination
- * overlaps kernel static data or bss.
- */
- for (i = 0; i < image->nr_segments; i++)
- if (image->segment[i].mem < __pa(_end))
- return -ETXTBSY;
-
- /* We also should not overwrite the tce tables */
- for_each_node_by_type(node, "pci") {
- basep = of_get_property(node, "linux,tce-base", NULL);
- sizep = of_get_property(node, "linux,tce-size", NULL);
- if (basep == NULL || sizep == NULL)
- continue;
-
- low = *basep;
- high = low + (*sizep);
-
- for (i = 0; i < image->nr_segments; i++) {
- begin = image->segment[i].mem;
- end = begin + image->segment[i].memsz;
-
- if ((begin < high) && (end > low))
- return -ETXTBSY;
- }
- }
-
- return 0;
-}
-
-static void copy_segments(unsigned long ind)
-{
- unsigned long entry;
- unsigned long *ptr;
- void *dest;
- void *addr;
-
- /*
- * We rely on kexec_load to create a lists that properly
- * initializes these pointers before they are used.
- * We will still crash if the list is wrong, but at least
- * the compiler will be quiet.
- */
- ptr = NULL;
- dest = NULL;
-
- for (entry = ind; !(entry & IND_DONE); entry = *ptr++) {
- addr = __va(entry & PAGE_MASK);
-
- switch (entry & IND_FLAGS) {
- case IND_DESTINATION:
- dest = addr;
- break;
- case IND_INDIRECTION:
- ptr = addr;
- break;
- case IND_SOURCE:
- copy_page(dest, addr);
- dest += PAGE_SIZE;
- }
- }
-}
-
-void kexec_copy_flush(struct kimage *image)
-{
- long i, nr_segments = image->nr_segments;
- struct kexec_segment ranges[KEXEC_SEGMENT_MAX];
-
- /* save the ranges on the stack to efficiently flush the icache */
- memcpy(ranges, image->segment, sizeof(ranges));
-
- /*
- * After this call we may not use anything allocated in dynamic
- * memory, including *image.
- *
- * Only globals and the stack are allowed.
- */
- copy_segments(image->head);
-
- /*
- * we need to clear the icache for all dest pages sometime,
- * including ones that were in place on the original copy
- */
- for (i = 0; i < nr_segments; i++)
- flush_icache_range((unsigned long)__va(ranges[i].mem),
- (unsigned long)__va(ranges[i].mem + ranges[i].memsz));
-}
-
-#ifdef CONFIG_SMP
-
-static int kexec_all_irq_disabled = 0;
-
-static void kexec_smp_down(void *arg)
-{
- local_irq_disable();
- hard_irq_disable();
-
- mb(); /* make sure our irqs are disabled before we say they are */
- get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
- while(kexec_all_irq_disabled == 0)
- cpu_relax();
- mb(); /* make sure all irqs are disabled before this */
- hw_breakpoint_disable();
- /*
- * Now every CPU has IRQs off, we can clear out any pending
- * IPIs and be sure that no more will come in after this.
- */
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(0, 1);
-
- kexec_smp_wait();
- /* NOTREACHED */
-}
-
-static void kexec_prepare_cpus_wait(int wait_state)
-{
- int my_cpu, i, notified=-1;
-
- hw_breakpoint_disable();
- my_cpu = get_cpu();
- /* Make sure each CPU has at least made it to the state we need.
- *
- * FIXME: There is a (slim) chance of a problem if not all of the CPUs
- * are correctly onlined. If somehow we start a CPU on boot with RTAS
- * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in
- * time, the boot CPU will timeout. If it does eventually execute
- * stuff, the secondary will start up (paca_ptrs[]->cpu_start was
- * written) and get into a peculiar state.
- * If the platform supports smp_ops->take_timebase(), the secondary CPU
- * will probably be spinning in there. If not (i.e. pseries), the
- * secondary will continue on and try to online itself/idle/etc. If it
- * survives that, we need to find these
- * possible-but-not-online-but-should-be CPUs and chaperone them into
- * kexec_smp_wait().
- */
- for_each_online_cpu(i) {
- if (i == my_cpu)
- continue;
-
- while (paca_ptrs[i]->kexec_state < wait_state) {
- barrier();
- if (i != notified) {
- printk(KERN_INFO "kexec: waiting for cpu %d "
- "(physical %d) to enter %i state\n",
- i, paca_ptrs[i]->hw_cpu_id, wait_state);
- notified = i;
- }
- }
- }
- mb();
-}
-
-/*
- * We need to make sure each present CPU is online. The next kernel will scan
- * the device tree and assume primary threads are online and query secondary
- * threads via RTAS to online them if required. If we don't online primary
- * threads, they will be stuck. However, we also online secondary threads as we
- * may be using 'cede offline'. In this case RTAS doesn't see the secondary
- * threads as offline -- and again, these CPUs will be stuck.
- *
- * So, we online all CPUs that should be running, including secondary threads.
- */
-static void wake_offline_cpus(void)
-{
- int cpu = 0;
-
- for_each_present_cpu(cpu) {
- if (!cpu_online(cpu)) {
- printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
- cpu);
- WARN_ON(cpu_up(cpu));
- }
- }
-}
-
-static void kexec_prepare_cpus(void)
-{
- wake_offline_cpus();
- smp_call_function(kexec_smp_down, NULL, /* wait */0);
- local_irq_disable();
- hard_irq_disable();
-
- mb(); /* make sure IRQs are disabled before we say they are */
- get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
-
- kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
- /* we are sure every CPU has IRQs off at this point */
- kexec_all_irq_disabled = 1;
-
- /*
- * Before removing MMU mappings make sure all CPUs have entered real
- * mode:
- */
- kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
-
- /* after we tell the others to go down */
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(0, 0);
-
- put_cpu();
-}
-
-#else /* ! SMP */
-
-static void kexec_prepare_cpus(void)
-{
- /*
- * move the secondarys to us so that we can copy
- * the new kernel 0-0x100 safely
- *
- * do this if kexec in setup.c ?
- *
- * We need to release the cpus if we are ever going from an
- * UP to an SMP kernel.
- */
- smp_release_cpus();
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(0, 0);
- local_irq_disable();
- hard_irq_disable();
-}
-
-#endif /* SMP */
-
-/*
- * kexec thread structure and stack.
- *
- * We need to make sure that this is 16384-byte aligned due to the
- * way process stacks are handled. It also must be statically allocated
- * or allocated as part of the kimage, because everything else may be
- * overwritten when we copy the kexec image. We piggyback on the
- * "init_task" linker section here to statically allocate a stack.
- *
- * We could use a smaller stack if we don't care about anything using
- * current, but that audit has not been performed.
- */
-static union thread_union kexec_stack __init_task_data =
- { };
-
-/*
- * For similar reasons to the stack above, the kexecing CPU needs to be on a
- * static PACA; we switch to kexec_paca.
- */
-struct paca_struct kexec_paca;
-
-/* Our assembly helper, in misc_64.S */
-extern void kexec_sequence(void *newstack, unsigned long start,
- void *image, void *control,
- void (*clear_all)(void),
- bool copy_with_mmu_off) __noreturn;
-
-/* too late to fail here */
-void default_machine_kexec(struct kimage *image)
-{
- bool copy_with_mmu_off;
-
- /* prepare control code if any */
-
- /*
- * If the kexec boot is the normal one, need to shutdown other cpus
- * into our wait loop and quiesce interrupts.
- * Otherwise, in the case of crashed mode (crashing_cpu >= 0),
- * stopping other CPUs and collecting their pt_regs is done before
- * using debugger IPI.
- */
-
- if (!kdump_in_progress())
- kexec_prepare_cpus();
-
- printk("kexec: Starting switchover sequence.\n");
-
- /* switch to a staticly allocated stack. Based on irq stack code.
- * We setup preempt_count to avoid using VMX in memcpy.
- * XXX: the task struct will likely be invalid once we do the copy!
- */
- current_thread_info()->flags = 0;
- current_thread_info()->preempt_count = HARDIRQ_OFFSET;
-
- /* We need a static PACA, too; copy this CPU's PACA over and switch to
- * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
- * non-static data.
- */
- memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
- kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
-#ifdef CONFIG_PPC_PSERIES
- kexec_paca.lppaca_ptr = NULL;
-#endif
-
- if (is_secure_guest() && !(image->preserve_context ||
- image->type == KEXEC_TYPE_CRASH)) {
- uv_unshare_all_pages();
- printk("kexec: Unshared all shared pages.\n");
- }
-
- paca_ptrs[kexec_paca.paca_index] = &kexec_paca;
-
- setup_paca(&kexec_paca);
-
- /*
- * The lppaca should be unregistered at this point so the HV won't
- * touch it. In the case of a crash, none of the lppacas are
- * unregistered so there is not much we can do about it here.
- */
-
- /*
- * On Book3S, the copy must happen with the MMU off if we are either
- * using Radix page tables or we are not in an LPAR since we can
- * overwrite the page tables while copying.
- *
- * In an LPAR, we keep the MMU on otherwise we can't access beyond
- * the RMA. On BookE there is no real MMU off mode, so we have to
- * keep it enabled as well (but then we have bolted TLB entries).
- */
-#ifdef CONFIG_PPC_BOOK3E
- copy_with_mmu_off = false;
-#else
- copy_with_mmu_off = radix_enabled() ||
- !(firmware_has_feature(FW_FEATURE_LPAR) ||
- firmware_has_feature(FW_FEATURE_PS3_LV1));
-#endif
-
- /* Some things are best done in assembly. Finding globals with
- * a toc is easier in C, so pass in what we can.
- */
- kexec_sequence(&kexec_stack, image->start, image,
- page_address(image->control_code_page),
- mmu_cleanup_all, copy_with_mmu_off);
- /* NOTREACHED */
-}
-
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Values we need to export to the second kernel via the device tree. */
-static unsigned long htab_base;
-static unsigned long htab_size;
-
-static struct property htab_base_prop = {
- .name = "linux,htab-base",
- .length = sizeof(unsigned long),
- .value = &htab_base,
-};
-
-static struct property htab_size_prop = {
- .name = "linux,htab-size",
- .length = sizeof(unsigned long),
- .value = &htab_size,
-};
-
-static int __init export_htab_values(void)
-{
- struct device_node *node;
-
- /* On machines with no htab htab_address is NULL */
- if (!htab_address)
- return -ENODEV;
-
- node = of_find_node_by_path("/chosen");
- if (!node)
- return -ENODEV;
-
- /* remove any stale propertys so ours can be found */
- of_remove_property(node, of_find_property(node, htab_base_prop.name, NULL));
- of_remove_property(node, of_find_property(node, htab_size_prop.name, NULL));
-
- htab_base = cpu_to_be64(__pa(htab_address));
- of_add_property(node, &htab_base_prop);
- htab_size = cpu_to_be64(htab_size_bytes);
- of_add_property(node, &htab_size_prop);
-
- of_node_put(node);
- return 0;
-}
-late_initcall(export_htab_values);
-#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c
deleted file mode 100644
index 143c917..0000000
--- a/arch/powerpc/kernel/machine_kexec_file_64.c
+++ /dev/null
@@ -1,254 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ppc64 code to implement the kexec_file_load syscall
- *
- * Copyright (C) 2004 Adam Litke (agl@us.ibm.com)
- * Copyright (C) 2004 IBM Corp.
- * Copyright (C) 2004,2005 Milton D Miller II, IBM Corporation
- * Copyright (C) 2005 R Sharada (sharada@in.ibm.com)
- * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com)
- * Copyright (C) 2016 IBM Corporation
- *
- * Based on kexec-tools' kexec-elf-ppc64.c, fs2dt.c.
- * Heavily modified for the kernel by
- * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
- */
-
-#include <linux/slab.h>
-#include <linux/kexec.h>
-#include <linux/of_fdt.h>
-#include <linux/libfdt.h>
-#include <asm/ima.h>
-
-#define SLAVE_CODE_SIZE 256
-
-const struct kexec_file_ops * const kexec_file_loaders[] = {
- &kexec_elf64_ops,
- NULL
-};
-
-int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
- unsigned long buf_len)
-{
- /* We don't support crash kernels yet. */
- if (image->type == KEXEC_TYPE_CRASH)
- return -EOPNOTSUPP;
-
- return kexec_image_probe_default(image, buf, buf_len);
-}
-
-/**
- * setup_purgatory - initialize the purgatory's global variables
- * @image: kexec image.
- * @slave_code: Slave code for the purgatory.
- * @fdt: Flattened device tree for the next kernel.
- * @kernel_load_addr: Address where the kernel is loaded.
- * @fdt_load_addr: Address where the flattened device tree is loaded.
- *
- * Return: 0 on success, or negative errno on error.
- */
-int setup_purgatory(struct kimage *image, const void *slave_code,
- const void *fdt, unsigned long kernel_load_addr,
- unsigned long fdt_load_addr)
-{
- unsigned int *slave_code_buf, master_entry;
- int ret;
-
- slave_code_buf = kmalloc(SLAVE_CODE_SIZE, GFP_KERNEL);
- if (!slave_code_buf)
- return -ENOMEM;
-
- /* Get the slave code from the new kernel and put it in purgatory. */
- ret = kexec_purgatory_get_set_symbol(image, "purgatory_start",
- slave_code_buf, SLAVE_CODE_SIZE,
- true);
- if (ret) {
- kfree(slave_code_buf);
- return ret;
- }
-
- master_entry = slave_code_buf[0];
- memcpy(slave_code_buf, slave_code, SLAVE_CODE_SIZE);
- slave_code_buf[0] = master_entry;
- ret = kexec_purgatory_get_set_symbol(image, "purgatory_start",
- slave_code_buf, SLAVE_CODE_SIZE,
- false);
- kfree(slave_code_buf);
-
- ret = kexec_purgatory_get_set_symbol(image, "kernel", &kernel_load_addr,
- sizeof(kernel_load_addr), false);
- if (ret)
- return ret;
- ret = kexec_purgatory_get_set_symbol(image, "dt_offset", &fdt_load_addr,
- sizeof(fdt_load_addr), false);
- if (ret)
- return ret;
-
- return 0;
-}
-
-/**
- * delete_fdt_mem_rsv - delete memory reservation with given address and size
- *
- * Return: 0 on success, or negative errno on error.
- */
-int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
-{
- int i, ret, num_rsvs = fdt_num_mem_rsv(fdt);
-
- for (i = 0; i < num_rsvs; i++) {
- uint64_t rsv_start, rsv_size;
-
- ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size);
- if (ret) {
- pr_err("Malformed device tree.\n");
- return -EINVAL;
- }
-
- if (rsv_start == start && rsv_size == size) {
- ret = fdt_del_mem_rsv(fdt, i);
- if (ret) {
- pr_err("Error deleting device tree reservation.\n");
- return -EINVAL;
- }
-
- return 0;
- }
- }
-
- return -ENOENT;
-}
-
-/*
- * setup_new_fdt - modify /chosen and memory reservation for the next kernel
- * @image: kexec image being loaded.
- * @fdt: Flattened device tree for the next kernel.
- * @initrd_load_addr: Address where the next initrd will be loaded.
- * @initrd_len: Size of the next initrd, or 0 if there will be none.
- * @cmdline: Command line for the next kernel, or NULL if there will
- * be none.
- *
- * Return: 0 on success, or negative errno on error.
- */
-int setup_new_fdt(const struct kimage *image, void *fdt,
- unsigned long initrd_load_addr, unsigned long initrd_len,
- const char *cmdline)
-{
- int ret, chosen_node;
- const void *prop;
-
- /* Remove memory reservation for the current device tree. */
- ret = delete_fdt_mem_rsv(fdt, __pa(initial_boot_params),
- fdt_totalsize(initial_boot_params));
- if (ret == 0)
- pr_debug("Removed old device tree reservation.\n");
- else if (ret != -ENOENT)
- return ret;
-
- chosen_node = fdt_path_offset(fdt, "/chosen");
- if (chosen_node == -FDT_ERR_NOTFOUND) {
- chosen_node = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"),
- "chosen");
- if (chosen_node < 0) {
- pr_err("Error creating /chosen.\n");
- return -EINVAL;
- }
- } else if (chosen_node < 0) {
- pr_err("Malformed device tree: error reading /chosen.\n");
- return -EINVAL;
- }
-
- /* Did we boot using an initrd? */
- prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL);
- if (prop) {
- uint64_t tmp_start, tmp_end, tmp_size;
-
- tmp_start = fdt64_to_cpu(*((const fdt64_t *) prop));
-
- prop = fdt_getprop(fdt, chosen_node, "linux,initrd-end", NULL);
- if (!prop) {
- pr_err("Malformed device tree.\n");
- return -EINVAL;
- }
- tmp_end = fdt64_to_cpu(*((const fdt64_t *) prop));
-
- /*
- * kexec reserves exact initrd size, while firmware may
- * reserve a multiple of PAGE_SIZE, so check for both.
- */
- tmp_size = tmp_end - tmp_start;
- ret = delete_fdt_mem_rsv(fdt, tmp_start, tmp_size);
- if (ret == -ENOENT)
- ret = delete_fdt_mem_rsv(fdt, tmp_start,
- round_up(tmp_size, PAGE_SIZE));
- if (ret == 0)
- pr_debug("Removed old initrd reservation.\n");
- else if (ret != -ENOENT)
- return ret;
-
- /* If there's no new initrd, delete the old initrd's info. */
- if (initrd_len == 0) {
- ret = fdt_delprop(fdt, chosen_node,
- "linux,initrd-start");
- if (ret) {
- pr_err("Error deleting linux,initrd-start.\n");
- return -EINVAL;
- }
-
- ret = fdt_delprop(fdt, chosen_node, "linux,initrd-end");
- if (ret) {
- pr_err("Error deleting linux,initrd-end.\n");
- return -EINVAL;
- }
- }
- }
-
- if (initrd_len) {
- ret = fdt_setprop_u64(fdt, chosen_node,
- "linux,initrd-start",
- initrd_load_addr);
- if (ret < 0)
- goto err;
-
- /* initrd-end is the first address after the initrd image. */
- ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-end",
- initrd_load_addr + initrd_len);
- if (ret < 0)
- goto err;
-
- ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len);
- if (ret) {
- pr_err("Error reserving initrd memory: %s\n",
- fdt_strerror(ret));
- return -EINVAL;
- }
- }
-
- if (cmdline != NULL) {
- ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline);
- if (ret < 0)
- goto err;
- } else {
- ret = fdt_delprop(fdt, chosen_node, "bootargs");
- if (ret && ret != -FDT_ERR_NOTFOUND) {
- pr_err("Error deleting bootargs.\n");
- return -EINVAL;
- }
- }
-
- ret = setup_ima_buffer(image, fdt, chosen_node);
- if (ret) {
- pr_err("Error setting up the new device tree.\n");
- return ret;
- }
-
- ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
- if (ret)
- goto err;
-
- return 0;
-
-err:
- pr_err("Error setting up the new device tree.\n");
- return -EINVAL;
-}
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 34c1001..63702c0 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -15,6 +15,8 @@
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/irq_work.h>
+#include <linux/extable.h>
+#include <linux/ftrace.h>
#include <asm/machdep.h>
#include <asm/mce.h>
@@ -47,6 +49,20 @@
DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_register_notifier);
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_notifier);
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
@@ -251,6 +267,19 @@
/* Queue irq work to process this event later. */
irq_work_queue(&mce_event_process_work);
}
+
+void mce_common_process_ue(struct pt_regs *regs,
+ struct mce_error_info *mce_err)
+{
+ const struct exception_table_entry *entry;
+
+ entry = search_kernel_exception_table(regs->nip);
+ if (entry) {
+ mce_err->ignore_event = true;
+ regs->nip = extable_fixup(entry);
+ }
+}
+
/*
* process pending MCE event from the mce event queue. This function will be
* called during syscall exit.
@@ -263,6 +292,7 @@
while (__this_cpu_read(mce_ue_count) > 0) {
index = __this_cpu_read(mce_ue_count) - 1;
evt = this_cpu_ptr(&mce_ue_event_queue[index]);
+ blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
#ifdef CONFIG_MEMORY_FAILURE
/*
* This should probably queued elsewhere, but
@@ -355,6 +385,7 @@
static const char *mc_user_types[] = {
"Indeterminate",
"tlbie(l) invalid",
+ "scv invalid",
};
static const char *mc_ra_types[] = {
"Indeterminate",
@@ -557,9 +588,15 @@
*
* regs->nip and regs->msr contains srr0 and ssr1.
*/
-long machine_check_early(struct pt_regs *regs)
+long notrace machine_check_early(struct pt_regs *regs)
{
long handled = 0;
+ u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
+
+ this_cpu_set_ftrace_enabled(0);
+ /* Do not use nmi_enter/exit for pseries hpte guest */
+ if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
+ nmi_enter();
hv_nmi_check_nonrecoverable(regs);
@@ -568,6 +605,12 @@
*/
if (ppc_md.machine_check_early)
handled = ppc_md.machine_check_early(regs);
+
+ if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
+ nmi_exit();
+
+ this_cpu_set_ftrace_enabled(ftrace_enabled);
+
return handled;
}
@@ -683,7 +726,7 @@
{
int ret;
- __this_cpu_inc(irq_stat.hmi_exceptions);
+ local_paca->hmi_irqs++;
ret = hmi_handle_debugtrig(regs);
if (ret >= 0)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 1cbf7f1..ea8b002 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -12,14 +12,15 @@
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/extable.h>
+#include <linux/pgtable.h>
#include <asm/mmu.h>
#include <asm/mce.h>
#include <asm/machdep.h>
-#include <asm/pgtable.h>
#include <asm/pte-walk.h>
#include <asm/sstep.h>
#include <asm/exception-64s.h>
#include <asm/extable.h>
+#include <asm/inst.h>
/*
* Convert an address related to an mm to a PFN. NOTE: we are in real
@@ -27,7 +28,7 @@
*/
unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
{
- pte_t *ptep;
+ pte_t *ptep, pte;
unsigned int shift;
unsigned long pfn, flags;
struct mm_struct *mm;
@@ -39,19 +40,23 @@
local_irq_save(flags);
ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
+ if (!ptep) {
+ pfn = ULONG_MAX;
+ goto out;
+ }
+ pte = READ_ONCE(*ptep);
- if (!ptep || pte_special(*ptep)) {
+ if (!pte_present(pte) || pte_special(pte)) {
pfn = ULONG_MAX;
goto out;
}
if (shift <= PAGE_SHIFT)
- pfn = pte_pfn(*ptep);
+ pfn = pte_pfn(pte);
else {
unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
- pfn = pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
+ pfn = pte_pfn(__pte(pte_val(pte) | (addr & rpnmask)));
}
-
out:
local_irq_restore(flags);
return pfn;
@@ -238,6 +243,45 @@
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, 0, 0, 0, 0, 0, 0 } };
+static const struct mce_ierror_table mce_p10_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008080000, true,
+ MCE_ERROR_TYPE_USER,MCE_USER_ERROR_SCV, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
struct mce_derror_table {
unsigned long dsisr_value;
bool dar_valid; /* dar is a valid indicator of faulting address */
@@ -356,6 +400,46 @@
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, false, 0, 0, 0, 0, 0 } };
+static const struct mce_derror_table mce_p10_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
uint64_t *phys_addr)
{
@@ -365,7 +449,7 @@
* in real-mode is tricky and can lead to recursive
* faults
*/
- int instr;
+ struct ppc_inst instr;
unsigned long pfn, instr_addr;
struct instruction_op op;
struct pt_regs tmp = *regs;
@@ -373,7 +457,7 @@
pfn = addr_to_pfn(regs, regs->nip);
if (pfn != ULONG_MAX) {
instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
- instr = *(unsigned int *)(instr_addr);
+ instr = ppc_inst_read((struct ppc_inst *)instr_addr);
if (!analyse_instr(&op, &tmp, instr)) {
pfn = addr_to_pfn(regs, op.ea);
*addr = op.ea;
@@ -391,12 +475,11 @@
return -1;
}
-static int mce_handle_ierror(struct pt_regs *regs,
+static int mce_handle_ierror(struct pt_regs *regs, unsigned long srr1,
const struct mce_ierror_table table[],
struct mce_error_info *mce_err, uint64_t *addr,
uint64_t *phys_addr)
{
- uint64_t srr1 = regs->msr;
int handled = 0;
int i;
@@ -579,14 +662,10 @@
struct mce_error_info *mce_err)
{
long handled = 0;
- const struct exception_table_entry *entry;
- entry = search_kernel_exception_table(regs->nip);
- if (entry) {
- mce_err->ignore_event = true;
- regs->nip = extable_fixup(entry);
+ mce_common_process_ue(regs, mce_err);
+ if (mce_err->ignore_event)
return 1;
- }
/*
* On specific SCOM read via MMIO we may get a machine check
@@ -603,19 +682,19 @@
}
static long mce_handle_error(struct pt_regs *regs,
+ unsigned long srr1,
const struct mce_derror_table dtable[],
const struct mce_ierror_table itable[])
{
struct mce_error_info mce_err = { 0 };
uint64_t addr, phys_addr = ULONG_MAX;
- uint64_t srr1 = regs->msr;
long handled;
if (SRR1_MC_LOADSTORE(srr1))
handled = mce_handle_derror(regs, dtable, &mce_err, &addr,
&phys_addr);
else
- handled = mce_handle_ierror(regs, itable, &mce_err, &addr,
+ handled = mce_handle_ierror(regs, srr1, itable, &mce_err, &addr,
&phys_addr);
if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
@@ -631,16 +710,20 @@
/* P7 DD1 leaves top bits of DSISR undefined */
regs->dsisr &= 0x0000ffff;
- return mce_handle_error(regs, mce_p7_derror_table, mce_p7_ierror_table);
+ return mce_handle_error(regs, regs->msr,
+ mce_p7_derror_table, mce_p7_ierror_table);
}
long __machine_check_early_realmode_p8(struct pt_regs *regs)
{
- return mce_handle_error(regs, mce_p8_derror_table, mce_p8_ierror_table);
+ return mce_handle_error(regs, regs->msr,
+ mce_p8_derror_table, mce_p8_ierror_table);
}
long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
+ unsigned long srr1 = regs->msr;
+
/*
* On POWER9 DD2.1 and below, it's possible to get a machine check
* caused by a paste instruction where only DSISR bit 25 is set. This
@@ -654,5 +737,39 @@
if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
return 1;
- return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
+ /*
+ * Async machine check due to bad real address from store or foreign
+ * link time out comes with the load/store bit (PPC bit 42) set in
+ * SRR1, but the cause comes in SRR1 not DSISR. Clear bit 42 so we're
+ * directed to the ierror table so it will find the cause (which
+ * describes it correctly as a store error).
+ */
+ if (SRR1_MC_LOADSTORE(srr1) &&
+ ((srr1 & 0x081c0000) == 0x08140000 ||
+ (srr1 & 0x081c0000) == 0x08180000)) {
+ srr1 &= ~PPC_BIT(42);
+ }
+
+ return mce_handle_error(regs, srr1,
+ mce_p9_derror_table, mce_p9_ierror_table);
+}
+
+long __machine_check_early_realmode_p10(struct pt_regs *regs)
+{
+ unsigned long srr1 = regs->msr;
+
+ /*
+ * Async machine check due to bad real address from store comes with
+ * the load/store bit (PPC bit 42) set in SRR1, but the cause comes in
+ * SRR1 not DSISR. Clear bit 42 so we're directed to the ierror table
+ * so it will find the cause (which describes it correctly as a store
+ * error).
+ */
+ if (SRR1_MC_LOADSTORE(srr1) &&
+ (srr1 & 0x081c0000) == 0x08140000) {
+ srr1 &= ~PPC_BIT(42);
+ }
+
+ return mce_handle_error(regs, srr1,
+ mce_p10_derror_table, mce_p10_ierror_table);
}
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 974f65f..5be96fe 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -36,6 +36,8 @@
add r3,r3,r5
mtlr r0
blr
+_ASM_NOKPROBE_SYMBOL(reloc_offset)
+_ASM_NOKPROBE_SYMBOL(add_reloc_offset)
.align 3
2: PPC_LONG 1b
@@ -110,7 +112,7 @@
li r3, 1
blr
-_GLOBAL(current_stack_pointer)
+_GLOBAL(current_stack_frame)
PPC_LL r3,0(r1)
blr
-EXPORT_SYMBOL(current_stack_pointer)
+EXPORT_SYMBOL(current_stack_frame)
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index f4e4a19..717e658 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -6,11 +6,6 @@
* Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
* and Paul Mackerras.
*
- * kexec bits:
- * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com>
- * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
- * PPC44x port. Copyright (C) 2011, IBM Corporation
- * Author: Suzuki Poulose <suzuki@in.ibm.com>
*/
#include <linux/sys.h>
@@ -25,7 +20,6 @@
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm/processor.h>
-#include <asm/kexec.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
#include <asm/export.h>
@@ -221,19 +215,6 @@
#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */
-/*
- * complement mask on the msr then "or" some values on.
- * _nmask_and_or_msr(nmask, value_to_or)
- */
-_GLOBAL(_nmask_and_or_msr)
- mfmsr r0 /* Get current msr */
- andc r0,r0,r3 /* And off the bits set in r3 (first parm) */
- or r0,r0,r4 /* Or on the bits in r4 (second parm) */
- SYNC /* Some chip revs have problems here... */
- mtmsr r0 /* Update machine state */
- isync
- blr /* Done */
-
#ifdef CONFIG_40x
/*
@@ -252,6 +233,7 @@
sync
isync
blr
+_ASM_NOKPROBE_SYMBOL(real_readb)
/*
* Do an IO access in real mode
@@ -269,53 +251,10 @@
sync
isync
blr
+_ASM_NOKPROBE_SYMBOL(real_writeb)
#endif /* CONFIG_40x */
-
-/*
- * Flush instruction cache.
- * This is a no-op on the 601.
- */
-#ifndef CONFIG_PPC_8xx
-_GLOBAL(flush_instruction_cache)
-#if defined(CONFIG_4xx)
-#ifdef CONFIG_403GCX
- li r3, 512
- mtctr r3
- lis r4, KERNELBASE@h
-1: iccci 0, r4
- addi r4, r4, 16
- bdnz 1b
-#else
- lis r3, KERNELBASE@h
- iccci 0,r3
-#endif
-#elif defined(CONFIG_FSL_BOOKE)
-#ifdef CONFIG_E200
- mfspr r3,SPRN_L1CSR0
- ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC
- /* msync; isync recommended here */
- mtspr SPRN_L1CSR0,r3
- isync
- blr
-#endif
- mfspr r3,SPRN_L1CSR1
- ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR
- mtspr SPRN_L1CSR1,r3
-#elif defined(CONFIG_PPC_BOOK3S_601)
- blr /* for 601, do nothing */
-#else
- /* 603/604 processor - use invalidate-all bit in HID0 */
- mfspr r3,SPRN_HID0
- ori r3,r3,HID0_ICFI
- mtspr SPRN_HID0,r3
-#endif /* CONFIG_4xx */
- isync
- blr
-EXPORT_SYMBOL(flush_instruction_cache)
-#endif /* CONFIG_PPC_8xx */
-
/*
* Copy a whole page. We use the dcbz instruction on the destination
* to reduce memory traffic (it eliminates the unnecessary reads of
@@ -494,488 +433,3 @@
*/
_GLOBAL(__main)
blr
-
-#ifdef CONFIG_KEXEC_CORE
- /*
- * Must be relocatable PIC code callable as a C function.
- */
- .globl relocate_new_kernel
-relocate_new_kernel:
- /* r3 = page_list */
- /* r4 = reboot_code_buffer */
- /* r5 = start_address */
-
-#ifdef CONFIG_FSL_BOOKE
-
- mr r29, r3
- mr r30, r4
- mr r31, r5
-
-#define ENTRY_MAPPING_KEXEC_SETUP
-#include "fsl_booke_entry_mapping.S"
-#undef ENTRY_MAPPING_KEXEC_SETUP
-
- mr r3, r29
- mr r4, r30
- mr r5, r31
-
- li r0, 0
-#elif defined(CONFIG_44x)
-
- /* Save our parameters */
- mr r29, r3
- mr r30, r4
- mr r31, r5
-
-#ifdef CONFIG_PPC_47x
- /* Check for 47x cores */
- mfspr r3,SPRN_PVR
- srwi r3,r3,16
- cmplwi cr0,r3,PVR_476FPE@h
- beq setup_map_47x
- cmplwi cr0,r3,PVR_476@h
- beq setup_map_47x
- cmplwi cr0,r3,PVR_476_ISS@h
- beq setup_map_47x
-#endif /* CONFIG_PPC_47x */
-
-/*
- * Code for setting up 1:1 mapping for PPC440x for KEXEC
- *
- * We cannot switch off the MMU on PPC44x.
- * So we:
- * 1) Invalidate all the mappings except the one we are running from.
- * 2) Create a tmp mapping for our code in the other address space(TS) and
- * jump to it. Invalidate the entry we started in.
- * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS.
- * 4) Jump to the 1:1 mapping in original TS.
- * 5) Invalidate the tmp mapping.
- *
- * - Based on the kexec support code for FSL BookE
- *
- */
-
- /*
- * Load the PID with kernel PID (0).
- * Also load our MSR_IS and TID to MMUCR for TLB search.
- */
- li r3, 0
- mtspr SPRN_PID, r3
- mfmsr r4
- andi. r4,r4,MSR_IS@l
- beq wmmucr
- oris r3,r3,PPC44x_MMUCR_STS@h
-wmmucr:
- mtspr SPRN_MMUCR,r3
- sync
-
- /*
- * Invalidate all the TLB entries except the current entry
- * where we are running from
- */
- bl 0f /* Find our address */
-0: mflr r5 /* Make it accessible */
- tlbsx r23,0,r5 /* Find entry we are in */
- li r4,0 /* Start at TLB entry 0 */
- li r3,0 /* Set PAGEID inval value */
-1: cmpw r23,r4 /* Is this our entry? */
- beq skip /* If so, skip the inval */
- tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */
-skip:
- addi r4,r4,1 /* Increment */
- cmpwi r4,64 /* Are we done? */
- bne 1b /* If not, repeat */
- isync
-
- /* Create a temp mapping and jump to it */
- andi. r6, r23, 1 /* Find the index to use */
- addi r24, r6, 1 /* r24 will contain 1 or 2 */
-
- mfmsr r9 /* get the MSR */
- rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */
- xori r7, r5, 1 /* Use the other address space */
-
- /* Read the current mapping entries */
- tlbre r3, r23, PPC44x_TLB_PAGEID
- tlbre r4, r23, PPC44x_TLB_XLAT
- tlbre r5, r23, PPC44x_TLB_ATTRIB
-
- /* Save our current XLAT entry */
- mr r25, r4
-
- /* Extract the TLB PageSize */
- li r10, 1 /* r10 will hold PageSize */
- rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */
-
- /* XXX: As of now we use 256M, 4K pages */
- cmpwi r11, PPC44x_TLB_256M
- bne tlb_4k
- rotlwi r10, r10, 28 /* r10 = 256M */
- b write_out
-tlb_4k:
- cmpwi r11, PPC44x_TLB_4K
- bne default
- rotlwi r10, r10, 12 /* r10 = 4K */
- b write_out
-default:
- rotlwi r10, r10, 10 /* r10 = 1K */
-
-write_out:
- /*
- * Write out the tmp 1:1 mapping for this code in other address space
- * Fixup EPN = RPN , TS=other address space
- */
- insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */
-
- /* Write out the tmp mapping entries */
- tlbwe r3, r24, PPC44x_TLB_PAGEID
- tlbwe r4, r24, PPC44x_TLB_XLAT
- tlbwe r5, r24, PPC44x_TLB_ATTRIB
-
- subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */
- not r10, r11 /* Mask for PageNum */
-
- /* Switch to other address space in MSR */
- insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */
-
- bl 1f
-1: mflr r8
- addi r8, r8, (2f-1b) /* Find the target offset */
-
- /* Jump to the tmp mapping */
- mtspr SPRN_SRR0, r8
- mtspr SPRN_SRR1, r9
- rfi
-
-2:
- /* Invalidate the entry we were executing from */
- li r3, 0
- tlbwe r3, r23, PPC44x_TLB_PAGEID
-
- /* attribute fields. rwx for SUPERVISOR mode */
- li r5, 0
- ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
-
- /* Create 1:1 mapping in 256M pages */
- xori r7, r7, 1 /* Revert back to Original TS */
-
- li r8, 0 /* PageNumber */
- li r6, 3 /* TLB Index, start at 3 */
-
-next_tlb:
- rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */
- mr r4, r3 /* RPN = EPN */
- ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */
- insrwi r3, r7, 1, 23 /* Set TS from r7 */
-
- tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */
- tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */
- tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */
-
- addi r8, r8, 1 /* Increment PN */
- addi r6, r6, 1 /* Increment TLB Index */
- cmpwi r8, 8 /* Are we done ? */
- bne next_tlb
- isync
-
- /* Jump to the new mapping 1:1 */
- li r9,0
- insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */
-
- bl 1f
-1: mflr r8
- and r8, r8, r11 /* Get our offset within page */
- addi r8, r8, (2f-1b)
-
- and r5, r25, r10 /* Get our target PageNum */
- or r8, r8, r5 /* Target jump address */
-
- mtspr SPRN_SRR0, r8
- mtspr SPRN_SRR1, r9
- rfi
-2:
- /* Invalidate the tmp entry we used */
- li r3, 0
- tlbwe r3, r24, PPC44x_TLB_PAGEID
- sync
- b ppc44x_map_done
-
-#ifdef CONFIG_PPC_47x
-
- /* 1:1 mapping for 47x */
-
-setup_map_47x:
-
- /*
- * Load the kernel pid (0) to PID and also to MMUCR[TID].
- * Also set the MSR IS->MMUCR STS
- */
- li r3, 0
- mtspr SPRN_PID, r3 /* Set PID */
- mfmsr r4 /* Get MSR */
- andi. r4, r4, MSR_IS@l /* TS=1? */
- beq 1f /* If not, leave STS=0 */
- oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */
-1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */
- sync
-
- /* Find the entry we are running from */
- bl 2f
-2: mflr r23
- tlbsx r23, 0, r23
- tlbre r24, r23, 0 /* TLB Word 0 */
- tlbre r25, r23, 1 /* TLB Word 1 */
- tlbre r26, r23, 2 /* TLB Word 2 */
-
-
- /*
- * Invalidates all the tlb entries by writing to 256 RPNs(r4)
- * of 4k page size in all 4 ways (0-3 in r3).
- * This would invalidate the entire UTLB including the one we are
- * running from. However the shadow TLB entries would help us
- * to continue the execution, until we flush them (rfi/isync).
- */
- addis r3, 0, 0x8000 /* specify the way */
- addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */
- addi r5, 0, 0
- b clear_utlb_entry
-
- /* Align the loop to speed things up. from head_44x.S */
- .align 6
-
-clear_utlb_entry:
-
- tlbwe r4, r3, 0
- tlbwe r5, r3, 1
- tlbwe r5, r3, 2
- addis r3, r3, 0x2000 /* Increment the way */
- cmpwi r3, 0
- bne clear_utlb_entry
- addis r3, 0, 0x8000
- addis r4, r4, 0x100 /* Increment the EPN */
- cmpwi r4, 0
- bne clear_utlb_entry
-
- /* Create the entries in the other address space */
- mfmsr r5
- rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */
- xori r7, r7, 1 /* r7 = !TS */
-
- insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */
-
- /*
- * write out the TLB entries for the tmp mapping
- * Use way '0' so that we could easily invalidate it later.
- */
- lis r3, 0x8000 /* Way '0' */
-
- tlbwe r24, r3, 0
- tlbwe r25, r3, 1
- tlbwe r26, r3, 2
-
- /* Update the msr to the new TS */
- insrwi r5, r7, 1, 26
-
- bl 1f
-1: mflr r6
- addi r6, r6, (2f-1b)
-
- mtspr SPRN_SRR0, r6
- mtspr SPRN_SRR1, r5
- rfi
-
- /*
- * Now we are in the tmp address space.
- * Create a 1:1 mapping for 0-2GiB in the original TS.
- */
-2:
- li r3, 0
- li r4, 0 /* TLB Word 0 */
- li r5, 0 /* TLB Word 1 */
- li r6, 0
- ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */
-
- li r8, 0 /* PageIndex */
-
- xori r7, r7, 1 /* revert back to original TS */
-
-write_utlb:
- rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */
- /* ERPN = 0 as we don't use memory above 2G */
-
- mr r4, r5 /* EPN = RPN */
- ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M)
- insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */
-
- tlbwe r4, r3, 0 /* Write out the entries */
- tlbwe r5, r3, 1
- tlbwe r6, r3, 2
- addi r8, r8, 1
- cmpwi r8, 8 /* Have we completed ? */
- bne write_utlb
-
- /* make sure we complete the TLB write up */
- isync
-
- /*
- * Prepare to jump to the 1:1 mapping.
- * 1) Extract page size of the tmp mapping
- * DSIZ = TLB_Word0[22:27]
- * 2) Calculate the physical address of the address
- * to jump to.
- */
- rlwinm r10, r24, 0, 22, 27
-
- cmpwi r10, PPC47x_TLB0_4K
- bne 0f
- li r10, 0x1000 /* r10 = 4k */
- bl 1f
-
-0:
- /* Defaults to 256M */
- lis r10, 0x1000
-
- bl 1f
-1: mflr r4
- addi r4, r4, (2f-1b) /* virtual address of 2f */
-
- subi r11, r10, 1 /* offsetmask = Pagesize - 1 */
- not r10, r11 /* Pagemask = ~(offsetmask) */
-
- and r5, r25, r10 /* Physical page */
- and r6, r4, r11 /* offset within the current page */
-
- or r5, r5, r6 /* Physical address for 2f */
-
- /* Switch the TS in MSR to the original one */
- mfmsr r8
- insrwi r8, r7, 1, 26
-
- mtspr SPRN_SRR1, r8
- mtspr SPRN_SRR0, r5
- rfi
-
-2:
- /* Invalidate the tmp mapping */
- lis r3, 0x8000 /* Way '0' */
-
- clrrwi r24, r24, 12 /* Clear the valid bit */
- tlbwe r24, r3, 0
- tlbwe r25, r3, 1
- tlbwe r26, r3, 2
-
- /* Make sure we complete the TLB write and flush the shadow TLB */
- isync
-
-#endif
-
-ppc44x_map_done:
-
-
- /* Restore the parameters */
- mr r3, r29
- mr r4, r30
- mr r5, r31
-
- li r0, 0
-#else
- li r0, 0
-
- /*
- * Set Machine Status Register to a known status,
- * switch the MMU off and jump to 1: in a single step.
- */
-
- mr r8, r0
- ori r8, r8, MSR_RI|MSR_ME
- mtspr SPRN_SRR1, r8
- addi r8, r4, 1f - relocate_new_kernel
- mtspr SPRN_SRR0, r8
- sync
- rfi
-
-1:
-#endif
- /* from this point address translation is turned off */
- /* and interrupts are disabled */
-
- /* set a new stack at the bottom of our page... */
- /* (not really needed now) */
- addi r1, r4, KEXEC_CONTROL_PAGE_SIZE - 8 /* for LR Save+Back Chain */
- stw r0, 0(r1)
-
- /* Do the copies */
- li r6, 0 /* checksum */
- mr r0, r3
- b 1f
-
-0: /* top, read another word for the indirection page */
- lwzu r0, 4(r3)
-
-1:
- /* is it a destination page? (r8) */
- rlwinm. r7, r0, 0, 31, 31 /* IND_DESTINATION (1<<0) */
- beq 2f
-
- rlwinm r8, r0, 0, 0, 19 /* clear kexec flags, page align */
- b 0b
-
-2: /* is it an indirection page? (r3) */
- rlwinm. r7, r0, 0, 30, 30 /* IND_INDIRECTION (1<<1) */
- beq 2f
-
- rlwinm r3, r0, 0, 0, 19 /* clear kexec flags, page align */
- subi r3, r3, 4
- b 0b
-
-2: /* are we done? */
- rlwinm. r7, r0, 0, 29, 29 /* IND_DONE (1<<2) */
- beq 2f
- b 3f
-
-2: /* is it a source page? (r9) */
- rlwinm. r7, r0, 0, 28, 28 /* IND_SOURCE (1<<3) */
- beq 0b
-
- rlwinm r9, r0, 0, 0, 19 /* clear kexec flags, page align */
-
- li r7, PAGE_SIZE / 4
- mtctr r7
- subi r9, r9, 4
- subi r8, r8, 4
-9:
- lwzu r0, 4(r9) /* do the copy */
- xor r6, r6, r0
- stwu r0, 4(r8)
- dcbst 0, r8
- sync
- icbi 0, r8
- bdnz 9b
-
- addi r9, r9, 4
- addi r8, r8, 4
- b 0b
-
-3:
-
- /* To be certain of avoiding problems with self-modifying code
- * execute a serializing instruction here.
- */
- isync
- sync
-
- mfspr r3, SPRN_PIR /* current core we are running on */
- mr r4, r5 /* load physical address of chunk called */
-
- /* jump to the entry point, usually the setup routine */
- mtlr r5
- blrl
-
-1: b 1b
-
-relocate_new_kernel_end:
-
- .globl relocate_new_kernel_size
-relocate_new_kernel_size:
- .long relocate_new_kernel_end - relocate_new_kernel
-#endif
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ff20c25..0704658 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -330,18 +330,13 @@
rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */
/* Set up a temp identity mapping v:0 to p:0 and return to it. */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
mtspr SPRN_MAS0,r9
lis r9,(MAS1_VALID|MAS1_IPROT)@h
ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
mtspr SPRN_MAS1,r9
- LOAD_REG_IMMEDIATE(r9, 0x0 | M_IF_NEEDED)
+ LOAD_REG_IMMEDIATE(r9, 0x0 | MAS2_M_IF_NEEDED)
mtspr SPRN_MAS2,r9
LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX)
@@ -370,7 +365,6 @@
li r4,KEXEC_STATE_REAL_MODE
stb r4,PACAKEXECSTATE(r13)
- SYNC
b kexec_wait
@@ -418,20 +412,6 @@
li r0,0
std r0,16(r1)
-BEGIN_FTR_SECTION
- /*
- * This is the best time to turn AMR/IAMR off.
- * key 0 is used in radix for supervisor<->user
- * protection, but on hash key 0 is reserved
- * ideally we want to enter with a clean state.
- * NOTE, we rely on r0 being 0 from above.
- */
- mtspr SPRN_IAMR,r0
-BEGIN_FTR_SECTION_NESTED(42)
- mtspr SPRN_AMOR,r0
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
/* save regs for local vars on new stack.
* yes, we won't go back, but ...
*/
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index df649ac..a211b02 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -86,3 +86,14 @@
return 0;
}
+
+#ifdef MODULES_VADDR
+void *module_alloc(unsigned long size)
+{
+ BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+ return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
+ PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+ __builtin_return_address(0));
+}
+#endif
diff --git a/arch/powerpc/kernel/module.lds b/arch/powerpc/kernel/module.lds
deleted file mode 100644
index cea5dc1..0000000
--- a/arch/powerpc/kernel/module.lds
+++ /dev/null
@@ -1,8 +0,0 @@
-/* Force alignment of .toc section. */
-SECTIONS
-{
- .toc 0 : ALIGN(256)
- {
- *(.got .toc)
- }
-}
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index d7134c6..c27b868 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -67,21 +67,6 @@
return 0;
}
-static void relaswap(void *_x, void *_y, int size)
-{
- uint32_t *x, *y, tmp;
- int i;
-
- y = (uint32_t *)_x;
- x = (uint32_t *)_y;
-
- for (i = 0; i < sizeof(Elf32_Rela) / sizeof(uint32_t); i++) {
- tmp = x[i];
- x[i] = y[i];
- y[i] = tmp;
- }
-}
-
/* Get the potential trampolines size required of the init and
non-init sections */
static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
@@ -118,7 +103,7 @@
*/
sort((void *)hdr + sechdrs[i].sh_offset,
sechdrs[i].sh_size / sizeof(Elf32_Rela),
- sizeof(Elf32_Rela), relacmp, relaswap);
+ sizeof(Elf32_Rela), relacmp, NULL);
ret += count_relocs((void *)hdr
+ sechdrs[i].sh_offset,
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 007606a..ae2b188 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -20,6 +20,7 @@
#include <linux/sort.h>
#include <asm/setup.h>
#include <asm/sections.h>
+#include <asm/inst.h>
/* FIXME: We don't do .init separately. To do this, we'd need to have
a separate r2 value in the init and core section, and stub between
@@ -144,42 +145,6 @@
PPC_INST_BCTR,
};
-#ifdef CONFIG_DYNAMIC_FTRACE
-int module_trampoline_target(struct module *mod, unsigned long addr,
- unsigned long *target)
-{
- struct ppc64_stub_entry *stub;
- func_desc_t funcdata;
- u32 magic;
-
- if (!within_module_core(addr, mod)) {
- pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name);
- return -EFAULT;
- }
-
- stub = (struct ppc64_stub_entry *)addr;
-
- if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
- pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
- return -EFAULT;
- }
-
- if (magic != STUB_MAGIC) {
- pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name);
- return -EFAULT;
- }
-
- if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) {
- pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
- return -EFAULT;
- }
-
- *target = stub_func_addr(funcdata);
-
- return 0;
-}
-#endif
-
/* Count how many different 24-bit relocations (different symbol,
different addend) */
static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num)
@@ -226,21 +191,6 @@
return 0;
}
-static void relaswap(void *_x, void *_y, int size)
-{
- uint64_t *x, *y, tmp;
- int i;
-
- y = (uint64_t *)_x;
- x = (uint64_t *)_y;
-
- for (i = 0; i < sizeof(Elf64_Rela) / sizeof(uint64_t); i++) {
- tmp = x[i];
- x[i] = y[i];
- y[i] = tmp;
- }
-}
-
/* Get size of potential trampolines required. */
static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
const Elf64_Shdr *sechdrs)
@@ -264,7 +214,7 @@
*/
sort((void *)sechdrs[i].sh_addr,
sechdrs[i].sh_size / sizeof(Elf64_Rela),
- sizeof(Elf64_Rela), relacmp, relaswap);
+ sizeof(Elf64_Rela), relacmp, NULL);
relocs += count_relocs((void *)sechdrs[i].sh_addr,
sechdrs[i].sh_size
@@ -384,6 +334,92 @@
return 0;
}
+#ifdef CONFIG_MPROFILE_KERNEL
+
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+/*
+ * ld r12,PACATOC(r13)
+ * addis r12,r12,<high>
+ * addi r12,r12,<low>
+ * mtctr r12
+ * bctr
+ */
+static u32 stub_insns[] = {
+ PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R13) | PACATOC,
+ PPC_INST_ADDIS | __PPC_RT(R12) | __PPC_RA(R12),
+ PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12),
+ PPC_INST_MTCTR | __PPC_RS(R12),
+ PPC_INST_BCTR,
+};
+
+/*
+ * For mprofile-kernel we use a special stub for ftrace_caller() because we
+ * can't rely on r2 containing this module's TOC when we enter the stub.
+ *
+ * That can happen if the function calling us didn't need to use the toc. In
+ * that case it won't have setup r2, and the r2 value will be either the
+ * kernel's toc, or possibly another modules toc.
+ *
+ * To deal with that this stub uses the kernel toc, which is always accessible
+ * via the paca (in r13). The target (ftrace_caller()) is responsible for
+ * saving and restoring the toc before returning.
+ */
+static inline int create_ftrace_stub(struct ppc64_stub_entry *entry,
+ unsigned long addr,
+ struct module *me)
+{
+ long reladdr;
+
+ memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+
+ /* Stub uses address relative to kernel toc (from the paca) */
+ reladdr = addr - kernel_toc_addr();
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("%s: Address of %ps out of range of kernel_toc.\n",
+ me->name, (void *)addr);
+ return 0;
+ }
+
+ entry->jump[1] |= PPC_HA(reladdr);
+ entry->jump[2] |= PPC_LO(reladdr);
+
+ /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */
+ entry->funcdata = func_desc(addr);
+ entry->magic = STUB_MAGIC;
+
+ return 1;
+}
+
+static bool is_mprofile_ftrace_call(const char *name)
+{
+ if (!strcmp("_mcount", name))
+ return true;
+#ifdef CONFIG_DYNAMIC_FTRACE
+ if (!strcmp("ftrace_caller", name))
+ return true;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ if (!strcmp("ftrace_regs_caller", name))
+ return true;
+#endif
+#endif
+
+ return false;
+}
+#else
+static inline int create_ftrace_stub(struct ppc64_stub_entry *entry,
+ unsigned long addr,
+ struct module *me)
+{
+ return 0;
+}
+
+static bool is_mprofile_ftrace_call(const char *name)
+{
+ return false;
+}
+#endif
+
/*
* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the
* value maximum span in an instruction which uses a signed offset). Round down
@@ -399,10 +435,14 @@
static inline int create_stub(const Elf64_Shdr *sechdrs,
struct ppc64_stub_entry *entry,
unsigned long addr,
- struct module *me)
+ struct module *me,
+ const char *name)
{
long reladdr;
+ if (is_mprofile_ftrace_call(name))
+ return create_ftrace_stub(entry, addr, me);
+
memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
/* Stub uses address relative to r2. */
@@ -426,7 +466,8 @@
stub to set up the TOC ptr (r2) for the function. */
static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
unsigned long addr,
- struct module *me)
+ struct module *me,
+ const char *name)
{
struct ppc64_stub_entry *stubs;
unsigned int i, num_stubs;
@@ -443,62 +484,19 @@
return (unsigned long)&stubs[i];
}
- if (!create_stub(sechdrs, &stubs[i], addr, me))
+ if (!create_stub(sechdrs, &stubs[i], addr, me, name))
return 0;
return (unsigned long)&stubs[i];
}
-#ifdef CONFIG_MPROFILE_KERNEL
-static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction)
-{
- if (strcmp("_mcount", name))
- return false;
-
- /*
- * Check if this is one of the -mprofile-kernel sequences.
- */
- if (instruction[-1] == PPC_INST_STD_LR &&
- instruction[-2] == PPC_INST_MFLR)
- return true;
-
- if (instruction[-1] == PPC_INST_MFLR)
- return true;
-
- return false;
-}
-
-/*
- * In case of _mcount calls, do not save the current callee's TOC (in r2) into
- * the original caller's stack frame. If we did we would clobber the saved TOC
- * value of the original caller.
- */
-static void squash_toc_save_inst(const char *name, unsigned long addr)
-{
- struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr;
-
- /* Only for calls to _mcount */
- if (strcmp("_mcount", name) != 0)
- return;
-
- stub->jump[2] = PPC_INST_NOP;
-}
-#else
-static void squash_toc_save_inst(const char *name, unsigned long addr) { }
-
-static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction)
-{
- return false;
-}
-#endif
-
/* We expect a noop next: if it is, replace it with instruction to
restore r2. */
static int restore_r2(const char *name, u32 *instruction, struct module *me)
{
u32 *prev_insn = instruction - 1;
- if (is_mprofile_mcount_callsite(name, prev_insn))
+ if (is_mprofile_ftrace_call(name))
return 1;
/*
@@ -506,7 +504,7 @@
* "link" branches and they don't return, so they don't need the r2
* restore afterwards.
*/
- if (!instr_is_relative_link_branch(*prev_insn))
+ if (!instr_is_relative_link_branch(ppc_inst(*prev_insn)))
return 1;
if (*instruction != PPC_INST_NOP) {
@@ -636,14 +634,13 @@
if (sym->st_shndx == SHN_UNDEF ||
sym->st_shndx == SHN_LIVEPATCH) {
/* External: go via stub */
- value = stub_for_addr(sechdrs, value, me);
+ value = stub_for_addr(sechdrs, value, me,
+ strtab + sym->st_name);
if (!value)
return -ENOENT;
if (!restore_r2(strtab + sym->st_name,
(u32 *)location + 1, me))
return -ENOEXEC;
-
- squash_toc_save_inst(strtab + sym->st_name, value);
} else
value += local_entry_offset(sym);
@@ -745,89 +742,53 @@
}
#ifdef CONFIG_DYNAMIC_FTRACE
-
-#ifdef CONFIG_MPROFILE_KERNEL
-
-#define PACATOC offsetof(struct paca_struct, kernel_toc)
-
-/*
- * For mprofile-kernel we use a special stub for ftrace_caller() because we
- * can't rely on r2 containing this module's TOC when we enter the stub.
- *
- * That can happen if the function calling us didn't need to use the toc. In
- * that case it won't have setup r2, and the r2 value will be either the
- * kernel's toc, or possibly another modules toc.
- *
- * To deal with that this stub uses the kernel toc, which is always accessible
- * via the paca (in r13). The target (ftrace_caller()) is responsible for
- * saving and restoring the toc before returning.
- */
-static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs,
- struct module *me, unsigned long addr)
+int module_trampoline_target(struct module *mod, unsigned long addr,
+ unsigned long *target)
{
- struct ppc64_stub_entry *entry;
- unsigned int i, num_stubs;
- /*
- * ld r12,PACATOC(r13)
- * addis r12,r12,<high>
- * addi r12,r12,<low>
- * mtctr r12
- * bctr
- */
- static u32 stub_insns[] = {
- PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R13) | PACATOC,
- PPC_INST_ADDIS | __PPC_RT(R12) | __PPC_RA(R12),
- PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12),
- PPC_INST_MTCTR | __PPC_RS(R12),
- PPC_INST_BCTR,
- };
- long reladdr;
+ struct ppc64_stub_entry *stub;
+ func_desc_t funcdata;
+ u32 magic;
- num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry);
-
- /* Find the next available stub entry */
- entry = (void *)sechdrs[me->arch.stubs_section].sh_addr;
- for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++);
-
- if (i >= num_stubs) {
- pr_err("%s: Unable to find a free slot for ftrace stub.\n", me->name);
- return 0;
+ if (!within_module_core(addr, mod)) {
+ pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name);
+ return -EFAULT;
}
- memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+ stub = (struct ppc64_stub_entry *)addr;
- /* Stub uses address relative to kernel toc (from the paca) */
- reladdr = addr - kernel_toc_addr();
- if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
- pr_err("%s: Address of %ps out of range of kernel_toc.\n",
- me->name, (void *)addr);
- return 0;
+ if (copy_from_kernel_nofault(&magic, &stub->magic,
+ sizeof(magic))) {
+ pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
}
- entry->jump[1] |= PPC_HA(reladdr);
- entry->jump[2] |= PPC_LO(reladdr);
+ if (magic != STUB_MAGIC) {
+ pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
- /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */
- entry->funcdata = func_desc(addr);
- entry->magic = STUB_MAGIC;
+ if (copy_from_kernel_nofault(&funcdata, &stub->funcdata,
+ sizeof(funcdata))) {
+ pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
- return (unsigned long)entry;
+ *target = stub_func_addr(funcdata);
+
+ return 0;
}
-#else
-static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs,
- struct module *me, unsigned long addr)
-{
- return stub_for_addr(sechdrs, addr, me);
-}
-#endif
int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
{
- mod->arch.tramp = create_ftrace_stub(sechdrs, mod,
- (unsigned long)ftrace_caller);
+ mod->arch.tramp = stub_for_addr(sechdrs,
+ (unsigned long)ftrace_caller,
+ mod,
+ "ftrace_caller");
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
- mod->arch.tramp_regs = create_ftrace_stub(sechdrs, mod,
- (unsigned long)ftrace_regs_caller);
+ mod->arch.tramp_regs = stub_for_addr(sechdrs,
+ (unsigned long)ftrace_regs_caller,
+ mod,
+ "ftrace_regs_caller");
if (!mod->arch.tramp_regs)
return -ENOENT;
#endif
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index fb4f610..532f226 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -655,9 +655,7 @@
int rc = -1;
switch (reason) {
- case KMSG_DUMP_RESTART:
- case KMSG_DUMP_HALT:
- case KMSG_DUMP_POWEROFF:
+ case KMSG_DUMP_SHUTDOWN:
/* These are almost always orderly shutdowns. */
return;
case KMSG_DUMP_OOPS:
@@ -854,8 +852,8 @@
BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
/* Convert sizes from bytes to blocks */
- req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
- min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+ req_size = ALIGN(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+ min_size = ALIGN(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
/* If no minimum size specified, make it the same as the
* requested size
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 427fc22..f89376f 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -62,12 +62,8 @@
/* Init pci_dn data structures */
pci_devs_phb_init_dynamic(phb);
- /* Create EEH devices for the PHB */
- eeh_dev_phb_init_dynamic(phb);
-
- /* Register devices with EEH */
- if (dev->dev.of_node->child)
- eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
+ /* Create EEH PE for the PHB */
+ eeh_phb_pe_create(phb);
/* Scan the bus */
pcibios_scan_phb(phb);
@@ -80,15 +76,9 @@
*/
pcibios_claim_one_bus(phb->bus);
- /* Finish EEH setup */
- eeh_add_device_tree_late(phb->bus);
-
/* Add probed PCI devices to the device model */
pci_bus_add_devices(phb->bus);
- /* sysfs files should only be added after devices are added */
- eeh_add_sysfs_files(phb->bus);
-
return 0;
}
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 024f7aa..69bfe96 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -16,6 +16,7 @@
#include <asm/code-patching.h>
#include <asm/sstep.h>
#include <asm/ppc-opcode.h>
+#include <asm/inst.h>
#define TMPL_CALL_HDLR_IDX \
(optprobe_template_call_handler - optprobe_template_entry)
@@ -99,8 +100,9 @@
* Ensure that the instruction is not a conditional branch,
* and that can be emulated.
*/
- if (!is_conditional_branch(*p->ainsn.insn) &&
- analyse_instr(&op, ®s, *p->ainsn.insn) == 1) {
+ if (!is_conditional_branch(ppc_inst_read((struct ppc_inst *)p->ainsn.insn)) &&
+ analyse_instr(&op, ®s,
+ ppc_inst_read((struct ppc_inst *)p->ainsn.insn)) == 1) {
emulate_update_regs(®s, &op);
nip = regs.nip;
}
@@ -147,50 +149,57 @@
void patch_imm32_load_insns(unsigned int val, kprobe_opcode_t *addr)
{
/* addis r4,0,(insn)@h */
- patch_instruction(addr, PPC_INST_ADDIS | ___PPC_RT(4) |
- ((val >> 16) & 0xffff));
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ADDIS | ___PPC_RT(4) |
+ ((val >> 16) & 0xffff)));
addr++;
/* ori r4,r4,(insn)@l */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(4) |
- ___PPC_RS(4) | (val & 0xffff));
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ORI | ___PPC_RA(4) |
+ ___PPC_RS(4) | (val & 0xffff)));
}
/*
* Generate instructions to load provided immediate 64-bit value
- * to register 'r3' and patch these instructions at 'addr'.
+ * to register 'reg' and patch these instructions at 'addr'.
*/
-void patch_imm64_load_insns(unsigned long val, kprobe_opcode_t *addr)
+void patch_imm64_load_insns(unsigned long val, int reg, kprobe_opcode_t *addr)
{
- /* lis r3,(op)@highest */
- patch_instruction(addr, PPC_INST_ADDIS | ___PPC_RT(3) |
- ((val >> 48) & 0xffff));
+ /* lis reg,(op)@highest */
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ADDIS | ___PPC_RT(reg) |
+ ((val >> 48) & 0xffff)));
addr++;
- /* ori r3,r3,(op)@higher */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(3) |
- ___PPC_RS(3) | ((val >> 32) & 0xffff));
+ /* ori reg,reg,(op)@higher */
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ORI | ___PPC_RA(reg) |
+ ___PPC_RS(reg) | ((val >> 32) & 0xffff)));
addr++;
- /* rldicr r3,r3,32,31 */
- patch_instruction(addr, PPC_INST_RLDICR | ___PPC_RA(3) |
- ___PPC_RS(3) | __PPC_SH64(32) | __PPC_ME64(31));
+ /* rldicr reg,reg,32,31 */
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_RLDICR | ___PPC_RA(reg) |
+ ___PPC_RS(reg) | __PPC_SH64(32) | __PPC_ME64(31)));
addr++;
- /* oris r3,r3,(op)@h */
- patch_instruction(addr, PPC_INST_ORIS | ___PPC_RA(3) |
- ___PPC_RS(3) | ((val >> 16) & 0xffff));
+ /* oris reg,reg,(op)@h */
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ORIS | ___PPC_RA(reg) |
+ ___PPC_RS(reg) | ((val >> 16) & 0xffff)));
addr++;
- /* ori r3,r3,(op)@l */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(3) |
- ___PPC_RS(3) | (val & 0xffff));
+ /* ori reg,reg,(op)@l */
+ patch_instruction((struct ppc_inst *)addr,
+ ppc_inst(PPC_INST_ORI | ___PPC_RA(reg) |
+ ___PPC_RS(reg) | (val & 0xffff)));
}
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
{
- kprobe_opcode_t *buff, branch_op_callback, branch_emulate_step;
- kprobe_opcode_t *op_callback_addr, *emulate_step_addr;
+ struct ppc_inst branch_op_callback, branch_emulate_step, temp;
+ kprobe_opcode_t *op_callback_addr, *emulate_step_addr, *buff;
long b_offset;
unsigned long nip, size;
int rc, i;
@@ -230,7 +239,8 @@
size = (TMPL_END_IDX * sizeof(kprobe_opcode_t)) / sizeof(int);
pr_devel("Copying template to %p, size %lu\n", buff, size);
for (i = 0; i < size; i++) {
- rc = patch_instruction(buff + i, *(optprobe_template_entry + i));
+ rc = patch_instruction((struct ppc_inst *)(buff + i),
+ ppc_inst(*(optprobe_template_entry + i)));
if (rc < 0)
goto error;
}
@@ -239,7 +249,7 @@
* Fixup the template with instructions to:
* 1. load the address of the actual probepoint
*/
- patch_imm64_load_insns((unsigned long)op, buff + TMPL_OP_IDX);
+ patch_imm64_load_insns((unsigned long)op, 3, buff + TMPL_OP_IDX);
/*
* 2. branch to optimized_callback() and emulate_step()
@@ -251,29 +261,34 @@
goto error;
}
- branch_op_callback = create_branch((unsigned int *)buff + TMPL_CALL_HDLR_IDX,
- (unsigned long)op_callback_addr,
- BRANCH_SET_LINK);
+ rc = create_branch(&branch_op_callback,
+ (struct ppc_inst *)(buff + TMPL_CALL_HDLR_IDX),
+ (unsigned long)op_callback_addr,
+ BRANCH_SET_LINK);
- branch_emulate_step = create_branch((unsigned int *)buff + TMPL_EMULATE_IDX,
- (unsigned long)emulate_step_addr,
- BRANCH_SET_LINK);
+ rc |= create_branch(&branch_emulate_step,
+ (struct ppc_inst *)(buff + TMPL_EMULATE_IDX),
+ (unsigned long)emulate_step_addr,
+ BRANCH_SET_LINK);
- if (!branch_op_callback || !branch_emulate_step)
+ if (rc)
goto error;
- patch_instruction(buff + TMPL_CALL_HDLR_IDX, branch_op_callback);
- patch_instruction(buff + TMPL_EMULATE_IDX, branch_emulate_step);
+ patch_instruction((struct ppc_inst *)(buff + TMPL_CALL_HDLR_IDX),
+ branch_op_callback);
+ patch_instruction((struct ppc_inst *)(buff + TMPL_EMULATE_IDX),
+ branch_emulate_step);
/*
* 3. load instruction to be emulated into relevant register, and
*/
- patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX);
+ temp = ppc_inst_read((struct ppc_inst *)p->ainsn.insn);
+ patch_imm64_load_insns(ppc_inst_as_u64(temp), 4, buff + TMPL_INSN_IDX);
/*
* 4. branch back from trampoline
*/
- patch_branch(buff + TMPL_RET_IDX, (unsigned long)nip, 0);
+ patch_branch((struct ppc_inst *)(buff + TMPL_RET_IDX), (unsigned long)nip, 0);
flush_icache_range((unsigned long)buff,
(unsigned long)(&buff[TMPL_END_IDX]));
@@ -305,6 +320,7 @@
void arch_optimize_kprobes(struct list_head *oplist)
{
+ struct ppc_inst instr;
struct optimized_kprobe *op;
struct optimized_kprobe *tmp;
@@ -315,9 +331,10 @@
*/
memcpy(op->optinsn.copied_insn, op->kp.addr,
RELATIVEJUMP_SIZE);
- patch_instruction(op->kp.addr,
- create_branch((unsigned int *)op->kp.addr,
- (unsigned long)op->optinsn.insn, 0));
+ create_branch(&instr,
+ (struct ppc_inst *)op->kp.addr,
+ (unsigned long)op->optinsn.insn, 0);
+ patch_instruction((struct ppc_inst *)op->kp.addr, instr);
list_del_init(&op->list);
}
}
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
index cf38352..ff8ba4d 100644
--- a/arch/powerpc/kernel/optprobes_head.S
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -94,6 +94,9 @@
/* 2, Pass instruction to be emulated in r4 */
nop
nop
+ nop
+ nop
+ nop
.global optprobe_template_call_emulate
optprobe_template_call_emulate:
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index c786adf..7f5aae3 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -8,14 +8,15 @@
#include <linux/memblock.h>
#include <linux/sched/task.h>
#include <linux/numa.h>
+#include <linux/pgtable.h>
#include <asm/lppaca.h>
#include <asm/paca.h>
#include <asm/sections.h>
-#include <asm/pgtable.h>
#include <asm/kexec.h>
#include <asm/svm.h>
#include <asm/ultravisor.h>
+#include <asm/rtas.h>
#include "setup.h"
@@ -56,8 +57,8 @@
#define LPPACA_SIZE 0x400
-static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
- unsigned long limit, int cpu)
+static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
+ int cpu)
{
size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE);
static unsigned long shared_lppaca_size;
@@ -67,6 +68,13 @@
if (!shared_lppaca) {
memblock_set_bottom_up(true);
+ /*
+ * See Documentation/powerpc/ultravisor.rst for more details.
+ *
+ * UV/HV data sharing is in PAGE_SIZE granularity. In order to
+ * minimize the number of pages shared, align the allocation to
+ * PAGE_SIZE.
+ */
shared_lppaca =
memblock_alloc_try_nid(shared_lppaca_total_size,
PAGE_SIZE, MEMBLOCK_LOW_LIMIT,
@@ -121,7 +129,7 @@
return NULL;
if (is_secure_guest())
- lp = alloc_shared_lppaca(LPPACA_SIZE, 0x400, limit, cpu);
+ lp = alloc_shared_lppaca(LPPACA_SIZE, limit, cpu);
else
lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu);
@@ -164,6 +172,30 @@
#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_PPC_PSERIES
+/**
+ * new_rtas_args() - Allocates rtas args
+ * @cpu: CPU number
+ * @limit: Memory limit for this allocation
+ *
+ * Allocates a struct rtas_args and return it's pointer,
+ * if not in Hypervisor mode
+ *
+ * Return: Pointer to allocated rtas_args
+ * NULL if CPU in Hypervisor Mode
+ */
+static struct rtas_args * __init new_rtas_args(int cpu, unsigned long limit)
+{
+ limit = min_t(unsigned long, limit, RTAS_INSTANTIATE_MAX);
+
+ if (early_cpu_has_feature(CPU_FTR_HVMODE))
+ return NULL;
+
+ return alloc_paca_data(sizeof(struct rtas_args), L1_CACHE_BYTES,
+ limit, cpu);
+}
+#endif /* CONFIG_PPC_PSERIES */
+
/* The Paca is an array with one entry per processor. Each contains an
* lppaca, which contains the information shared between the
* hypervisor and Linux.
@@ -202,6 +234,10 @@
/* For now -- if we have threads this will be adjusted later */
new_paca->tcd_ptr = &new_paca->tcd;
#endif
+
+#ifdef CONFIG_PPC_PSERIES
+ new_paca->rtas_args_reentrant = NULL;
+#endif
}
/* Put the paca pointer into r13 and SPRG_PACA */
@@ -274,6 +310,9 @@
#ifdef CONFIG_PPC_BOOK3S_64
paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
#endif
+#ifdef CONFIG_PPC_PSERIES
+ paca->rtas_args_reentrant = new_rtas_args(cpu, limit);
+#endif
paca_struct_size += sizeof(struct paca_struct);
}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index a2c258a..7920559 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -261,12 +261,6 @@
#endif /* CONFIG_PCI_IOV */
-void pcibios_bus_add_device(struct pci_dev *pdev)
-{
- if (ppc_md.pcibios_bus_add_device)
- ppc_md.pcibios_bus_add_device(pdev);
-}
-
static resource_size_t pcibios_io_size(const struct pci_controller *hose)
{
#ifdef CONFIG_PPC64
@@ -734,7 +728,7 @@
" MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
range.cpu_addr, range.cpu_addr + range.size - 1,
range.pci_addr,
- (range.pci_space & 0x40000000) ?
+ (range.flags & IORESOURCE_PREFETCH) ?
"Prefetch" : "");
/* We support only 3 memory ranges */
@@ -964,7 +958,7 @@
phb->controller_ops.dma_bus_setup(bus);
}
-static void pcibios_setup_device(struct pci_dev *dev)
+void pcibios_bus_add_device(struct pci_dev *dev)
{
struct pci_controller *phb;
/* Fixup NUMA node as it may not be setup yet by the generic
@@ -985,17 +979,13 @@
pci_read_irq_line(dev);
if (ppc_md.pci_irq_fixup)
ppc_md.pci_irq_fixup(dev);
+
+ if (ppc_md.pcibios_bus_add_device)
+ ppc_md.pcibios_bus_add_device(dev);
}
int pcibios_add_device(struct pci_dev *dev)
{
- /*
- * We can only call pcibios_setup_device() after bus setup is complete,
- * since some of the platform specific DMA setup code depends on it.
- */
- if (dev->bus->is_added)
- pcibios_setup_device(dev);
-
#ifdef CONFIG_PCI_IOV
if (ppc_md.pcibios_fixup_sriov)
ppc_md.pcibios_fixup_sriov(dev);
@@ -1004,24 +994,6 @@
return 0;
}
-void pcibios_setup_bus_devices(struct pci_bus *bus)
-{
- struct pci_dev *dev;
-
- pr_debug("PCI: Fixup bus devices %d (%s)\n",
- bus->number, bus->self ? pci_name(bus->self) : "PHB");
-
- list_for_each_entry(dev, &bus->devices, bus_list) {
- /* Cardbus can call us to add new devices to a bus, so ignore
- * those who are already fully discovered
- */
- if (pci_dev_is_added(dev))
- continue;
-
- pcibios_setup_device(dev);
- }
-}
-
void pcibios_set_master(struct pci_dev *dev)
{
/* No special bus mastering setup handling */
@@ -1037,19 +1009,9 @@
/* Now fixup the bus bus */
pcibios_setup_bus_self(bus);
-
- /* Now fixup devices on that bus */
- pcibios_setup_bus_devices(bus);
}
EXPORT_SYMBOL(pcibios_fixup_bus);
-void pci_fixup_cardbus(struct pci_bus *bus)
-{
- /* Now fixup devices on that bus */
- pcibios_setup_bus_devices(bus);
-}
-
-
static int skip_isa_ioresource_align(struct pci_dev *dev)
{
if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) &&
@@ -1437,14 +1399,8 @@
pci_assign_unassigned_bus_resources(bus);
}
- /* Fixup EEH */
- eeh_add_device_tree_late(bus);
-
/* Add new devices to global lists. Register in proc, sysfs. */
pci_bus_add_devices(bus);
-
- /* sysfs files should only be added after devices are added */
- eeh_add_sysfs_files(bus);
}
EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index fc62c4b..2fc1219 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -57,8 +57,6 @@
struct pci_controller *phb = pci_bus_to_host(dev->bus);
struct pci_dn *pdn = pci_get_pdn(dev);
- eeh_remove_device(dev);
-
if (phb->controller_ops.release_device)
phb->controller_ops.release_device(dev);
@@ -112,8 +110,6 @@
struct pci_controller *phb;
struct device_node *dn = pci_bus_to_OF_node(bus);
- eeh_add_device_tree_early(PCI_DN(dn));
-
phb = pci_bus_to_host(bus);
mode = PCI_PROBE_NORMAL;
@@ -134,7 +130,6 @@
*/
slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
- pcibios_setup_bus_devices(bus);
max = bus->busn_res.start;
/*
* Scan bridges that are already configured. We don't touch
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index f83d1f6..9312e6e 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -100,7 +100,7 @@
pci_name(bus->self));
#ifdef CONFIG_PPC_BOOK3S_64
- __flush_hash_table_range(&init_mm, res->start + _IO_BASE,
+ __flush_hash_table_range(res->start + _IO_BASE,
res->end + _IO_BASE + 1);
#endif
return 0;
@@ -109,29 +109,53 @@
/* Get the host bridge */
hose = pci_bus_to_host(bus);
- /* Check if we have IOs allocated */
- if (hose->io_base_alloc == NULL)
- return 0;
-
pr_debug("IO unmapping for PHB %pOF\n", hose->dn);
pr_debug(" alloc=0x%p\n", hose->io_base_alloc);
- /* This is a PHB, we fully unmap the IO area */
- vunmap(hose->io_base_alloc);
-
+ iounmap(hose->io_base_alloc);
return 0;
}
EXPORT_SYMBOL_GPL(pcibios_unmap_io_space);
-static int pcibios_map_phb_io_space(struct pci_controller *hose)
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
{
struct vm_struct *area;
+ unsigned long addr;
+
+ WARN_ON_ONCE(paddr & ~PAGE_MASK);
+ WARN_ON_ONCE(size & ~PAGE_MASK);
+
+ /*
+ * Let's allocate some IO space for that guy. We don't pass VM_IOREMAP
+ * because we don't care about alignment tricks that the core does in
+ * that case. Maybe we should due to stupid card with incomplete
+ * address decoding but I'd rather not deal with those outside of the
+ * reserved 64K legacy region.
+ */
+ area = __get_vm_area_caller(size, 0, PHB_IO_BASE, PHB_IO_END,
+ __builtin_return_address(0));
+ if (!area)
+ return NULL;
+
+ addr = (unsigned long)area->addr;
+ if (ioremap_page_range(addr, addr + size, paddr,
+ pgprot_noncached(PAGE_KERNEL))) {
+ unmap_kernel_range(addr, size);
+ return NULL;
+ }
+
+ return (void __iomem *)addr;
+}
+EXPORT_SYMBOL_GPL(ioremap_phb);
+
+static int pcibios_map_phb_io_space(struct pci_controller *hose)
+{
unsigned long phys_page;
unsigned long size_page;
unsigned long io_virt_offset;
- phys_page = _ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
- size_page = _ALIGN_UP(hose->pci_io_size, PAGE_SIZE);
+ phys_page = ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
+ size_page = ALIGN(hose->pci_io_size, PAGE_SIZE);
/* Make sure IO area address is clear */
hose->io_base_alloc = NULL;
@@ -146,12 +170,11 @@
* with incomplete address decoding but I'd rather not deal with
* those outside of the reserved 64K legacy region.
*/
- area = __get_vm_area(size_page, 0, PHB_IO_BASE, PHB_IO_END);
- if (area == NULL)
+ hose->io_base_alloc = ioremap_phb(phys_page, size_page);
+ if (!hose->io_base_alloc)
return -ENOMEM;
- hose->io_base_alloc = area->addr;
- hose->io_base_virt = (void __iomem *)(area->addr +
- hose->io_base_phys - phys_page);
+ hose->io_base_virt = hose->io_base_alloc +
+ hose->io_base_phys - phys_page;
pr_debug("IO mapping for PHB %pOF\n", hose->dn);
pr_debug(" phys=0x%016llx, virt=0x%p (alloc=0x%p)\n",
@@ -159,11 +182,6 @@
pr_debug(" size=0x%016llx (alloc=0x%016lx)\n",
hose->pci_io_size, size_page);
- /* Establish the mapping */
- if (__ioremap_at(phys_page, area->addr, size_page,
- pgprot_noncached(PAGE_KERNEL)) == NULL)
- return -ENOMEM;
-
/* Fixup hose IO resource */
io_virt_offset = pcibios_io_space_offset(hose);
hose->io_resource.start += io_virt_offset;
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index d876eda..e99b7c5 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -124,9 +124,28 @@
return NULL;
}
+#ifdef CONFIG_EEH
+static struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
+{
+ struct eeh_dev *edev;
+
+ /* Allocate EEH device */
+ edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+ if (!edev)
+ return NULL;
+
+ /* Associate EEH device with OF node */
+ pdn->edev = edev;
+ edev->pdn = pdn;
+ edev->bdfn = (pdn->busno << 8) | pdn->devfn;
+ edev->controller = pdn->phb;
+
+ return edev;
+}
+#endif /* CONFIG_EEH */
+
#ifdef CONFIG_PCI_IOV
-static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
- int vf_index,
+static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent,
int busno, int devfn)
{
struct pci_dn *pdn;
@@ -143,7 +162,6 @@
pdn->parent = parent;
pdn->busno = busno;
pdn->devfn = devfn;
- pdn->vf_index = vf_index;
pdn->pe_number = IODA_INVALID_PE;
INIT_LIST_HEAD(&pdn->child_list);
INIT_LIST_HEAD(&pdn->list);
@@ -151,17 +169,15 @@
return pdn;
}
-#endif
-struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev)
{
-#ifdef CONFIG_PCI_IOV
struct pci_dn *parent, *pdn;
int i;
/* Only support IOV for now */
- if (!pdev->is_physfn)
- return pci_get_pdn(pdev);
+ if (WARN_ON(!pdev->is_physfn))
+ return NULL;
/* Check if VFs have been populated */
pdn = pci_get_pdn(pdev);
@@ -176,7 +192,7 @@
for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
struct eeh_dev *edev __maybe_unused;
- pdn = add_one_dev_pci_data(parent, i,
+ pdn = add_one_sriov_vf_pdn(parent,
pci_iov_virtfn_bus(pdev, i),
pci_iov_virtfn_devfn(pdev, i));
if (!pdn) {
@@ -189,34 +205,23 @@
/* Create the EEH device for the VF */
edev = eeh_dev_init(pdn);
BUG_ON(!edev);
+
+ /* FIXME: these should probably be populated by the EEH probe */
edev->physfn = pdev;
+ edev->vf_index = i;
#endif /* CONFIG_EEH */
}
-#endif /* CONFIG_PCI_IOV */
-
return pci_get_pdn(pdev);
}
-void remove_dev_pci_data(struct pci_dev *pdev)
+void remove_sriov_vf_pdns(struct pci_dev *pdev)
{
-#ifdef CONFIG_PCI_IOV
struct pci_dn *parent;
struct pci_dn *pdn, *tmp;
int i;
- /*
- * VF and VF PE are created/released dynamically, so we need to
- * bind/unbind them. Otherwise the VF and VF PE would be mismatched
- * when re-enabling SR-IOV.
- */
- if (pdev->is_virtfn) {
- pdn = pci_get_pdn(pdev);
- pdn->pe_number = IODA_INVALID_PE;
- return;
- }
-
/* Only support IOV PF for now */
- if (!pdev->is_physfn)
+ if (WARN_ON(!pdev->is_physfn))
return;
/* Check if VFs have been populated */
@@ -258,7 +263,7 @@
* have a configured PE.
*/
if (edev->pe)
- eeh_rmv_from_parent_pe(edev);
+ eeh_pe_tree_remove(edev);
pdn->edev = NULL;
kfree(edev);
@@ -271,8 +276,8 @@
kfree(pdn);
}
}
-#endif /* CONFIG_PCI_IOV */
}
+#endif /* CONFIG_PCI_IOV */
struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
struct device_node *dn)
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index f91d7e9..c3024f1 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -414,7 +414,6 @@
*/
if (!rescan_existing)
pcibios_setup_bus_self(bus);
- pcibios_setup_bus_devices(bus);
/* Now scan child busses */
for_each_pci_bridge(dev, bus)
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
index f3bd0bb..2d4d21b 100644
--- a/arch/powerpc/kernel/ppc_save_regs.S
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -55,14 +55,17 @@
PPC_STL r29,29*SZL(r3)
PPC_STL r30,30*SZL(r3)
PPC_STL r31,31*SZL(r3)
+ lbz r0,PACAIRQSOFTMASK(r13)
+ PPC_STL r0,SOFTE-STACK_FRAME_OVERHEAD(r3)
#endif
/* go up one stack frame for SP */
PPC_LL r4,0(r1)
PPC_STL r4,1*SZL(r3)
/* get caller's LR */
PPC_LL r0,LRSAVE(r4)
- PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3)
PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3)
+ mflr r0
+ PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3)
mfmsr r0
PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3)
mfctr r0
@@ -73,4 +76,5 @@
PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3)
li r0,0
PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,ORIG_GPR3-STACK_FRAME_OVERHEAD(r3)
blr
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index be3758d..8778174 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -39,10 +39,10 @@
return 0;
}
-static const struct file_operations page_map_fops = {
- .llseek = page_map_seek,
- .read = page_map_read,
- .mmap = page_map_mmap
+static const struct proc_ops page_map_proc_ops = {
+ .proc_lseek = page_map_seek,
+ .proc_read = page_map_read,
+ .proc_mmap = page_map_mmap,
};
@@ -51,7 +51,7 @@
struct proc_dir_entry *pde;
pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
- &page_map_fops, vdso_data);
+ &page_map_proc_ops, vdso_data);
if (!pde)
return 1;
proc_set_size(pde, PAGE_SIZE);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c94bba9..3064694 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -41,7 +41,6 @@
#include <linux/pkeys.h>
#include <linux/seq_buf.h>
-#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/mmu.h>
@@ -125,10 +124,8 @@
newmsr = oldmsr | bits;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
newmsr |= MSR_VSX;
-#endif
if (oldmsr != newmsr)
mtmsr_isync(newmsr);
@@ -145,10 +142,8 @@
newmsr = oldmsr & ~bits;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
newmsr &= ~MSR_VSX;
-#endif
if (oldmsr != newmsr)
mtmsr_isync(newmsr);
@@ -163,10 +158,8 @@
save_fpu(tsk);
msr = tsk->thread.regs->msr;
msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr &= ~MSR_VSX;
-#endif
tsk->thread.regs->msr = msr;
}
@@ -236,23 +229,11 @@
}
}
EXPORT_SYMBOL(enable_kernel_fp);
-
-static int restore_fp(struct task_struct *tsk)
-{
- if (tsk->thread.load_fp) {
- load_fp_state(¤t->thread.fp_state);
- current->thread.load_fp++;
- return 1;
- }
- return 0;
-}
#else
-static int restore_fp(struct task_struct *tsk) { return 0; }
+static inline void __giveup_fpu(struct task_struct *tsk) { }
#endif /* CONFIG_PPC_FPU */
#ifdef CONFIG_ALTIVEC
-#define loadvec(thr) ((thr).load_vec)
-
static void __giveup_altivec(struct task_struct *tsk)
{
unsigned long msr;
@@ -260,10 +241,8 @@
save_altivec(tsk);
msr = tsk->thread.regs->msr;
msr &= ~MSR_VEC;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr &= ~MSR_VSX;
-#endif
tsk->thread.regs->msr = msr;
}
@@ -318,21 +297,6 @@
}
}
EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
-
-static int restore_altivec(struct task_struct *tsk)
-{
- if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
- load_vr_state(&tsk->thread.vr_state);
- tsk->thread.used_vr = 1;
- tsk->thread.load_vec++;
-
- return 1;
- }
- return 0;
-}
-#else
-#define loadvec(thr) 0
-static inline int restore_altivec(struct task_struct *tsk) { return 0; }
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
@@ -400,18 +364,6 @@
}
}
EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
-
-static int restore_vsx(struct task_struct *tsk)
-{
- if (cpu_has_feature(CPU_FTR_VSX)) {
- tsk->thread.used_vsr = 1;
- return 1;
- }
-
- return 0;
-}
-#else
-static inline int restore_vsx(struct task_struct *tsk) { return 0; }
#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
@@ -456,21 +408,14 @@
static int __init init_msr_all_available(void)
{
-#ifdef CONFIG_PPC_FPU
- msr_all_available |= MSR_FP;
-#endif
-#ifdef CONFIG_ALTIVEC
+ if (IS_ENABLED(CONFIG_PPC_FPU))
+ msr_all_available |= MSR_FP;
if (cpu_has_feature(CPU_FTR_ALTIVEC))
msr_all_available |= MSR_VEC;
-#endif
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr_all_available |= MSR_VSX;
-#endif
-#ifdef CONFIG_SPE
if (cpu_has_feature(CPU_FTR_SPE))
msr_all_available |= MSR_SPE;
-#endif
return 0;
}
@@ -494,23 +439,72 @@
WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
-#ifdef CONFIG_PPC_FPU
if (usermsr & MSR_FP)
__giveup_fpu(tsk);
-#endif
-#ifdef CONFIG_ALTIVEC
if (usermsr & MSR_VEC)
__giveup_altivec(tsk);
-#endif
-#ifdef CONFIG_SPE
if (usermsr & MSR_SPE)
__giveup_spe(tsk);
-#endif
msr_check_and_clear(msr_all_available);
}
EXPORT_SYMBOL(giveup_all);
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_FPU
+static bool should_restore_fp(void)
+{
+ if (current->thread.load_fp) {
+ current->thread.load_fp++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_fp(void)
+{
+ load_fp_state(¤t->thread.fp_state);
+}
+#else
+static bool should_restore_fp(void) { return false; }
+static void do_restore_fp(void) { }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static bool should_restore_altivec(void)
+{
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (current->thread.load_vec)) {
+ current->thread.load_vec++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_altivec(void)
+{
+ load_vr_state(¤t->thread.vr_state);
+ current->thread.used_vr = 1;
+}
+#else
+static bool should_restore_altivec(void) { return false; }
+static void do_restore_altivec(void) { }
+#endif /* CONFIG_ALTIVEC */
+
+static bool should_restore_vsx(void)
+{
+ if (cpu_has_feature(CPU_FTR_VSX))
+ return true;
+ return false;
+}
+#ifdef CONFIG_VSX
+static void do_restore_vsx(void)
+{
+ current->thread.used_vsr = 1;
+}
+#else
+static void do_restore_vsx(void) { }
+#endif /* CONFIG_VSX */
+
/*
* The exception exit path calls restore_math() with interrupts hard disabled
* but the soft irq state not "reconciled". ftrace code that calls
@@ -524,33 +518,50 @@
void notrace restore_math(struct pt_regs *regs)
{
unsigned long msr;
-
- if (!MSR_TM_ACTIVE(regs->msr) &&
- !current->thread.load_fp && !loadvec(current->thread))
- return;
+ unsigned long new_msr = 0;
msr = regs->msr;
- msr_check_and_set(msr_all_available);
/*
- * Only reload if the bit is not set in the user MSR, the bit BEING set
- * indicates that the registers are hot
+ * new_msr tracks the facilities that are to be restored. Only reload
+ * if the bit is not set in the user MSR (if it is set, the registers
+ * are live for the user thread).
*/
- if ((!(msr & MSR_FP)) && restore_fp(current))
- msr |= MSR_FP | current->thread.fpexc_mode;
+ if ((!(msr & MSR_FP)) && should_restore_fp())
+ new_msr |= MSR_FP;
- if ((!(msr & MSR_VEC)) && restore_altivec(current))
- msr |= MSR_VEC;
+ if ((!(msr & MSR_VEC)) && should_restore_altivec())
+ new_msr |= MSR_VEC;
- if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) &&
- restore_vsx(current)) {
- msr |= MSR_VSX;
+ if ((!(msr & MSR_VSX)) && should_restore_vsx()) {
+ if (((msr | new_msr) & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC))
+ new_msr |= MSR_VSX;
}
- msr_check_and_clear(msr_all_available);
+ if (new_msr) {
+ unsigned long fpexc_mode = 0;
- regs->msr = msr;
+ msr_check_and_set(new_msr);
+
+ if (new_msr & MSR_FP) {
+ do_restore_fp();
+
+ // This also covers VSX, because VSX implies FP
+ fpexc_mode = current->thread.fpexc_mode;
+ }
+
+ if (new_msr & MSR_VEC)
+ do_restore_altivec();
+
+ if (new_msr & MSR_VSX)
+ do_restore_vsx();
+
+ msr_check_and_clear(new_msr);
+
+ regs->msr |= new_msr | fpexc_mode;
+ }
}
+#endif /* CONFIG_PPC_BOOK3S_64 */
static void save_all(struct task_struct *tsk)
{
@@ -611,6 +622,44 @@
(void __user *)address);
}
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
+
+static void do_break_handler(struct pt_regs *regs)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ struct arch_hw_breakpoint *info;
+ struct ppc_inst instr = ppc_inst(0);
+ int type = 0;
+ int size = 0;
+ unsigned long ea;
+ int i;
+
+ /*
+ * If underneath hw supports only one watchpoint, we know it
+ * caused exception. 8xx also falls into this category.
+ */
+ if (nr_wp_slots() == 1) {
+ __set_breakpoint(0, &null_brk);
+ current->thread.hw_brk[0] = null_brk;
+ current->thread.hw_brk[0].flags |= HW_BRK_FLAG_DISABLED;
+ return;
+ }
+
+ /* Otherwise findout which DAWR caused exception and disable it. */
+ wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ info = ¤t->thread.hw_brk[i];
+ if (!info->address)
+ continue;
+
+ if (wp_check_constraints(regs, instr, ea, type, size, info)) {
+ __set_breakpoint(i, &null_brk);
+ current->thread.hw_brk[i] = null_brk;
+ current->thread.hw_brk[i].flags |= HW_BRK_FLAG_DISABLED;
+ }
+ }
+}
+
void do_break (struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
@@ -622,15 +671,22 @@
if (debugger_break_match(regs))
return;
- /* Clear the breakpoint */
- hw_breakpoint_disable();
+ /*
+ * We reach here only when watchpoint exception is generated by ptrace
+ * event (or hw is buggy!). Now if CONFIG_HAVE_HW_BREAKPOINT is set,
+ * watchpoint is already handled by hw_breakpoint_handler() so we don't
+ * have to do anything. But when CONFIG_HAVE_HW_BREAKPOINT is not set,
+ * we need to manually handle the watchpoint here.
+ */
+ if (!IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT))
+ do_break_handler(regs);
/* Deliver the signal to userspace */
force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address);
}
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk);
+static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk[HBP_NUM_MAX]);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
/*
@@ -704,19 +760,49 @@
EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
#ifndef CONFIG_HAVE_HW_BREAKPOINT
-static void set_breakpoint(struct arch_hw_breakpoint *brk)
+static void set_breakpoint(int i, struct arch_hw_breakpoint *brk)
{
preempt_disable();
- __set_breakpoint(brk);
+ __set_breakpoint(i, brk);
preempt_enable();
}
static void set_debug_reg_defaults(struct thread_struct *thread)
{
- thread->hw_brk.address = 0;
- thread->hw_brk.type = 0;
- if (ppc_breakpoint_available())
- set_breakpoint(&thread->hw_brk);
+ int i;
+ struct arch_hw_breakpoint null_brk = {0};
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ thread->hw_brk[i] = null_brk;
+ if (ppc_breakpoint_available())
+ set_breakpoint(i, &thread->hw_brk[i]);
+ }
+}
+
+static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
+ struct arch_hw_breakpoint *b)
+{
+ if (a->address != b->address)
+ return false;
+ if (a->type != b->type)
+ return false;
+ if (a->len != b->len)
+ return false;
+ /* no need to check hw_len. it's calculated from address and len */
+ return true;
+}
+
+static void switch_hw_breakpoint(struct task_struct *new)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (likely(hw_brk_match(this_cpu_ptr(¤t_brk[i]),
+ &new->thread.hw_brk[i])))
+ continue;
+
+ __set_breakpoint(i, &new->thread.hw_brk[i]);
+ }
}
#endif /* !CONFIG_HAVE_HW_BREAKPOINT */
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
@@ -725,9 +811,8 @@
static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
{
mtspr(SPRN_DAC1, dabr);
-#ifdef CONFIG_PPC_47x
- isync();
-#endif
+ if (IS_ENABLED(CONFIG_PPC_47x))
+ isync();
return 0;
}
#elif defined(CONFIG_PPC_BOOK3S)
@@ -738,28 +823,6 @@
mtspr(SPRN_DABRX, dabrx);
return 0;
}
-#elif defined(CONFIG_PPC_8xx)
-static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
-{
- unsigned long addr = dabr & ~HW_BRK_TYPE_DABR;
- unsigned long lctrl1 = 0x90000000; /* compare type: equal on E & F */
- unsigned long lctrl2 = 0x8e000002; /* watchpoint 1 on cmp E | F */
-
- if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
- lctrl1 |= 0xa0000;
- else if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
- lctrl1 |= 0xf0000;
- else if ((dabr & HW_BRK_TYPE_RDWR) == 0)
- lctrl2 = 0;
-
- mtspr(SPRN_LCTRL2, 0);
- mtspr(SPRN_CMPE, addr);
- mtspr(SPRN_CMPF, addr + 4);
- mtspr(SPRN_LCTRL1, lctrl1);
- mtspr(SPRN_LCTRL2, lctrl2);
-
- return 0;
-}
#else
static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
{
@@ -780,13 +843,48 @@
return __set_dabr(dabr, dabrx);
}
-void __set_breakpoint(struct arch_hw_breakpoint *brk)
+static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
{
- memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk));
+ unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW |
+ LCTRL1_CRWF_RW;
+ unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN;
+ unsigned long start_addr = ALIGN_DOWN(brk->address, HW_BREAKPOINT_SIZE);
+ unsigned long end_addr = ALIGN(brk->address + brk->len, HW_BREAKPOINT_SIZE);
+
+ if (start_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_F;
+ else if (end_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_E;
+ else
+ lctrl2 |= LCTRL2_LW0LA_EandF;
+
+ mtspr(SPRN_LCTRL2, 0);
+
+ if ((brk->type & HW_BRK_TYPE_RDWR) == 0)
+ return 0;
+
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
+ lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO;
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
+ lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO;
+
+ mtspr(SPRN_CMPE, start_addr - 1);
+ mtspr(SPRN_CMPF, end_addr);
+ mtspr(SPRN_LCTRL1, lctrl1);
+ mtspr(SPRN_LCTRL2, lctrl2);
+
+ return 0;
+}
+
+void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
+{
+ memcpy(this_cpu_ptr(¤t_brk[nr]), brk, sizeof(*brk));
if (dawr_enabled())
// Power8 or later
- set_dawr(brk);
+ set_dawr(nr, brk);
+ else if (IS_ENABLED(CONFIG_PPC_8xx))
+ set_breakpoint_8xx(brk);
else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
// Power7 or earlier
set_dabr(brk);
@@ -807,18 +905,6 @@
}
EXPORT_SYMBOL_GPL(ppc_breakpoint_available);
-static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
- struct arch_hw_breakpoint *b)
-{
- if (a->address != b->address)
- return false;
- if (a->type != b->type)
- return false;
- if (a->len != b->len)
- return false;
- return true;
-}
-
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static inline bool tm_enabled(struct task_struct *tsk)
@@ -1141,6 +1227,19 @@
__flush_tlb_pending(batch);
batch->active = 0;
}
+
+ /*
+ * On POWER9 the copy-paste buffer can only paste into
+ * foreign real addresses, so unprivileged processes can not
+ * see the data or use it in any way unless they have
+ * foreign real mappings. If the new process has the foreign
+ * real address mappings, we must issue a cp_abort to clear
+ * any state and prevent snooping, corruption or a covert
+ * channel. ISA v3.1 supports paste into local memory.
+ */
+ if (new->mm && (cpu_has_feature(CPU_FTR_ARCH_31) ||
+ atomic_read(&new->mm->context.vas_windows)))
+ asm volatile(PPC_CP_ABORT);
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -1151,8 +1250,7 @@
* schedule DABR
*/
#ifndef CONFIG_HAVE_HW_BREAKPOINT
- if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk)))
- __set_breakpoint(&new->thread.hw_brk);
+ switch_hw_breakpoint(new);
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
#endif
@@ -1187,27 +1285,33 @@
last = _switch(old_thread, new_thread);
+ /*
+ * Nothing after _switch will be run for newly created tasks,
+ * because they switch directly to ret_from_fork/ret_from_kernel_thread
+ * etc. Code added here should have a comment explaining why that is
+ * okay.
+ */
+
#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * This applies to a process that was context switched while inside
+ * arch_enter_lazy_mmu_mode(), to re-activate the batch that was
+ * deactivated above, before _switch(). This will never be the case
+ * for new tasks.
+ */
if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
batch = this_cpu_ptr(&ppc64_tlb_batch);
batch->active = 1;
}
- if (current->thread.regs) {
+ /*
+ * Math facilities are masked out of the child MSR in copy_thread.
+ * A new task does not need to restore_math because it will
+ * demand fault them.
+ */
+ if (current->thread.regs)
restore_math(current->thread.regs);
-
- /*
- * The copy-paste buffer can only store into foreign real
- * addresses, so unprivileged processes can not see the
- * data or use it in any way unless they have foreign real
- * mappings. If the new process has the foreign real address
- * mappings, we must issue a cp_abort to clear any state and
- * prevent snooping, corruption or a covert channel.
- */
- if (current->thread.used_vas)
- asm volatile(PPC_CP_ABORT);
- }
#endif /* CONFIG_PPC_BOOK3S_64 */
return last;
@@ -1239,7 +1343,7 @@
pr_cont("\n");
if (!__kernel_text_address(pc) ||
- probe_kernel_address((const void *)pc, instr)) {
+ get_kernel_nofault(instr, (const void *)pc)) {
pr_cont("XXXXXXXX ");
} else {
if (nip == pc)
@@ -1263,16 +1367,6 @@
pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
- /*
- * Make sure the NIP points at userspace, not kernel text/data or
- * elsewhere.
- */
- if (!__access_ok(pc, NR_INSN_TO_PRINT * sizeof(int), USER_DS)) {
- pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
- current->comm, current->pid);
- return;
- }
-
seq_buf_init(&s, buf, sizeof(buf));
while (n) {
@@ -1283,7 +1377,8 @@
for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
int instr;
- if (probe_kernel_address((const void *)pc, instr)) {
+ if (copy_from_user_nofault(&instr, (void __user *)pc,
+ sizeof(instr))) {
seq_buf_printf(&s, "XXXXXXXX ");
continue;
}
@@ -1401,14 +1496,15 @@
print_msr_bits(regs->msr);
pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer);
trap = TRAP(regs);
- if ((TRAP(regs) != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
+ if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR))
pr_cont("CFAR: "REG" ", regs->orig_gpr3);
- if (trap == 0x200 || trap == 0x300 || trap == 0x600)
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
- pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
-#else
- pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
-#endif
+ if (trap == 0x200 || trap == 0x300 || trap == 0x600) {
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+ else
+ pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+ }
+
#ifdef CONFIG_PPC64
pr_cont("IRQMASK: %lx ", regs->softe);
#endif
@@ -1425,15 +1521,15 @@
break;
}
pr_cont("\n");
-#ifdef CONFIG_KALLSYMS
/*
* Lookup NIP late so we have the best change of getting the
* above info out without failing
*/
- printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
- printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
-#endif
- show_stack(current, (unsigned long *) regs->gpr[1]);
+ if (IS_ENABLED(CONFIG_KALLSYMS)) {
+ printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
+ printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
+ }
+ show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT);
if (!user_mode(regs))
show_instructions(regs);
}
@@ -1456,27 +1552,6 @@
}
#endif
-int set_thread_uses_vas(void)
-{
-#ifdef CONFIG_PPC_BOOK3S_64
- if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -EINVAL;
-
- current->thread.used_vas = 1;
-
- /*
- * Even a process that has no foreign real address mapping can use
- * an unpaired COPY instruction (to no real effect). Issue CP_ABORT
- * to clear any pending COPY and prevent a covert channel.
- *
- * __switch_to() will issue CP_ABORT on future context switches.
- */
- asm volatile(PPC_CP_ABORT);
-
-#endif /* CONFIG_PPC_BOOK3S_64 */
- return 0;
-}
-
#ifdef CONFIG_PPC64
/**
* Assign a TIDR (thread ID) for task @t and set it in the thread
@@ -1589,16 +1664,20 @@
/*
* Copy architecture-specific thread state
*/
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long kthread_arg, struct task_struct *p,
unsigned long tls)
{
struct pt_regs *childregs, *kregs;
extern void ret_from_fork(void);
+ extern void ret_from_fork_scv(void);
extern void ret_from_kernel_thread(void);
void (*f)(void);
unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
struct thread_info *ti = task_thread_info(p);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int i;
+#endif
klp_init_thread_info(p);
@@ -1628,17 +1707,20 @@
if (usp)
childregs->gpr[1] = usp;
p->thread.regs = childregs;
- childregs->gpr[3] = 0; /* Result from fork() */
+ /* 64s sets this in ret_from_fork */
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ childregs->gpr[3] = 0; /* Result from fork() */
if (clone_flags & CLONE_SETTLS) {
-#ifdef CONFIG_PPC64
if (!is_32bit_task())
childregs->gpr[13] = tls;
else
-#endif
childregs->gpr[2] = tls;
}
- f = ret_from_fork;
+ if (trap_is_scv(regs))
+ f = ret_from_fork_scv;
+ else
+ f = ret_from_fork;
}
childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
sp -= STACK_FRAME_OVERHEAD;
@@ -1660,7 +1742,8 @@
p->thread.ksp_limit = (unsigned long)end_of_stack(p);
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
- p->thread.ptrace_bps[0] = NULL;
+ for (i = 0; i < nr_wp_slots(); i++)
+ p->thread.ptrace_bps[i] = NULL;
#endif
p->thread.fp_save_area = NULL;
@@ -1694,11 +1777,9 @@
#ifdef CONFIG_PPC64
unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */
-#ifdef CONFIG_PPC_BOOK3S_64
- if (!radix_enabled())
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
preload_new_slb_context(start, sp);
#endif
-#endif
/*
* If we exec out of a kernel thread then thread.regs will not be
@@ -1731,7 +1812,7 @@
* FULL_REGS(regs) return true. This is necessary to allow
* ptrace to examine the thread immediately after exec.
*/
- regs->trap &= ~1UL;
+ SET_FULL_REGS(regs);
#ifdef CONFIG_PPC32
regs->mq = 0;
@@ -1829,7 +1910,6 @@
* fpexc_mode. fpexc_mode is also used for setting FP exception
* mode (asyn, precise, disabled) for 'Classic' FP. */
if (val & PR_FP_EXC_SW_ENABLE) {
-#ifdef CONFIG_SPE
if (cpu_has_feature(CPU_FTR_SPE)) {
/*
* When the sticky exception bits are set
@@ -1843,16 +1923,15 @@
* anyway to restore the prctl settings from
* the saved environment.
*/
+#ifdef CONFIG_SPE
tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
tsk->thread.fpexc_mode = val &
(PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
+#endif
return 0;
} else {
return -EINVAL;
}
-#else
- return -EINVAL;
-#endif
}
/* on a CONFIG_SPE this does not hurt us. The bits that
@@ -1871,10 +1950,9 @@
int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
{
- unsigned int val;
+ unsigned int val = 0;
- if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
-#ifdef CONFIG_SPE
+ if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) {
if (cpu_has_feature(CPU_FTR_SPE)) {
/*
* When the sticky exception bits are set
@@ -1888,15 +1966,15 @@
* anyway to restore the prctl settings from
* the saved environment.
*/
+#ifdef CONFIG_SPE
tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
val = tsk->thread.fpexc_mode;
+#endif
} else
return -EINVAL;
-#else
- return -EINVAL;
-#endif
- else
+ } else {
val = __unpack_fe01(tsk->thread.fpexc_mode);
+ }
return put_user(val, (unsigned int __user *) adr);
}
@@ -1972,6 +2050,32 @@
return 0;
}
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+#ifdef CONFIG_PPC64
+ unsigned long stack_page;
+ unsigned long cpu = task_cpu(p);
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+ stack_page = (unsigned long)paca_ptrs[cpu]->nmi_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->mc_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+# endif
+#endif
+
+ return 0;
+}
+
+
int validate_sp(unsigned long sp, struct task_struct *p,
unsigned long nbytes)
{
@@ -1983,7 +2087,10 @@
if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
- return valid_irq_stack(sp, p, nbytes);
+ if (valid_irq_stack(sp, p, nbytes))
+ return 1;
+
+ return valid_emergency_stack(sp, p, nbytes);
}
EXPORT_SYMBOL(validate_sp);
@@ -2030,15 +2137,14 @@
static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
-void show_stack(struct task_struct *tsk, unsigned long *stack)
+void show_stack(struct task_struct *tsk, unsigned long *stack,
+ const char *loglvl)
{
unsigned long sp, ip, lr, newsp;
int count = 0;
int firstframe = 1;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long ret_addr;
int ftrace_idx = 0;
-#endif
if (tsk == NULL)
tsk = current;
@@ -2049,13 +2155,13 @@
sp = (unsigned long) stack;
if (sp == 0) {
if (tsk == current)
- sp = current_stack_pointer();
+ sp = current_stack_frame();
else
sp = tsk->thread.ksp;
}
lr = 0;
- printk("Call Trace:\n");
+ printk("%sCall Trace:\n", loglvl);
do {
if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
break;
@@ -2064,13 +2170,12 @@
newsp = stack[0];
ip = stack[STACK_FRAME_LR_SAVE];
if (!firstframe || ip != lr) {
- printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ printk("%s["REG"] ["REG"] %pS",
+ loglvl, sp, ip, (void *)ip);
ret_addr = ftrace_graph_ret_addr(current,
&ftrace_idx, ip, stack);
if (ret_addr != ip)
pr_cont(" (%pS)", (void *)ret_addr);
-#endif
if (firstframe)
pr_cont(" (unreliable)");
pr_cont("\n");
@@ -2086,8 +2191,9 @@
struct pt_regs *regs = (struct pt_regs *)
(sp + STACK_FRAME_OVERHEAD);
lr = regs->link;
- printk("--- interrupt: %lx at %pS\n LR = %pS\n",
- regs->trap, (void *)regs->nip, (void *)lr);
+ printk("%s--- interrupt: %lx at %pS\n LR = %pS\n",
+ loglvl, regs->trap,
+ (void *)regs->nip, (void *)lr);
firstframe = 1;
}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 537142b..7a14a09 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -30,6 +30,7 @@
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/cpu.h>
+#include <linux/pgtable.h>
#include <asm/prom.h>
#include <asm/rtas.h>
@@ -41,7 +42,6 @@
#include <asm/smp.h>
#include <asm/mmu.h>
#include <asm/paca.h>
-#include <asm/pgtable.h>
#include <asm/powernv.h>
#include <asm/iommu.h>
#include <asm/btext.h>
@@ -96,8 +96,8 @@
if (!initrd_start)
return 0;
- return (start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
- start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
+ return (start + size) > ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
+ start <= ALIGN(initrd_end, PAGE_SIZE);
#else
return 0;
#endif
@@ -163,7 +163,7 @@
{ .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 },
+ { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE },
#endif
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
@@ -175,6 +175,8 @@
*/
{ .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 },
};
static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -468,8 +470,9 @@
* This contains a list of memory blocks along with NUMA affinity
* information.
*/
-static void __init early_init_drmem_lmb(struct drmem_lmb *lmb,
- const __be32 **usm)
+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;
@@ -484,7 +487,7 @@
*/
if ((lmb->flags & DRCONF_MEM_RESERVED) ||
!(lmb->flags & DRCONF_MEM_ASSIGNED))
- return;
+ return 0;
if (*usm)
is_kexec_kdump = 1;
@@ -499,7 +502,7 @@
*/
rngs = dt_mem_next_cell(dt_root_size_cells, usm);
if (!rngs) /* there are no (base, size) duple */
- return;
+ return 0;
}
do {
@@ -515,10 +518,17 @@
size = 0x80000000ul - base;
}
+ if (!validate_mem_limit(base, &size))
+ continue;
+
DBG("Adding: %llx -> %llx\n", base, size);
- if (validate_mem_limit(base, &size))
- memblock_add(base, size);
+ memblock_add(base, size);
+
+ if (lmb->flags & DRCONF_MEM_HOTREMOVABLE)
+ memblock_mark_hotplug(base, size);
} while (--rngs);
+
+ return 0;
}
#endif /* CONFIG_PPC_PSERIES */
@@ -529,7 +539,7 @@
#ifdef CONFIG_PPC_PSERIES
if (depth == 1 &&
strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) {
- walk_drmem_lmbs_early(node, early_init_drmem_lmb);
+ walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb);
return 0;
}
#endif
@@ -623,9 +633,9 @@
#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_UP(initrd_end, PAGE_SIZE) -
- _ALIGN_DOWN(initrd_start, PAGE_SIZE));
+ 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 */
@@ -766,6 +776,11 @@
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_allow_resize();
memblock_dump_all();
@@ -810,6 +825,11 @@
/* 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"))
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1b65fb7..9e71c07 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -26,6 +26,7 @@
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/bitops.h>
+#include <linux/pgtable.h>
#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/page.h>
@@ -34,7 +35,6 @@
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
@@ -45,7 +45,7 @@
#include <linux/linux_logo.h>
/* All of prom_init bss lives here */
-#define __prombss __section(.bss.prominit)
+#define __prombss __section(".bss.prominit")
/*
* Eventually bump that one up
@@ -169,6 +169,7 @@
#ifdef CONFIG_PPC_PSERIES
static bool __prombss prom_radix_disable;
+static bool __prombss prom_radix_gtse_disable;
static bool __prombss prom_xive_disable;
#endif
@@ -303,16 +304,24 @@
return NULL;
}
-static size_t __init prom_strlcpy(char *dest, const char *src, size_t size)
+static size_t __init prom_strlcat(char *dest, const char *src, size_t count)
{
- size_t ret = prom_strlen(src);
+ size_t dsize = prom_strlen(dest);
+ size_t len = prom_strlen(src);
+ size_t res = dsize + len;
- if (size) {
- size_t len = (ret >= size) ? size - 1 : ret;
- memcpy(dest, src, len);
- dest[len] = '\0';
- }
- return ret;
+ /* This would be a bug */
+ if (dsize >= count)
+ return count;
+
+ dest += dsize;
+ count -= dsize;
+ if (len >= count)
+ len = count-1;
+ memcpy(dest, src, len);
+ dest[len] = 0;
+ return res;
+
}
#ifdef CONFIG_PPC_PSERIES
@@ -764,10 +773,14 @@
prom_cmd_line[0] = 0;
p = prom_cmd_line;
- if ((long)prom.chosen > 0)
+
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && (long)prom.chosen > 0)
l = prom_getprop(prom.chosen, "bootargs", p, COMMAND_LINE_SIZE-1);
- if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && (l <= 0 || p[0] == '\0')) /* dbl check */
- prom_strlcpy(prom_cmd_line, CONFIG_CMDLINE, sizeof(prom_cmd_line));
+
+ if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || l <= 0 || p[0] == '\0')
+ prom_strlcat(prom_cmd_line, " " CONFIG_CMDLINE,
+ sizeof(prom_cmd_line));
+
prom_printf("command line: %s\n", prom_cmd_line);
#ifdef CONFIG_PPC64
@@ -811,6 +824,12 @@
if (prom_radix_disable)
prom_debug("Radix disabled from cmdline\n");
+ opt = prom_strstr(prom_cmd_line, "radix_hcall_invalidate=on");
+ if (opt) {
+ prom_radix_gtse_disable = true;
+ prom_debug("Radix GTSE disabled from cmdline\n");
+ }
+
opt = prom_strstr(prom_cmd_line, "xive=off");
if (opt) {
prom_xive_disable = true;
@@ -908,7 +927,7 @@
} __packed;
struct ibm_arch_vec {
- struct { u32 mask, val; } pvrs[12];
+ struct { u32 mask, val; } pvrs[14];
u8 num_vectors;
@@ -962,6 +981,14 @@
.val = cpu_to_be32(0x004e0000),
},
{
+ .mask = cpu_to_be32(0xffff0000), /* POWER10 */
+ .val = cpu_to_be32(0x00800000),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 3.1-compliant */
+ .val = cpu_to_be32(0x0f000006),
+ },
+ {
.mask = cpu_to_be32(0xffffffff), /* all 3.00-compliant */
.val = cpu_to_be32(0x0f000005),
},
@@ -990,7 +1017,7 @@
.byte1 = 0,
.arch_versions = OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 |
OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07,
- .arch_versions3 = OV1_PPC_3_00,
+ .arch_versions3 = OV1_PPC_3_00 | OV1_PPC_3_1,
},
.vec2_len = VECTOR_LENGTH(sizeof(struct option_vector2)),
@@ -1265,10 +1292,8 @@
prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
break;
case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
- if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
- prom_debug("Radix - GTSE supported\n");
- support->radix_gtse = true;
- }
+ if (val & OV5_FEAT(OV5_RADIX_GTSE))
+ support->radix_gtse = !prom_radix_gtse_disable;
break;
case OV5_INDX(OV5_XIVE_SUPPORT): /* Interrupt mode */
prom_parse_xive_model(val & OV5_FEAT(OV5_XIVE_SUPPORT),
@@ -1312,12 +1337,15 @@
}
}
- if (supported.radix_mmu && supported.radix_gtse &&
- IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
- /* Radix preferred - but we require GTSE for now */
- prom_debug("Asking for radix with GTSE\n");
+ if (supported.radix_mmu && IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
+ /* Radix preferred - Check if GTSE is also supported */
+ prom_debug("Asking for radix\n");
ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
- ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+ if (supported.radix_gtse)
+ ibm_architecture_vec.vec5.radix_ext =
+ OV5_FEAT(OV5_RADIX_GTSE);
+ else
+ prom_debug("Radix GTSE isn't supported\n");
} else if (supported.hash_mmu) {
/* Default to hash mmu (if we can) */
prom_debug("Asking for hash\n");
@@ -1433,18 +1461,18 @@
unsigned long addr = 0;
if (align)
- base = _ALIGN_UP(base, align);
+ base = ALIGN(base, align);
prom_debug("%s(%lx, %lx)\n", __func__, size, align);
if (ram_top == 0)
prom_panic("alloc_up() called with mem not initialized\n");
if (align)
- base = _ALIGN_UP(alloc_bottom, align);
+ base = ALIGN(alloc_bottom, align);
else
base = alloc_bottom;
for(; (base + size) <= alloc_top;
- base = _ALIGN_UP(base + 0x100000, align)) {
+ base = ALIGN(base + 0x100000, align)) {
prom_debug(" trying: 0x%lx\n\r", base);
addr = (unsigned long)prom_claim(base, size, 0);
if (addr != PROM_ERROR && addr != 0)
@@ -1484,7 +1512,7 @@
if (highmem) {
/* Carve out storage for the TCE table. */
- addr = _ALIGN_DOWN(alloc_top_high - size, align);
+ addr = ALIGN_DOWN(alloc_top_high - size, align);
if (addr <= alloc_bottom)
return 0;
/* Will we bump into the RMO ? If yes, check out that we
@@ -1502,9 +1530,9 @@
goto bail;
}
- base = _ALIGN_DOWN(alloc_top - size, align);
+ base = ALIGN_DOWN(alloc_top - size, align);
for (; base > alloc_bottom;
- base = _ALIGN_DOWN(base - 0x100000, align)) {
+ base = ALIGN_DOWN(base - 0x100000, align)) {
prom_debug(" trying: 0x%lx\n\r", base);
addr = (unsigned long)prom_claim(base, size, 0);
if (addr != PROM_ERROR && addr != 0)
@@ -1570,8 +1598,8 @@
* have our terminator with "size" set to 0 since we are
* dumb and just copy this entire array to the boot params
*/
- base = _ALIGN_DOWN(base, PAGE_SIZE);
- top = _ALIGN_UP(top, PAGE_SIZE);
+ base = ALIGN_DOWN(base, PAGE_SIZE);
+ top = ALIGN(top, PAGE_SIZE);
size = top - base;
if (cnt >= (MEM_RESERVE_MAP_SIZE - 1))
@@ -2390,10 +2418,19 @@
u32 width, height, pitch, addr;
prom_printf("Setting btext !\n");
- prom_getprop(node, "width", &width, 4);
- prom_getprop(node, "height", &height, 4);
- prom_getprop(node, "linebytes", &pitch, 4);
- prom_getprop(node, "address", &addr, 4);
+
+ if (prom_getprop(node, "width", &width, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "height", &height, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "linebytes", &pitch, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "address", &addr, 4) == PROM_ERROR)
+ return;
+
prom_printf("W=%d H=%d LB=%d addr=0x%x\n",
width, height, pitch, addr);
btext_setup_display(width, height, 8, pitch, addr);
@@ -2410,7 +2447,7 @@
{
void *ret;
- *mem_start = _ALIGN(*mem_start, align);
+ *mem_start = ALIGN(*mem_start, align);
while ((*mem_start + needed) > *mem_end) {
unsigned long room, chunk;
@@ -2546,7 +2583,7 @@
*lp++ = *p;
}
*lp = 0;
- *mem_start = _ALIGN((unsigned long)lp + 1, 4);
+ *mem_start = ALIGN((unsigned long)lp + 1, 4);
}
/* get it again for debugging */
@@ -2592,7 +2629,7 @@
/* push property content */
valp = make_room(mem_start, mem_end, l, 4);
call_prom("getprop", 4, 1, node, pname, valp, l);
- *mem_start = _ALIGN(*mem_start, 4);
+ *mem_start = ALIGN(*mem_start, 4);
if (!prom_strcmp(pname, "phandle"))
has_phandle = 1;
@@ -2651,7 +2688,7 @@
prom_panic ("couldn't get device tree root\n");
/* Build header and make room for mem rsv map */
- mem_start = _ALIGN(mem_start, 4);
+ mem_start = ALIGN(mem_start, 4);
hdr = make_room(&mem_start, &mem_end,
sizeof(struct boot_param_header), 4);
dt_header_start = (unsigned long)hdr;
@@ -2919,7 +2956,7 @@
/* Check if the phy-handle property exists - bail if it does */
rv = prom_getprop(node, "phy-handle", prop, sizeof(prop));
- if (!rv)
+ if (rv <= 0)
return;
/*
@@ -3238,7 +3275,7 @@
/*
* Call the Ultravisor to transfer us to secure memory if we have an ESM blob.
*/
-static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
+static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt)
{
int ret;
@@ -3268,7 +3305,7 @@
}
}
#else
-static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
+static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt)
{
}
#endif /* CONFIG_PPC_SVM */
@@ -3461,7 +3498,6 @@
*/
hdr = dt_header_start;
- /* Don't print anything after quiesce under OPAL, it crashes OFW */
prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
prom_debug("->dt_header_start=0x%lx\n", hdr);
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
deleted file mode 100644
index 8c92feb..0000000
--- a/arch/powerpc/kernel/ptrace.c
+++ /dev/null
@@ -1,3401 +0,0 @@
-/*
- * PowerPC version
- * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- * Derived from "arch/m68k/kernel/ptrace.c"
- * Copyright (C) 1994 by Hamish Macdonald
- * Taken from linux/kernel/ptrace.c and modified for M680x0.
- * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
- *
- * Modified by Cort Dougan (cort@hq.fsmlabs.com)
- * and Paul Mackerras (paulus@samba.org).
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file README.legal in the main directory of
- * this archive for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/regset.h>
-#include <linux/tracehook.h>
-#include <linux/elf.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/signal.h>
-#include <linux/seccomp.h>
-#include <linux/audit.h>
-#include <trace/syscall.h>
-#include <linux/hw_breakpoint.h>
-#include <linux/perf_event.h>
-#include <linux/context_tracking.h>
-#include <linux/nospec.h>
-
-#include <linux/uaccess.h>
-#include <linux/pkeys.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/switch_to.h>
-#include <asm/tm.h>
-#include <asm/asm-prototypes.h>
-#include <asm/debug.h>
-#include <asm/hw_breakpoint.h>
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
-/*
- * The parameter save area on the stack is used to store arguments being passed
- * to callee function and is located at fixed offset from stack pointer.
- */
-#ifdef CONFIG_PPC32
-#define PARAMETER_SAVE_AREA_OFFSET 24 /* bytes */
-#else /* CONFIG_PPC32 */
-#define PARAMETER_SAVE_AREA_OFFSET 48 /* bytes */
-#endif
-
-struct pt_regs_offset {
- const char *name;
- int offset;
-};
-
-#define STR(s) #s /* convert to string */
-#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
-#define GPR_OFFSET_NAME(num) \
- {.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
- {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
-#define REG_OFFSET_END {.name = NULL, .offset = 0}
-
-#define TVSO(f) (offsetof(struct thread_vr_state, f))
-#define TFSO(f) (offsetof(struct thread_fp_state, f))
-#define TSO(f) (offsetof(struct thread_struct, f))
-
-static const struct pt_regs_offset regoffset_table[] = {
- GPR_OFFSET_NAME(0),
- GPR_OFFSET_NAME(1),
- GPR_OFFSET_NAME(2),
- GPR_OFFSET_NAME(3),
- GPR_OFFSET_NAME(4),
- GPR_OFFSET_NAME(5),
- GPR_OFFSET_NAME(6),
- GPR_OFFSET_NAME(7),
- GPR_OFFSET_NAME(8),
- GPR_OFFSET_NAME(9),
- GPR_OFFSET_NAME(10),
- GPR_OFFSET_NAME(11),
- GPR_OFFSET_NAME(12),
- GPR_OFFSET_NAME(13),
- GPR_OFFSET_NAME(14),
- GPR_OFFSET_NAME(15),
- GPR_OFFSET_NAME(16),
- GPR_OFFSET_NAME(17),
- GPR_OFFSET_NAME(18),
- GPR_OFFSET_NAME(19),
- GPR_OFFSET_NAME(20),
- GPR_OFFSET_NAME(21),
- GPR_OFFSET_NAME(22),
- GPR_OFFSET_NAME(23),
- GPR_OFFSET_NAME(24),
- GPR_OFFSET_NAME(25),
- GPR_OFFSET_NAME(26),
- GPR_OFFSET_NAME(27),
- GPR_OFFSET_NAME(28),
- GPR_OFFSET_NAME(29),
- GPR_OFFSET_NAME(30),
- GPR_OFFSET_NAME(31),
- REG_OFFSET_NAME(nip),
- REG_OFFSET_NAME(msr),
- REG_OFFSET_NAME(ctr),
- REG_OFFSET_NAME(link),
- REG_OFFSET_NAME(xer),
- REG_OFFSET_NAME(ccr),
-#ifdef CONFIG_PPC64
- REG_OFFSET_NAME(softe),
-#else
- REG_OFFSET_NAME(mq),
-#endif
- REG_OFFSET_NAME(trap),
- REG_OFFSET_NAME(dar),
- REG_OFFSET_NAME(dsisr),
- REG_OFFSET_END,
-};
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static void flush_tmregs_to_thread(struct task_struct *tsk)
-{
- /*
- * If task is not current, it will have been flushed already to
- * it's thread_struct during __switch_to().
- *
- * A reclaim flushes ALL the state or if not in TM save TM SPRs
- * in the appropriate thread structures from live.
- */
-
- if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
- return;
-
- if (MSR_TM_SUSPENDED(mfmsr())) {
- tm_reclaim_current(TM_CAUSE_SIGNAL);
- } else {
- tm_enable();
- tm_save_sprs(&(tsk->thread));
- }
-}
-#else
-static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
-#endif
-
-/**
- * regs_query_register_offset() - query register offset from its name
- * @name: the name of a register
- *
- * regs_query_register_offset() returns the offset of a register in struct
- * pt_regs from its name. If the name is invalid, this returns -EINVAL;
- */
-int regs_query_register_offset(const char *name)
-{
- const struct pt_regs_offset *roff;
- for (roff = regoffset_table; roff->name != NULL; roff++)
- if (!strcmp(roff->name, name))
- return roff->offset;
- return -EINVAL;
-}
-
-/**
- * regs_query_register_name() - query register name from its offset
- * @offset: the offset of a register in struct pt_regs.
- *
- * regs_query_register_name() returns the name of a register from its
- * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
- */
-const char *regs_query_register_name(unsigned int offset)
-{
- const struct pt_regs_offset *roff;
- for (roff = regoffset_table; roff->name != NULL; roff++)
- if (roff->offset == offset)
- return roff->name;
- return NULL;
-}
-
-/*
- * does not yet catch signals sent when the child dies.
- * in exit.c or in signal.c.
- */
-
-/*
- * Set of msr bits that gdb can change on behalf of a process.
- */
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-#define MSR_DEBUGCHANGE 0
-#else
-#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE)
-#endif
-
-/*
- * Max register writeable via put_reg
- */
-#ifdef CONFIG_PPC32
-#define PT_MAX_PUT_REG PT_MQ
-#else
-#define PT_MAX_PUT_REG PT_CCR
-#endif
-
-static unsigned long get_user_msr(struct task_struct *task)
-{
- return task->thread.regs->msr | task->thread.fpexc_mode;
-}
-
-static int set_user_msr(struct task_struct *task, unsigned long msr)
-{
- task->thread.regs->msr &= ~MSR_DEBUGCHANGE;
- task->thread.regs->msr |= msr & MSR_DEBUGCHANGE;
- return 0;
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static unsigned long get_user_ckpt_msr(struct task_struct *task)
-{
- return task->thread.ckpt_regs.msr | task->thread.fpexc_mode;
-}
-
-static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr)
-{
- task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE;
- task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE;
- return 0;
-}
-
-static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap)
-{
- task->thread.ckpt_regs.trap = trap & 0xfff0;
- return 0;
-}
-#endif
-
-#ifdef CONFIG_PPC64
-static int get_user_dscr(struct task_struct *task, unsigned long *data)
-{
- *data = task->thread.dscr;
- return 0;
-}
-
-static int set_user_dscr(struct task_struct *task, unsigned long dscr)
-{
- task->thread.dscr = dscr;
- task->thread.dscr_inherit = 1;
- return 0;
-}
-#else
-static int get_user_dscr(struct task_struct *task, unsigned long *data)
-{
- return -EIO;
-}
-
-static int set_user_dscr(struct task_struct *task, unsigned long dscr)
-{
- return -EIO;
-}
-#endif
-
-/*
- * We prevent mucking around with the reserved area of trap
- * which are used internally by the kernel.
- */
-static int set_user_trap(struct task_struct *task, unsigned long trap)
-{
- task->thread.regs->trap = trap & 0xfff0;
- return 0;
-}
-
-/*
- * Get contents of register REGNO in task TASK.
- */
-int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
-{
- unsigned int regs_max;
-
- if ((task->thread.regs == NULL) || !data)
- return -EIO;
-
- if (regno == PT_MSR) {
- *data = get_user_msr(task);
- return 0;
- }
-
- if (regno == PT_DSCR)
- return get_user_dscr(task, data);
-
-#ifdef CONFIG_PPC64
- /*
- * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
- * no more used as a flag, lets force usr to alway see the softe value as 1
- * which means interrupts are not soft disabled.
- */
- if (regno == PT_SOFTE) {
- *data = 1;
- return 0;
- }
-#endif
-
- regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
- if (regno < regs_max) {
- regno = array_index_nospec(regno, regs_max);
- *data = ((unsigned long *)task->thread.regs)[regno];
- return 0;
- }
-
- return -EIO;
-}
-
-/*
- * Write contents of register REGNO in task TASK.
- */
-int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
-{
- if (task->thread.regs == NULL)
- return -EIO;
-
- if (regno == PT_MSR)
- return set_user_msr(task, data);
- if (regno == PT_TRAP)
- return set_user_trap(task, data);
- if (regno == PT_DSCR)
- return set_user_dscr(task, data);
-
- if (regno <= PT_MAX_PUT_REG) {
- regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
- ((unsigned long *)task->thread.regs)[regno] = data;
- return 0;
- }
- return -EIO;
-}
-
-static int gpr_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int i, ret;
-
- if (target->thread.regs == NULL)
- return -EIO;
-
- if (!FULL_REGS(target->thread.regs)) {
- /* We have a partial register set. Fill 14-31 with bogus values */
- for (i = 14; i < 32; i++)
- target->thread.regs->gpr[i] = NV_REG_POISON;
- }
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- target->thread.regs,
- 0, offsetof(struct pt_regs, msr));
- if (!ret) {
- unsigned long msr = get_user_msr(target);
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
- offsetof(struct pt_regs, msr),
- offsetof(struct pt_regs, msr) +
- sizeof(msr));
- }
-
- BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
- offsetof(struct pt_regs, msr) + sizeof(long));
-
- if (!ret)
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.regs->orig_gpr3,
- offsetof(struct pt_regs, orig_gpr3),
- sizeof(struct user_pt_regs));
- if (!ret)
- ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
- sizeof(struct user_pt_regs), -1);
-
- return ret;
-}
-
-static int gpr_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- unsigned long reg;
- int ret;
-
- if (target->thread.regs == NULL)
- return -EIO;
-
- CHECK_FULL_REGS(target->thread.regs);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- target->thread.regs,
- 0, PT_MSR * sizeof(reg));
-
- if (!ret && count > 0) {
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
- PT_MSR * sizeof(reg),
- (PT_MSR + 1) * sizeof(reg));
- if (!ret)
- ret = set_user_msr(target, reg);
- }
-
- BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
- offsetof(struct pt_regs, msr) + sizeof(long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.regs->orig_gpr3,
- PT_ORIG_R3 * sizeof(reg),
- (PT_MAX_PUT_REG + 1) * sizeof(reg));
-
- if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
- ret = user_regset_copyin_ignore(
- &pos, &count, &kbuf, &ubuf,
- (PT_MAX_PUT_REG + 1) * sizeof(reg),
- PT_TRAP * sizeof(reg));
-
- if (!ret && count > 0) {
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
- PT_TRAP * sizeof(reg),
- (PT_TRAP + 1) * sizeof(reg));
- if (!ret)
- ret = set_user_trap(target, reg);
- }
-
- if (!ret)
- ret = user_regset_copyin_ignore(
- &pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
-
- return ret;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last checkpointed
- * value of all FPR registers for the current transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * u64 fpr[32];
- * u64 fpscr;
- * };
- */
-static int fpr_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
-#ifdef CONFIG_VSX
- u64 buf[33];
- int i;
-
- flush_fp_to_thread(target);
-
- /* copy to local buffer then write that out */
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.TS_FPR(i);
- buf[32] = target->thread.fp_state.fpscr;
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-#else
- BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32]));
-
- flush_fp_to_thread(target);
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fp_state, 0, -1);
-#endif
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last checkpointed
- * value of all FPR registers for the current transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * u64 fpr[32];
- * u64 fpscr;
- * };
- *
- */
-static int fpr_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
-#ifdef CONFIG_VSX
- u64 buf[33];
- int i;
-
- flush_fp_to_thread(target);
-
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.TS_FPR(i);
- buf[32] = target->thread.fp_state.fpscr;
-
- /* copy to local buffer then write that out */
- i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
- if (i)
- return i;
-
- for (i = 0; i < 32 ; i++)
- target->thread.TS_FPR(i) = buf[i];
- target->thread.fp_state.fpscr = buf[32];
- return 0;
-#else
- BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32]));
-
- flush_fp_to_thread(target);
-
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fp_state, 0, -1);
-#endif
-}
-
-#ifdef CONFIG_ALTIVEC
-/*
- * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go.
- * The transfer totals 34 quadword. Quadwords 0-31 contain the
- * corresponding vector registers. Quadword 32 contains the vscr as the
- * last word (offset 12) within that quadword. Quadword 33 contains the
- * vrsave as the first word (offset 0) within the quadword.
- *
- * This definition of the VMX state is compatible with the current PPC32
- * ptrace interface. This allows signal handling and ptrace to use the
- * same structures. This also simplifies the implementation of a bi-arch
- * (combined (32- and 64-bit) gdb.
- */
-
-static int vr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- flush_altivec_to_thread(target);
- return target->thread.used_vr ? regset->n : 0;
-}
-
-/*
- * Regardless of transactions, 'vr_state' holds the current running
- * value of all the VMX registers and 'ckvr_state' holds the last
- * checkpointed value of all the VMX registers for the current
- * transaction to fall back on in case it aborts.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * vector128 vr[32];
- * vector128 vscr;
- * vector128 vrsave;
- * };
- */
-static int vr_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- flush_altivec_to_thread(target);
-
- BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
- offsetof(struct thread_vr_state, vr[32]));
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.vr_state, 0,
- 33 * sizeof(vector128));
- if (!ret) {
- /*
- * Copy out only the low-order word of vrsave.
- */
- int start, end;
- union {
- elf_vrreg_t reg;
- u32 word;
- } vrsave;
- memset(&vrsave, 0, sizeof(vrsave));
-
- vrsave.word = target->thread.vrsave;
-
- start = 33 * sizeof(vector128);
- end = start + sizeof(vrsave);
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
- start, end);
- }
-
- return ret;
-}
-
-/*
- * Regardless of transactions, 'vr_state' holds the current running
- * value of all the VMX registers and 'ckvr_state' holds the last
- * checkpointed value of all the VMX registers for the current
- * transaction to fall back on in case it aborts.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * vector128 vr[32];
- * vector128 vscr;
- * vector128 vrsave;
- * };
- */
-static int vr_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- flush_altivec_to_thread(target);
-
- BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
- offsetof(struct thread_vr_state, vr[32]));
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.vr_state, 0,
- 33 * sizeof(vector128));
- if (!ret && count > 0) {
- /*
- * We use only the first word of vrsave.
- */
- int start, end;
- union {
- elf_vrreg_t reg;
- u32 word;
- } vrsave;
- memset(&vrsave, 0, sizeof(vrsave));
-
- vrsave.word = target->thread.vrsave;
-
- start = 33 * sizeof(vector128);
- end = start + sizeof(vrsave);
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
- start, end);
- if (!ret)
- target->thread.vrsave = vrsave.word;
- }
-
- return ret;
-}
-#endif /* CONFIG_ALTIVEC */
-
-#ifdef CONFIG_VSX
-/*
- * Currently to set and and get all the vsx state, you need to call
- * the fp and VMX calls as well. This only get/sets the lower 32
- * 128bit VSX registers.
- */
-
-static int vsr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- flush_vsx_to_thread(target);
- return target->thread.used_vsr ? regset->n : 0;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last
- * checkpointed value of all FPR registers for the current
- * transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * u64 vsx[32];
- * };
- */
-static int vsr_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- u64 buf[32];
- int ret, i;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
- flush_vsx_to_thread(target);
-
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- buf, 0, 32 * sizeof(double));
-
- return ret;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last
- * checkpointed value of all FPR registers for the current
- * transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- * u64 vsx[32];
- * };
- */
-static int vsr_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- u64 buf[32];
- int ret,i;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
- flush_vsx_to_thread(target);
-
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- buf, 0, 32 * sizeof(double));
- if (!ret)
- for (i = 0; i < 32 ; i++)
- target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-
- return ret;
-}
-#endif /* CONFIG_VSX */
-
-#ifdef CONFIG_SPE
-
-/*
- * For get_evrregs/set_evrregs functions 'data' has the following layout:
- *
- * struct {
- * u32 evr[32];
- * u64 acc;
- * u32 spefscr;
- * }
- */
-
-static int evr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- flush_spe_to_thread(target);
- return target->thread.used_spe ? regset->n : 0;
-}
-
-static int evr_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- flush_spe_to_thread(target);
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.evr,
- 0, sizeof(target->thread.evr));
-
- BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
- offsetof(struct thread_struct, spefscr));
-
- if (!ret)
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.acc,
- sizeof(target->thread.evr), -1);
-
- return ret;
-}
-
-static int evr_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- flush_spe_to_thread(target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.evr,
- 0, sizeof(target->thread.evr));
-
- BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
- offsetof(struct thread_struct, spefscr));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.acc,
- sizeof(target->thread.evr), -1);
-
- return ret;
-}
-#endif /* CONFIG_SPE */
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/**
- * tm_cgpr_active - get active number of registers in CGPR
- * @target: The target task.
- * @regset: The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed GPR category.
- */
-static int tm_cgpr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return 0;
-
- return regset->n;
-}
-
-/**
- * tm_cgpr_get - get CGPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy from.
- * @ubuf: User buffer to copy into.
- *
- * This function gets transaction checkpointed GPR registers.
- *
- * When the transaction is active, 'ckpt_regs' holds all the checkpointed
- * GPR register values for the current transaction to fall back on if it
- * aborts in between. This function gets those checkpointed GPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- * struct pt_regs ckpt_regs;
- * };
- */
-static int tm_cgpr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckpt_regs,
- 0, offsetof(struct pt_regs, msr));
- if (!ret) {
- unsigned long msr = get_user_ckpt_msr(target);
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
- offsetof(struct pt_regs, msr),
- offsetof(struct pt_regs, msr) +
- sizeof(msr));
- }
-
- BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
- offsetof(struct pt_regs, msr) + sizeof(long));
-
- if (!ret)
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckpt_regs.orig_gpr3,
- offsetof(struct pt_regs, orig_gpr3),
- sizeof(struct user_pt_regs));
- if (!ret)
- ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
- sizeof(struct user_pt_regs), -1);
-
- return ret;
-}
-
-/*
- * tm_cgpr_set - set the CGPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy into.
- * @ubuf: User buffer to copy from.
- *
- * This function sets in transaction checkpointed GPR registers.
- *
- * When the transaction is active, 'ckpt_regs' holds the checkpointed
- * GPR register values for the current transaction to fall back on if it
- * aborts in between. This function sets those checkpointed GPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- * struct pt_regs ckpt_regs;
- * };
- */
-static int tm_cgpr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- unsigned long reg;
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckpt_regs,
- 0, PT_MSR * sizeof(reg));
-
- if (!ret && count > 0) {
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
- PT_MSR * sizeof(reg),
- (PT_MSR + 1) * sizeof(reg));
- if (!ret)
- ret = set_user_ckpt_msr(target, reg);
- }
-
- BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
- offsetof(struct pt_regs, msr) + sizeof(long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckpt_regs.orig_gpr3,
- PT_ORIG_R3 * sizeof(reg),
- (PT_MAX_PUT_REG + 1) * sizeof(reg));
-
- if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
- ret = user_regset_copyin_ignore(
- &pos, &count, &kbuf, &ubuf,
- (PT_MAX_PUT_REG + 1) * sizeof(reg),
- PT_TRAP * sizeof(reg));
-
- if (!ret && count > 0) {
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
- PT_TRAP * sizeof(reg),
- (PT_TRAP + 1) * sizeof(reg));
- if (!ret)
- ret = set_user_ckpt_trap(target, reg);
- }
-
- if (!ret)
- ret = user_regset_copyin_ignore(
- &pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
-
- return ret;
-}
-
-/**
- * tm_cfpr_active - get active number of registers in CFPR
- * @target: The target task.
- * @regset: The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed FPR category.
- */
-static int tm_cfpr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return 0;
-
- return regset->n;
-}
-
-/**
- * tm_cfpr_get - get CFPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy from.
- * @ubuf: User buffer to copy into.
- *
- * This function gets in transaction checkpointed FPR registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * values for the current transaction to fall back on if it aborts
- * in between. This function gets those checkpointed FPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- * u64 fpr[32];
- * u64 fpscr;
- *};
- */
-static int tm_cfpr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- u64 buf[33];
- int i;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- /* copy to local buffer then write that out */
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.TS_CKFPR(i);
- buf[32] = target->thread.ckfp_state.fpscr;
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-}
-
-/**
- * tm_cfpr_set - set CFPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy into.
- * @ubuf: User buffer to copy from.
- *
- * This function sets in transaction checkpointed FPR registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * FPR register values for the current transaction to fall back on
- * if it aborts in between. This function sets these checkpointed
- * FPR registers. The userspace interface buffer layout is as follows.
- *
- * struct data {
- * u64 fpr[32];
- * u64 fpscr;
- *};
- */
-static int tm_cfpr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- u64 buf[33];
- int i;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- for (i = 0; i < 32; i++)
- buf[i] = target->thread.TS_CKFPR(i);
- buf[32] = target->thread.ckfp_state.fpscr;
-
- /* copy to local buffer then write that out */
- i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
- if (i)
- return i;
- for (i = 0; i < 32 ; i++)
- target->thread.TS_CKFPR(i) = buf[i];
- target->thread.ckfp_state.fpscr = buf[32];
- return 0;
-}
-
-/**
- * tm_cvmx_active - get active number of registers in CVMX
- * @target: The target task.
- * @regset: The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in checkpointed VMX category.
- */
-static int tm_cvmx_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return 0;
-
- return regset->n;
-}
-
-/**
- * tm_cvmx_get - get CMVX registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy from.
- * @ubuf: User buffer to copy into.
- *
- * This function gets in transaction checkpointed VMX registers.
- *
- * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
- * the checkpointed values for the current transaction to fall
- * back on if it aborts in between. The userspace interface buffer
- * layout is as follows.
- *
- * struct data {
- * vector128 vr[32];
- * vector128 vscr;
- * vector128 vrsave;
- *};
- */
-static int tm_cvmx_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- /* Flush the state */
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckvr_state, 0,
- 33 * sizeof(vector128));
- if (!ret) {
- /*
- * Copy out only the low-order word of vrsave.
- */
- union {
- elf_vrreg_t reg;
- u32 word;
- } vrsave;
- memset(&vrsave, 0, sizeof(vrsave));
- vrsave.word = target->thread.ckvrsave;
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
- 33 * sizeof(vector128), -1);
- }
-
- return ret;
-}
-
-/**
- * tm_cvmx_set - set CMVX registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy into.
- * @ubuf: User buffer to copy from.
- *
- * This function sets in transaction checkpointed VMX registers.
- *
- * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
- * the checkpointed values for the current transaction to fall
- * back on if it aborts in between. The userspace interface buffer
- * layout is as follows.
- *
- * struct data {
- * vector128 vr[32];
- * vector128 vscr;
- * vector128 vrsave;
- *};
- */
-static int tm_cvmx_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.ckvr_state, 0,
- 33 * sizeof(vector128));
- if (!ret && count > 0) {
- /*
- * We use only the low-order word of vrsave.
- */
- union {
- elf_vrreg_t reg;
- u32 word;
- } vrsave;
- memset(&vrsave, 0, sizeof(vrsave));
- vrsave.word = target->thread.ckvrsave;
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
- 33 * sizeof(vector128), -1);
- if (!ret)
- target->thread.ckvrsave = vrsave.word;
- }
-
- return ret;
-}
-
-/**
- * tm_cvsx_active - get active number of registers in CVSX
- * @target: The target task.
- * @regset: The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed VSX category.
- */
-static int tm_cvsx_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return 0;
-
- flush_vsx_to_thread(target);
- return target->thread.used_vsr ? regset->n : 0;
-}
-
-/**
- * tm_cvsx_get - get CVSX registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy from.
- * @ubuf: User buffer to copy into.
- *
- * This function gets in transaction checkpointed VSX registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * values for the current transaction to fall back on if it aborts
- * in between. This function gets those checkpointed VSX registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- * u64 vsx[32];
- *};
- */
-static int tm_cvsx_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- u64 buf[32];
- int ret, i;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- /* Flush the state */
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
- flush_vsx_to_thread(target);
-
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- buf, 0, 32 * sizeof(double));
-
- return ret;
-}
-
-/**
- * tm_cvsx_set - set CFPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy into.
- * @ubuf: User buffer to copy from.
- *
- * This function sets in transaction checkpointed VSX registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * VSX register values for the current transaction to fall back on
- * if it aborts in between. This function sets these checkpointed
- * FPR registers. The userspace interface buffer layout is as follows.
- *
- * struct data {
- * u64 vsx[32];
- *};
- */
-static int tm_cvsx_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- u64 buf[32];
- int ret, i;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- /* Flush the state */
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
- flush_vsx_to_thread(target);
-
- for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- buf, 0, 32 * sizeof(double));
- if (!ret)
- for (i = 0; i < 32 ; i++)
- target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-
- return ret;
-}
-
-/**
- * tm_spr_active - get active number of registers in TM SPR
- * @target: The target task.
- * @regset: The user regset structure.
- *
- * This function checks the active number of available
- * regisers in the transactional memory SPR category.
- */
-static int tm_spr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- return regset->n;
-}
-
-/**
- * tm_spr_get - get the TM related SPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy from.
- * @ubuf: User buffer to copy into.
- *
- * This function gets transactional memory related SPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct {
- * u64 tm_tfhar;
- * u64 tm_texasr;
- * u64 tm_tfiar;
- * };
- */
-static int tm_spr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- /* Build tests */
- BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
- BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
- BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- /* Flush the states */
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- /* TFHAR register */
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tfhar, 0, sizeof(u64));
-
- /* TEXASR register */
- if (!ret)
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_texasr, sizeof(u64),
- 2 * sizeof(u64));
-
- /* TFIAR register */
- if (!ret)
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tfiar,
- 2 * sizeof(u64), 3 * sizeof(u64));
- return ret;
-}
-
-/**
- * tm_spr_set - set the TM related SPR registers
- * @target: The target task.
- * @regset: The user regset structure.
- * @pos: The buffer position.
- * @count: Number of bytes to copy.
- * @kbuf: Kernel buffer to copy into.
- * @ubuf: User buffer to copy from.
- *
- * This function sets transactional memory related SPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct {
- * u64 tm_tfhar;
- * u64 tm_texasr;
- * u64 tm_tfiar;
- * };
- */
-static int tm_spr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- /* Build tests */
- BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
- BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
- BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- /* Flush the states */
- flush_tmregs_to_thread(target);
- flush_fp_to_thread(target);
- flush_altivec_to_thread(target);
-
- /* TFHAR register */
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tfhar, 0, sizeof(u64));
-
- /* TEXASR register */
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_texasr, sizeof(u64),
- 2 * sizeof(u64));
-
- /* TFIAR register */
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tfiar,
- 2 * sizeof(u64), 3 * sizeof(u64));
- return ret;
-}
-
-static int tm_tar_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (MSR_TM_ACTIVE(target->thread.regs->msr))
- return regset->n;
-
- return 0;
-}
-
-static int tm_tar_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tar, 0, sizeof(u64));
- return ret;
-}
-
-static int tm_tar_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_tar, 0, sizeof(u64));
- return ret;
-}
-
-static int tm_ppr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (MSR_TM_ACTIVE(target->thread.regs->msr))
- return regset->n;
-
- return 0;
-}
-
-
-static int tm_ppr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_ppr, 0, sizeof(u64));
- return ret;
-}
-
-static int tm_ppr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_ppr, 0, sizeof(u64));
- return ret;
-}
-
-static int tm_dscr_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (MSR_TM_ACTIVE(target->thread.regs->msr))
- return regset->n;
-
- return 0;
-}
-
-static int tm_dscr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_dscr, 0, sizeof(u64));
- return ret;
-}
-
-static int tm_dscr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_feature(CPU_FTR_TM))
- return -ENODEV;
-
- if (!MSR_TM_ACTIVE(target->thread.regs->msr))
- return -ENODATA;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tm_dscr, 0, sizeof(u64));
- return ret;
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-
-#ifdef CONFIG_PPC64
-static int ppr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.regs->ppr, 0, sizeof(u64));
-}
-
-static int ppr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.regs->ppr, 0, sizeof(u64));
-}
-
-static int dscr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.dscr, 0, sizeof(u64));
-}
-static int dscr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.dscr, 0, sizeof(u64));
-}
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-static int tar_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.tar, 0, sizeof(u64));
-}
-static int tar_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.tar, 0, sizeof(u64));
-}
-
-static int ebb_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- if (target->thread.used_ebb)
- return regset->n;
-
- return 0;
-}
-
-static int ebb_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- /* Build tests */
- BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
- BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- if (!target->thread.used_ebb)
- return -ENODATA;
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.ebbrr, 0, 3 * sizeof(unsigned long));
-}
-
-static int ebb_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret = 0;
-
- /* Build tests */
- BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
- BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- if (target->thread.used_ebb)
- return -ENODATA;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.ebbrr, 0, sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.ebbhr, sizeof(unsigned long),
- 2 * sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.bescr,
- 2 * sizeof(unsigned long), 3 * sizeof(unsigned long));
-
- return ret;
-}
-static int pmu_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- return regset->n;
-}
-
-static int pmu_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- /* Build tests */
- BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
- BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
- BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
- BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.siar, 0,
- 5 * sizeof(unsigned long));
-}
-
-static int pmu_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret = 0;
-
- /* Build tests */
- BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
- BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
- BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
- BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.siar, 0,
- sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.sdar, sizeof(unsigned long),
- 2 * sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.sier, 2 * sizeof(unsigned long),
- 3 * sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.mmcr2, 3 * sizeof(unsigned long),
- 4 * sizeof(unsigned long));
-
- if (!ret)
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.mmcr0, 4 * sizeof(unsigned long),
- 5 * sizeof(unsigned long));
- return ret;
-}
-#endif
-
-#ifdef CONFIG_PPC_MEM_KEYS
-static int pkey_active(struct task_struct *target,
- const struct user_regset *regset)
-{
- if (!arch_pkeys_enabled())
- return -ENODEV;
-
- return regset->n;
-}
-
-static int pkey_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
- BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
-
- if (!arch_pkeys_enabled())
- return -ENODEV;
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.amr, 0,
- ELF_NPKEY * sizeof(unsigned long));
-}
-
-static int pkey_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- u64 new_amr;
- int ret;
-
- if (!arch_pkeys_enabled())
- return -ENODEV;
-
- /* Only the AMR can be set from userspace */
- if (pos != 0 || count != sizeof(new_amr))
- return -EINVAL;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &new_amr, 0, sizeof(new_amr));
- if (ret)
- return ret;
-
- /* UAMOR determines which bits of the AMR can be set from userspace. */
- target->thread.amr = (new_amr & target->thread.uamor) |
- (target->thread.amr & ~target->thread.uamor);
-
- return 0;
-}
-#endif /* CONFIG_PPC_MEM_KEYS */
-
-/*
- * These are our native regset flavors.
- */
-enum powerpc_regset {
- REGSET_GPR,
- REGSET_FPR,
-#ifdef CONFIG_ALTIVEC
- REGSET_VMX,
-#endif
-#ifdef CONFIG_VSX
- REGSET_VSX,
-#endif
-#ifdef CONFIG_SPE
- REGSET_SPE,
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- REGSET_TM_CGPR, /* TM checkpointed GPR registers */
- REGSET_TM_CFPR, /* TM checkpointed FPR registers */
- REGSET_TM_CVMX, /* TM checkpointed VMX registers */
- REGSET_TM_CVSX, /* TM checkpointed VSX registers */
- REGSET_TM_SPR, /* TM specific SPR registers */
- REGSET_TM_CTAR, /* TM checkpointed TAR register */
- REGSET_TM_CPPR, /* TM checkpointed PPR register */
- REGSET_TM_CDSCR, /* TM checkpointed DSCR register */
-#endif
-#ifdef CONFIG_PPC64
- REGSET_PPR, /* PPR register */
- REGSET_DSCR, /* DSCR register */
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
- REGSET_TAR, /* TAR register */
- REGSET_EBB, /* EBB registers */
- REGSET_PMR, /* Performance Monitor Registers */
-#endif
-#ifdef CONFIG_PPC_MEM_KEYS
- REGSET_PKEY, /* AMR register */
-#endif
-};
-
-static const struct user_regset native_regsets[] = {
- [REGSET_GPR] = {
- .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
- .size = sizeof(long), .align = sizeof(long),
- .get = gpr_get, .set = gpr_set
- },
- [REGSET_FPR] = {
- .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
- .size = sizeof(double), .align = sizeof(double),
- .get = fpr_get, .set = fpr_set
- },
-#ifdef CONFIG_ALTIVEC
- [REGSET_VMX] = {
- .core_note_type = NT_PPC_VMX, .n = 34,
- .size = sizeof(vector128), .align = sizeof(vector128),
- .active = vr_active, .get = vr_get, .set = vr_set
- },
-#endif
-#ifdef CONFIG_VSX
- [REGSET_VSX] = {
- .core_note_type = NT_PPC_VSX, .n = 32,
- .size = sizeof(double), .align = sizeof(double),
- .active = vsr_active, .get = vsr_get, .set = vsr_set
- },
-#endif
-#ifdef CONFIG_SPE
- [REGSET_SPE] = {
- .core_note_type = NT_PPC_SPE, .n = 35,
- .size = sizeof(u32), .align = sizeof(u32),
- .active = evr_active, .get = evr_get, .set = evr_set
- },
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- [REGSET_TM_CGPR] = {
- .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
- .size = sizeof(long), .align = sizeof(long),
- .active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set
- },
- [REGSET_TM_CFPR] = {
- .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
- .size = sizeof(double), .align = sizeof(double),
- .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
- },
- [REGSET_TM_CVMX] = {
- .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
- .size = sizeof(vector128), .align = sizeof(vector128),
- .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
- },
- [REGSET_TM_CVSX] = {
- .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
- .size = sizeof(double), .align = sizeof(double),
- .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
- },
- [REGSET_TM_SPR] = {
- .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
- },
- [REGSET_TM_CTAR] = {
- .core_note_type = NT_PPC_TM_CTAR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
- },
- [REGSET_TM_CPPR] = {
- .core_note_type = NT_PPC_TM_CPPR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
- },
- [REGSET_TM_CDSCR] = {
- .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
- },
-#endif
-#ifdef CONFIG_PPC64
- [REGSET_PPR] = {
- .core_note_type = NT_PPC_PPR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = ppr_get, .set = ppr_set
- },
- [REGSET_DSCR] = {
- .core_note_type = NT_PPC_DSCR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = dscr_get, .set = dscr_set
- },
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
- [REGSET_TAR] = {
- .core_note_type = NT_PPC_TAR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = tar_get, .set = tar_set
- },
- [REGSET_EBB] = {
- .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = ebb_active, .get = ebb_get, .set = ebb_set
- },
- [REGSET_PMR] = {
- .core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = pmu_active, .get = pmu_get, .set = pmu_set
- },
-#endif
-#ifdef CONFIG_PPC_MEM_KEYS
- [REGSET_PKEY] = {
- .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = pkey_active, .get = pkey_get, .set = pkey_set
- },
-#endif
-};
-
-static const struct user_regset_view user_ppc_native_view = {
- .name = UTS_MACHINE, .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI,
- .regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
-};
-
-#ifdef CONFIG_PPC64
-#include <linux/compat.h>
-
-static int gpr32_get_common(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf,
- unsigned long *regs)
-{
- compat_ulong_t *k = kbuf;
- compat_ulong_t __user *u = ubuf;
- compat_ulong_t reg;
-
- pos /= sizeof(reg);
- count /= sizeof(reg);
-
- if (kbuf)
- for (; count > 0 && pos < PT_MSR; --count)
- *k++ = regs[pos++];
- else
- for (; count > 0 && pos < PT_MSR; --count)
- if (__put_user((compat_ulong_t) regs[pos++], u++))
- return -EFAULT;
-
- if (count > 0 && pos == PT_MSR) {
- reg = get_user_msr(target);
- if (kbuf)
- *k++ = reg;
- else if (__put_user(reg, u++))
- return -EFAULT;
- ++pos;
- --count;
- }
-
- if (kbuf)
- for (; count > 0 && pos < PT_REGS_COUNT; --count)
- *k++ = regs[pos++];
- else
- for (; count > 0 && pos < PT_REGS_COUNT; --count)
- if (__put_user((compat_ulong_t) regs[pos++], u++))
- return -EFAULT;
-
- kbuf = k;
- ubuf = u;
- pos *= sizeof(reg);
- count *= sizeof(reg);
- return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
- PT_REGS_COUNT * sizeof(reg), -1);
-}
-
-static int gpr32_set_common(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf,
- unsigned long *regs)
-{
- const compat_ulong_t *k = kbuf;
- const compat_ulong_t __user *u = ubuf;
- compat_ulong_t reg;
-
- pos /= sizeof(reg);
- count /= sizeof(reg);
-
- if (kbuf)
- for (; count > 0 && pos < PT_MSR; --count)
- regs[pos++] = *k++;
- else
- for (; count > 0 && pos < PT_MSR; --count) {
- if (__get_user(reg, u++))
- return -EFAULT;
- regs[pos++] = reg;
- }
-
-
- if (count > 0 && pos == PT_MSR) {
- if (kbuf)
- reg = *k++;
- else if (__get_user(reg, u++))
- return -EFAULT;
- set_user_msr(target, reg);
- ++pos;
- --count;
- }
-
- if (kbuf) {
- for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
- regs[pos++] = *k++;
- for (; count > 0 && pos < PT_TRAP; --count, ++pos)
- ++k;
- } else {
- for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
- if (__get_user(reg, u++))
- return -EFAULT;
- regs[pos++] = reg;
- }
- for (; count > 0 && pos < PT_TRAP; --count, ++pos)
- if (__get_user(reg, u++))
- return -EFAULT;
- }
-
- if (count > 0 && pos == PT_TRAP) {
- if (kbuf)
- reg = *k++;
- else if (__get_user(reg, u++))
- return -EFAULT;
- set_user_trap(target, reg);
- ++pos;
- --count;
- }
-
- kbuf = k;
- ubuf = u;
- pos *= sizeof(reg);
- count *= sizeof(reg);
- return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static int tm_cgpr32_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
- &target->thread.ckpt_regs.gpr[0]);
-}
-
-static int tm_cgpr32_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
- &target->thread.ckpt_regs.gpr[0]);
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-
-static int gpr32_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int i;
-
- if (target->thread.regs == NULL)
- return -EIO;
-
- if (!FULL_REGS(target->thread.regs)) {
- /*
- * We have a partial register set.
- * Fill 14-31 with bogus values.
- */
- for (i = 14; i < 32; i++)
- target->thread.regs->gpr[i] = NV_REG_POISON;
- }
- return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
- &target->thread.regs->gpr[0]);
-}
-
-static int gpr32_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- if (target->thread.regs == NULL)
- return -EIO;
-
- CHECK_FULL_REGS(target->thread.regs);
- return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
- &target->thread.regs->gpr[0]);
-}
-
-/*
- * These are the regset flavors matching the CONFIG_PPC32 native set.
- */
-static const struct user_regset compat_regsets[] = {
- [REGSET_GPR] = {
- .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
- .size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
- .get = gpr32_get, .set = gpr32_set
- },
- [REGSET_FPR] = {
- .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
- .size = sizeof(double), .align = sizeof(double),
- .get = fpr_get, .set = fpr_set
- },
-#ifdef CONFIG_ALTIVEC
- [REGSET_VMX] = {
- .core_note_type = NT_PPC_VMX, .n = 34,
- .size = sizeof(vector128), .align = sizeof(vector128),
- .active = vr_active, .get = vr_get, .set = vr_set
- },
-#endif
-#ifdef CONFIG_SPE
- [REGSET_SPE] = {
- .core_note_type = NT_PPC_SPE, .n = 35,
- .size = sizeof(u32), .align = sizeof(u32),
- .active = evr_active, .get = evr_get, .set = evr_set
- },
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- [REGSET_TM_CGPR] = {
- .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
- .size = sizeof(long), .align = sizeof(long),
- .active = tm_cgpr_active,
- .get = tm_cgpr32_get, .set = tm_cgpr32_set
- },
- [REGSET_TM_CFPR] = {
- .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
- .size = sizeof(double), .align = sizeof(double),
- .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
- },
- [REGSET_TM_CVMX] = {
- .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
- .size = sizeof(vector128), .align = sizeof(vector128),
- .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
- },
- [REGSET_TM_CVSX] = {
- .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
- .size = sizeof(double), .align = sizeof(double),
- .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
- },
- [REGSET_TM_SPR] = {
- .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
- },
- [REGSET_TM_CTAR] = {
- .core_note_type = NT_PPC_TM_CTAR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
- },
- [REGSET_TM_CPPR] = {
- .core_note_type = NT_PPC_TM_CPPR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
- },
- [REGSET_TM_CDSCR] = {
- .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
- },
-#endif
-#ifdef CONFIG_PPC64
- [REGSET_PPR] = {
- .core_note_type = NT_PPC_PPR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = ppr_get, .set = ppr_set
- },
- [REGSET_DSCR] = {
- .core_note_type = NT_PPC_DSCR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = dscr_get, .set = dscr_set
- },
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
- [REGSET_TAR] = {
- .core_note_type = NT_PPC_TAR, .n = 1,
- .size = sizeof(u64), .align = sizeof(u64),
- .get = tar_get, .set = tar_set
- },
- [REGSET_EBB] = {
- .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
- .size = sizeof(u64), .align = sizeof(u64),
- .active = ebb_active, .get = ebb_get, .set = ebb_set
- },
-#endif
-};
-
-static const struct user_regset_view user_ppc_compat_view = {
- .name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
- .regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
-};
-#endif /* CONFIG_PPC64 */
-
-const struct user_regset_view *task_user_regset_view(struct task_struct *task)
-{
-#ifdef CONFIG_PPC64
- if (test_tsk_thread_flag(task, TIF_32BIT))
- return &user_ppc_compat_view;
-#endif
- return &user_ppc_native_view;
-}
-
-
-void user_enable_single_step(struct task_struct *task)
-{
- struct pt_regs *regs = task->thread.regs;
-
- if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- task->thread.debug.dbcr0 &= ~DBCR0_BT;
- task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
- regs->msr |= MSR_DE;
-#else
- regs->msr &= ~MSR_BE;
- regs->msr |= MSR_SE;
-#endif
- }
- set_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-void user_enable_block_step(struct task_struct *task)
-{
- struct pt_regs *regs = task->thread.regs;
-
- if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- task->thread.debug.dbcr0 &= ~DBCR0_IC;
- task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT;
- regs->msr |= MSR_DE;
-#else
- regs->msr &= ~MSR_SE;
- regs->msr |= MSR_BE;
-#endif
- }
- set_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-void user_disable_single_step(struct task_struct *task)
-{
- struct pt_regs *regs = task->thread.regs;
-
- if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- /*
- * The logic to disable single stepping should be as
- * simple as turning off the Instruction Complete flag.
- * And, after doing so, if all debug flags are off, turn
- * off DBCR0(IDM) and MSR(DE) .... Torez
- */
- task->thread.debug.dbcr0 &= ~(DBCR0_IC|DBCR0_BT);
- /*
- * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
- */
- if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
- task->thread.debug.dbcr1)) {
- /*
- * All debug events were off.....
- */
- task->thread.debug.dbcr0 &= ~DBCR0_IDM;
- regs->msr &= ~MSR_DE;
- }
-#else
- regs->msr &= ~(MSR_SE | MSR_BE);
-#endif
- }
- clear_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-void ptrace_triggered(struct perf_event *bp,
- struct perf_sample_data *data, struct pt_regs *regs)
-{
- struct perf_event_attr attr;
-
- /*
- * Disable the breakpoint request here since ptrace has defined a
- * one-shot behaviour for breakpoint exceptions in PPC64.
- * The SIGTRAP signal is generated automatically for us in do_dabr().
- * We don't have to do anything about that here
- */
- attr = bp->attr;
- attr.disabled = true;
- modify_user_hw_breakpoint(bp, &attr);
-}
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
-static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
- unsigned long data)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- int ret;
- struct thread_struct *thread = &(task->thread);
- struct perf_event *bp;
- struct perf_event_attr attr;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
- bool set_bp = true;
- struct arch_hw_breakpoint hw_brk;
-#endif
-
- /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
- * For embedded processors we support one DAC and no IAC's at the
- * moment.
- */
- if (addr > 0)
- return -EINVAL;
-
- /* The bottom 3 bits in dabr are flags */
- if ((data & ~0x7UL) >= TASK_SIZE)
- return -EIO;
-
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
- /* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
- * It was assumed, on previous implementations, that 3 bits were
- * passed together with the data address, fitting the design of the
- * DABR register, as follows:
- *
- * bit 0: Read flag
- * bit 1: Write flag
- * bit 2: Breakpoint translation
- *
- * Thus, we use them here as so.
- */
-
- /* Ensure breakpoint translation bit is set */
- if (data && !(data & HW_BRK_TYPE_TRANSLATE))
- return -EIO;
- hw_brk.address = data & (~HW_BRK_TYPE_DABR);
- hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
- hw_brk.len = 8;
- set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- bp = thread->ptrace_bps[0];
- if (!set_bp) {
- if (bp) {
- unregister_hw_breakpoint(bp);
- thread->ptrace_bps[0] = NULL;
- }
- return 0;
- }
- if (bp) {
- attr = bp->attr;
- attr.bp_addr = hw_brk.address;
- arch_bp_generic_fields(hw_brk.type, &attr.bp_type);
-
- /* Enable breakpoint */
- attr.disabled = false;
-
- ret = modify_user_hw_breakpoint(bp, &attr);
- if (ret) {
- return ret;
- }
- thread->ptrace_bps[0] = bp;
- thread->hw_brk = hw_brk;
- return 0;
- }
-
- /* Create a new breakpoint request if one doesn't exist already */
- hw_breakpoint_init(&attr);
- attr.bp_addr = hw_brk.address;
- attr.bp_len = 8;
- arch_bp_generic_fields(hw_brk.type,
- &attr.bp_type);
-
- thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
- ptrace_triggered, NULL, task);
- if (IS_ERR(bp)) {
- thread->ptrace_bps[0] = NULL;
- return PTR_ERR(bp);
- }
-
-#else /* !CONFIG_HAVE_HW_BREAKPOINT */
- if (set_bp && (!ppc_breakpoint_available()))
- return -ENODEV;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
- task->thread.hw_brk = hw_brk;
-#else /* CONFIG_PPC_ADV_DEBUG_REGS */
- /* As described above, it was assumed 3 bits were passed with the data
- * address, but we will assume only the mode bits will be passed
- * as to not cause alignment restrictions for DAC-based processors.
- */
-
- /* DAC's hold the whole address without any mode flags */
- task->thread.debug.dac1 = data & ~0x3UL;
-
- if (task->thread.debug.dac1 == 0) {
- dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
- if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
- task->thread.debug.dbcr1)) {
- task->thread.regs->msr &= ~MSR_DE;
- task->thread.debug.dbcr0 &= ~DBCR0_IDM;
- }
- return 0;
- }
-
- /* Read or Write bits must be set */
-
- if (!(data & 0x3UL))
- return -EINVAL;
-
- /* Set the Internal Debugging flag (IDM bit 1) for the DBCR0
- register */
- task->thread.debug.dbcr0 |= DBCR0_IDM;
-
- /* Check for write and read flags and set DBCR0
- accordingly */
- dbcr_dac(task) &= ~(DBCR_DAC1R|DBCR_DAC1W);
- if (data & 0x1UL)
- dbcr_dac(task) |= DBCR_DAC1R;
- if (data & 0x2UL)
- dbcr_dac(task) |= DBCR_DAC1W;
- task->thread.regs->msr |= MSR_DE;
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
- return 0;
-}
-
-/*
- * Called by kernel/ptrace.c when detaching..
- *
- * Make sure single step bits etc are not set.
- */
-void ptrace_disable(struct task_struct *child)
-{
- /* make sure the single step bit is not set. */
- user_disable_single_step(child);
-}
-
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-static long set_instruction_bp(struct task_struct *child,
- struct ppc_hw_breakpoint *bp_info)
-{
- int slot;
- int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0);
- int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0);
- int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0);
- int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0);
-
- if (dbcr_iac_range(child) & DBCR_IAC12MODE)
- slot2_in_use = 1;
- if (dbcr_iac_range(child) & DBCR_IAC34MODE)
- slot4_in_use = 1;
-
- if (bp_info->addr >= TASK_SIZE)
- return -EIO;
-
- if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
-
- /* Make sure range is valid. */
- if (bp_info->addr2 >= TASK_SIZE)
- return -EIO;
-
- /* We need a pair of IAC regsisters */
- if ((!slot1_in_use) && (!slot2_in_use)) {
- slot = 1;
- child->thread.debug.iac1 = bp_info->addr;
- child->thread.debug.iac2 = bp_info->addr2;
- child->thread.debug.dbcr0 |= DBCR0_IAC1;
- if (bp_info->addr_mode ==
- PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
- dbcr_iac_range(child) |= DBCR_IAC12X;
- else
- dbcr_iac_range(child) |= DBCR_IAC12I;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
- } else if ((!slot3_in_use) && (!slot4_in_use)) {
- slot = 3;
- child->thread.debug.iac3 = bp_info->addr;
- child->thread.debug.iac4 = bp_info->addr2;
- child->thread.debug.dbcr0 |= DBCR0_IAC3;
- if (bp_info->addr_mode ==
- PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
- dbcr_iac_range(child) |= DBCR_IAC34X;
- else
- dbcr_iac_range(child) |= DBCR_IAC34I;
-#endif
- } else
- return -ENOSPC;
- } else {
- /* We only need one. If possible leave a pair free in
- * case a range is needed later
- */
- if (!slot1_in_use) {
- /*
- * Don't use iac1 if iac1-iac2 are free and either
- * iac3 or iac4 (but not both) are free
- */
- if (slot2_in_use || (slot3_in_use == slot4_in_use)) {
- slot = 1;
- child->thread.debug.iac1 = bp_info->addr;
- child->thread.debug.dbcr0 |= DBCR0_IAC1;
- goto out;
- }
- }
- if (!slot2_in_use) {
- slot = 2;
- child->thread.debug.iac2 = bp_info->addr;
- child->thread.debug.dbcr0 |= DBCR0_IAC2;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
- } else if (!slot3_in_use) {
- slot = 3;
- child->thread.debug.iac3 = bp_info->addr;
- child->thread.debug.dbcr0 |= DBCR0_IAC3;
- } else if (!slot4_in_use) {
- slot = 4;
- child->thread.debug.iac4 = bp_info->addr;
- child->thread.debug.dbcr0 |= DBCR0_IAC4;
-#endif
- } else
- return -ENOSPC;
- }
-out:
- child->thread.debug.dbcr0 |= DBCR0_IDM;
- child->thread.regs->msr |= MSR_DE;
-
- return slot;
-}
-
-static int del_instruction_bp(struct task_struct *child, int slot)
-{
- switch (slot) {
- case 1:
- if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0)
- return -ENOENT;
-
- if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
- /* address range - clear slots 1 & 2 */
- child->thread.debug.iac2 = 0;
- dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
- }
- child->thread.debug.iac1 = 0;
- child->thread.debug.dbcr0 &= ~DBCR0_IAC1;
- break;
- case 2:
- if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0)
- return -ENOENT;
-
- if (dbcr_iac_range(child) & DBCR_IAC12MODE)
- /* used in a range */
- return -EINVAL;
- child->thread.debug.iac2 = 0;
- child->thread.debug.dbcr0 &= ~DBCR0_IAC2;
- break;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
- case 3:
- if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0)
- return -ENOENT;
-
- if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
- /* address range - clear slots 3 & 4 */
- child->thread.debug.iac4 = 0;
- dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
- }
- child->thread.debug.iac3 = 0;
- child->thread.debug.dbcr0 &= ~DBCR0_IAC3;
- break;
- case 4:
- if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0)
- return -ENOENT;
-
- if (dbcr_iac_range(child) & DBCR_IAC34MODE)
- /* Used in a range */
- return -EINVAL;
- child->thread.debug.iac4 = 0;
- child->thread.debug.dbcr0 &= ~DBCR0_IAC4;
- break;
-#endif
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
-{
- int byte_enable =
- (bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
- & 0xf;
- int condition_mode =
- bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
- int slot;
-
- if (byte_enable && (condition_mode == 0))
- return -EINVAL;
-
- if (bp_info->addr >= TASK_SIZE)
- return -EIO;
-
- if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
- slot = 1;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
- dbcr_dac(child) |= DBCR_DAC1R;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
- dbcr_dac(child) |= DBCR_DAC1W;
- child->thread.debug.dac1 = (unsigned long)bp_info->addr;
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
- if (byte_enable) {
- child->thread.debug.dvc1 =
- (unsigned long)bp_info->condition_value;
- child->thread.debug.dbcr2 |=
- ((byte_enable << DBCR2_DVC1BE_SHIFT) |
- (condition_mode << DBCR2_DVC1M_SHIFT));
- }
-#endif
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
- } else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
- /* Both dac1 and dac2 are part of a range */
- return -ENOSPC;
-#endif
- } else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
- slot = 2;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
- dbcr_dac(child) |= DBCR_DAC2R;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
- dbcr_dac(child) |= DBCR_DAC2W;
- child->thread.debug.dac2 = (unsigned long)bp_info->addr;
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
- if (byte_enable) {
- child->thread.debug.dvc2 =
- (unsigned long)bp_info->condition_value;
- child->thread.debug.dbcr2 |=
- ((byte_enable << DBCR2_DVC2BE_SHIFT) |
- (condition_mode << DBCR2_DVC2M_SHIFT));
- }
-#endif
- } else
- return -ENOSPC;
- child->thread.debug.dbcr0 |= DBCR0_IDM;
- child->thread.regs->msr |= MSR_DE;
-
- return slot + 4;
-}
-
-static int del_dac(struct task_struct *child, int slot)
-{
- if (slot == 1) {
- if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
- return -ENOENT;
-
- child->thread.debug.dac1 = 0;
- dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
- if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
- child->thread.debug.dac2 = 0;
- child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
- }
- child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
-#endif
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
- child->thread.debug.dvc1 = 0;
-#endif
- } else if (slot == 2) {
- if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
- return -ENOENT;
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
- if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE)
- /* Part of a range */
- return -EINVAL;
- child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
-#endif
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
- child->thread.debug.dvc2 = 0;
-#endif
- child->thread.debug.dac2 = 0;
- dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
- } else
- return -EINVAL;
-
- return 0;
-}
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-static int set_dac_range(struct task_struct *child,
- struct ppc_hw_breakpoint *bp_info)
-{
- int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
-
- /* We don't allow range watchpoints to be used with DVC */
- if (bp_info->condition_mode)
- return -EINVAL;
-
- /*
- * Best effort to verify the address range. The user/supervisor bits
- * prevent trapping in kernel space, but let's fail on an obvious bad
- * range. The simple test on the mask is not fool-proof, and any
- * exclusive range will spill over into kernel space.
- */
- if (bp_info->addr >= TASK_SIZE)
- return -EIO;
- if (mode == PPC_BREAKPOINT_MODE_MASK) {
- /*
- * dac2 is a bitmask. Don't allow a mask that makes a
- * kernel space address from a valid dac1 value
- */
- if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
- return -EIO;
- } else {
- /*
- * For range breakpoints, addr2 must also be a valid address
- */
- if (bp_info->addr2 >= TASK_SIZE)
- return -EIO;
- }
-
- if (child->thread.debug.dbcr0 &
- (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
- return -ENOSPC;
-
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
- child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
- child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
- child->thread.debug.dac1 = bp_info->addr;
- child->thread.debug.dac2 = bp_info->addr2;
- if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
- child->thread.debug.dbcr2 |= DBCR2_DAC12M;
- else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
- child->thread.debug.dbcr2 |= DBCR2_DAC12MX;
- else /* PPC_BREAKPOINT_MODE_MASK */
- child->thread.debug.dbcr2 |= DBCR2_DAC12MM;
- child->thread.regs->msr |= MSR_DE;
-
- return 5;
-}
-#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
-
-static long ppc_set_hwdebug(struct task_struct *child,
- struct ppc_hw_breakpoint *bp_info)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- int len = 0;
- struct thread_struct *thread = &(child->thread);
- struct perf_event *bp;
- struct perf_event_attr attr;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
- struct arch_hw_breakpoint brk;
-#endif
-
- if (bp_info->version != 1)
- return -ENOTSUPP;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- /*
- * Check for invalid flags and combinations
- */
- if ((bp_info->trigger_type == 0) ||
- (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
- PPC_BREAKPOINT_TRIGGER_RW)) ||
- (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
- (bp_info->condition_mode &
- ~(PPC_BREAKPOINT_CONDITION_MODE |
- PPC_BREAKPOINT_CONDITION_BE_ALL)))
- return -EINVAL;
-#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
- if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
- return -EINVAL;
-#endif
-
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
- if ((bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE) ||
- (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE))
- return -EINVAL;
- return set_instruction_bp(child, bp_info);
- }
- if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
- return set_dac(child, bp_info);
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
- return set_dac_range(child, bp_info);
-#else
- return -EINVAL;
-#endif
-#else /* !CONFIG_PPC_ADV_DEBUG_DVCS */
- /*
- * We only support one data breakpoint
- */
- if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
- (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
- bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
- return -EINVAL;
-
- if ((unsigned long)bp_info->addr >= TASK_SIZE)
- return -EIO;
-
- brk.address = bp_info->addr & ~7UL;
- brk.type = HW_BRK_TYPE_TRANSLATE;
- brk.len = 8;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
- brk.type |= HW_BRK_TYPE_READ;
- if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
- brk.type |= HW_BRK_TYPE_WRITE;
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- /*
- * Check if the request is for 'range' breakpoints. We can
- * support it if range < 8 bytes.
- */
- if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
- len = bp_info->addr2 - bp_info->addr;
- else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
- len = 1;
- else
- return -EINVAL;
- bp = thread->ptrace_bps[0];
- if (bp)
- return -ENOSPC;
-
- /* Create a new breakpoint request if one doesn't exist already */
- hw_breakpoint_init(&attr);
- attr.bp_addr = (unsigned long)bp_info->addr & ~HW_BREAKPOINT_ALIGN;
- attr.bp_len = len;
- arch_bp_generic_fields(brk.type, &attr.bp_type);
-
- thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
- ptrace_triggered, NULL, child);
- if (IS_ERR(bp)) {
- thread->ptrace_bps[0] = NULL;
- return PTR_ERR(bp);
- }
-
- return 1;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
- if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT)
- return -EINVAL;
-
- if (child->thread.hw_brk.address)
- return -ENOSPC;
-
- if (!ppc_breakpoint_available())
- return -ENODEV;
-
- child->thread.hw_brk = brk;
-
- return 1;
-#endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */
-}
-
-static long ppc_del_hwdebug(struct task_struct *child, long data)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- int ret = 0;
- struct thread_struct *thread = &(child->thread);
- struct perf_event *bp;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- int rc;
-
- if (data <= 4)
- rc = del_instruction_bp(child, (int)data);
- else
- rc = del_dac(child, (int)data - 4);
-
- if (!rc) {
- if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0,
- child->thread.debug.dbcr1)) {
- child->thread.debug.dbcr0 &= ~DBCR0_IDM;
- child->thread.regs->msr &= ~MSR_DE;
- }
- }
- return rc;
-#else
- if (data != 1)
- return -EINVAL;
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- bp = thread->ptrace_bps[0];
- if (bp) {
- unregister_hw_breakpoint(bp);
- thread->ptrace_bps[0] = NULL;
- } else
- ret = -ENOENT;
- return ret;
-#else /* CONFIG_HAVE_HW_BREAKPOINT */
- if (child->thread.hw_brk.address == 0)
- return -ENOENT;
-
- child->thread.hw_brk.address = 0;
- child->thread.hw_brk.type = 0;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
- return 0;
-#endif
-}
-
-long arch_ptrace(struct task_struct *child, long request,
- unsigned long addr, unsigned long data)
-{
- int ret = -EPERM;
- void __user *datavp = (void __user *) data;
- unsigned long __user *datalp = datavp;
-
- switch (request) {
- /* read the word at location addr in the USER area. */
- case PTRACE_PEEKUSR: {
- unsigned long index, tmp;
-
- ret = -EIO;
- /* convert to index and check */
-#ifdef CONFIG_PPC32
- index = addr >> 2;
- if ((addr & 3) || (index > PT_FPSCR)
- || (child->thread.regs == NULL))
-#else
- index = addr >> 3;
- if ((addr & 7) || (index > PT_FPSCR))
-#endif
- break;
-
- CHECK_FULL_REGS(child->thread.regs);
- if (index < PT_FPR0) {
- ret = ptrace_get_reg(child, (int) index, &tmp);
- if (ret)
- break;
- } else {
- unsigned int fpidx = index - PT_FPR0;
-
- flush_fp_to_thread(child);
- if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(&tmp, &child->thread.TS_FPR(fpidx),
- sizeof(long));
- else
- tmp = child->thread.fp_state.fpscr;
- }
- ret = put_user(tmp, datalp);
- break;
- }
-
- /* write the word at location addr in the USER area */
- case PTRACE_POKEUSR: {
- unsigned long index;
-
- ret = -EIO;
- /* convert to index and check */
-#ifdef CONFIG_PPC32
- index = addr >> 2;
- if ((addr & 3) || (index > PT_FPSCR)
- || (child->thread.regs == NULL))
-#else
- index = addr >> 3;
- if ((addr & 7) || (index > PT_FPSCR))
-#endif
- break;
-
- CHECK_FULL_REGS(child->thread.regs);
- if (index < PT_FPR0) {
- ret = ptrace_put_reg(child, index, data);
- } else {
- unsigned int fpidx = index - PT_FPR0;
-
- flush_fp_to_thread(child);
- if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(&child->thread.TS_FPR(fpidx), &data,
- sizeof(long));
- else
- child->thread.fp_state.fpscr = data;
- ret = 0;
- }
- break;
- }
-
- case PPC_PTRACE_GETHWDBGINFO: {
- struct ppc_debug_info dbginfo;
-
- dbginfo.version = 1;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- dbginfo.num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
- dbginfo.num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
- dbginfo.num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
- dbginfo.data_bp_alignment = 4;
- dbginfo.sizeof_condition = 4;
- dbginfo.features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
- PPC_DEBUG_FEATURE_INSN_BP_MASK;
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
- dbginfo.features |=
- PPC_DEBUG_FEATURE_DATA_BP_RANGE |
- PPC_DEBUG_FEATURE_DATA_BP_MASK;
-#endif
-#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
- dbginfo.num_instruction_bps = 0;
- if (ppc_breakpoint_available())
- dbginfo.num_data_bps = 1;
- else
- dbginfo.num_data_bps = 0;
- dbginfo.num_condition_regs = 0;
-#ifdef CONFIG_PPC64
- dbginfo.data_bp_alignment = 8;
-#else
- dbginfo.data_bp_alignment = 4;
-#endif
- dbginfo.sizeof_condition = 0;
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
- if (dawr_enabled())
- dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
-#else
- dbginfo.features = 0;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-
- if (copy_to_user(datavp, &dbginfo,
- sizeof(struct ppc_debug_info)))
- return -EFAULT;
- return 0;
- }
-
- case PPC_PTRACE_SETHWDEBUG: {
- struct ppc_hw_breakpoint bp_info;
-
- if (copy_from_user(&bp_info, datavp,
- sizeof(struct ppc_hw_breakpoint)))
- return -EFAULT;
- return ppc_set_hwdebug(child, &bp_info);
- }
-
- case PPC_PTRACE_DELHWDEBUG: {
- ret = ppc_del_hwdebug(child, data);
- break;
- }
-
- case PTRACE_GET_DEBUGREG: {
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
- unsigned long dabr_fake;
-#endif
- ret = -EINVAL;
- /* We only support one DABR and no IABRS at the moment */
- if (addr > 0)
- break;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- ret = put_user(child->thread.debug.dac1, datalp);
-#else
- dabr_fake = ((child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) |
- (child->thread.hw_brk.type & HW_BRK_TYPE_DABR));
- ret = put_user(dabr_fake, datalp);
-#endif
- break;
- }
-
- case PTRACE_SET_DEBUGREG:
- ret = ptrace_set_debugreg(child, addr, data);
- break;
-
-#ifdef CONFIG_PPC64
- case PTRACE_GETREGS64:
-#endif
- case PTRACE_GETREGS: /* Get all pt_regs from the child. */
- return copy_regset_to_user(child, &user_ppc_native_view,
- REGSET_GPR,
- 0, sizeof(struct user_pt_regs),
- datavp);
-
-#ifdef CONFIG_PPC64
- case PTRACE_SETREGS64:
-#endif
- case PTRACE_SETREGS: /* Set all gp regs in the child. */
- return copy_regset_from_user(child, &user_ppc_native_view,
- REGSET_GPR,
- 0, sizeof(struct user_pt_regs),
- datavp);
-
- case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
- return copy_regset_to_user(child, &user_ppc_native_view,
- REGSET_FPR,
- 0, sizeof(elf_fpregset_t),
- datavp);
-
- case PTRACE_SETFPREGS: /* Set the child FPU state (FPR0...31 + FPSCR) */
- return copy_regset_from_user(child, &user_ppc_native_view,
- REGSET_FPR,
- 0, sizeof(elf_fpregset_t),
- datavp);
-
-#ifdef CONFIG_ALTIVEC
- case PTRACE_GETVRREGS:
- return copy_regset_to_user(child, &user_ppc_native_view,
- REGSET_VMX,
- 0, (33 * sizeof(vector128) +
- sizeof(u32)),
- datavp);
-
- case PTRACE_SETVRREGS:
- return copy_regset_from_user(child, &user_ppc_native_view,
- REGSET_VMX,
- 0, (33 * sizeof(vector128) +
- sizeof(u32)),
- datavp);
-#endif
-#ifdef CONFIG_VSX
- case PTRACE_GETVSRREGS:
- return copy_regset_to_user(child, &user_ppc_native_view,
- REGSET_VSX,
- 0, 32 * sizeof(double),
- datavp);
-
- case PTRACE_SETVSRREGS:
- return copy_regset_from_user(child, &user_ppc_native_view,
- REGSET_VSX,
- 0, 32 * sizeof(double),
- datavp);
-#endif
-#ifdef CONFIG_SPE
- case PTRACE_GETEVRREGS:
- /* Get the child spe register state. */
- return copy_regset_to_user(child, &user_ppc_native_view,
- REGSET_SPE, 0, 35 * sizeof(u32),
- datavp);
-
- case PTRACE_SETEVRREGS:
- /* Set the child spe register state. */
- return copy_regset_from_user(child, &user_ppc_native_view,
- REGSET_SPE, 0, 35 * sizeof(u32),
- datavp);
-#endif
-
- default:
- ret = ptrace_request(child, request, addr, data);
- break;
- }
- return ret;
-}
-
-#ifdef CONFIG_SECCOMP
-static int do_seccomp(struct pt_regs *regs)
-{
- if (!test_thread_flag(TIF_SECCOMP))
- return 0;
-
- /*
- * The ABI we present to seccomp tracers is that r3 contains
- * the syscall return value and orig_gpr3 contains the first
- * syscall parameter. This is different to the ptrace ABI where
- * both r3 and orig_gpr3 contain the first syscall parameter.
- */
- regs->gpr[3] = -ENOSYS;
-
- /*
- * We use the __ version here because we have already checked
- * TIF_SECCOMP. If this fails, there is nothing left to do, we
- * have already loaded -ENOSYS into r3, or seccomp has put
- * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
- */
- if (__secure_computing(NULL))
- return -1;
-
- /*
- * The syscall was allowed by seccomp, restore the register
- * state to what audit expects.
- * Note that we use orig_gpr3, which means a seccomp tracer can
- * modify the first syscall parameter (in orig_gpr3) and also
- * allow the syscall to proceed.
- */
- regs->gpr[3] = regs->orig_gpr3;
-
- return 0;
-}
-#else
-static inline int do_seccomp(struct pt_regs *regs) { return 0; }
-#endif /* CONFIG_SECCOMP */
-
-/**
- * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
- * @regs: the pt_regs of the task to trace (current)
- *
- * Performs various types of tracing on syscall entry. This includes seccomp,
- * ptrace, syscall tracepoints and audit.
- *
- * The pt_regs are potentially visible to userspace via ptrace, so their
- * contents is ABI.
- *
- * One or more of the tracers may modify the contents of pt_regs, in particular
- * to modify arguments or even the syscall number itself.
- *
- * It's also possible that a tracer can choose to reject the system call. In
- * that case this function will return an illegal syscall number, and will put
- * an appropriate return value in regs->r3.
- *
- * Return: the (possibly changed) syscall number.
- */
-long do_syscall_trace_enter(struct pt_regs *regs)
-{
- u32 flags;
-
- user_exit();
-
- flags = READ_ONCE(current_thread_info()->flags) &
- (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
-
- if (flags) {
- int rc = tracehook_report_syscall_entry(regs);
-
- if (unlikely(flags & _TIF_SYSCALL_EMU)) {
- /*
- * A nonzero return code from
- * tracehook_report_syscall_entry() tells us to prevent
- * the syscall execution, but we are not going to
- * execute it anyway.
- *
- * Returning -1 will skip the syscall execution. We want
- * to avoid clobbering any registers, so we don't goto
- * the skip label below.
- */
- return -1;
- }
-
- if (rc) {
- /*
- * The tracer decided to abort the syscall. Note that
- * the tracer may also just change regs->gpr[0] to an
- * invalid syscall number, that is handled below on the
- * exit path.
- */
- goto skip;
- }
- }
-
- /* Run seccomp after ptrace; allow it to set gpr[3]. */
- if (do_seccomp(regs))
- return -1;
-
- /* Avoid trace and audit when syscall is invalid. */
- if (regs->gpr[0] >= NR_syscalls)
- goto skip;
-
- if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_enter(regs, regs->gpr[0]);
-
-#ifdef CONFIG_PPC64
- if (!is_32bit_task())
- audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
- regs->gpr[5], regs->gpr[6]);
- else
-#endif
- audit_syscall_entry(regs->gpr[0],
- regs->gpr[3] & 0xffffffff,
- regs->gpr[4] & 0xffffffff,
- regs->gpr[5] & 0xffffffff,
- regs->gpr[6] & 0xffffffff);
-
- /* Return the possibly modified but valid syscall number */
- return regs->gpr[0];
-
-skip:
- /*
- * If we are aborting explicitly, or if the syscall number is
- * now invalid, set the return value to -ENOSYS.
- */
- regs->gpr[3] = -ENOSYS;
- return -1;
-}
-
-void do_syscall_trace_leave(struct pt_regs *regs)
-{
- int step;
-
- audit_syscall_exit(regs);
-
- if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_exit(regs, regs->result);
-
- step = test_thread_flag(TIF_SINGLESTEP);
- if (step || test_thread_flag(TIF_SYSCALL_TRACE))
- tracehook_report_syscall_exit(regs, step);
-
- user_enter();
-}
-
-void __init pt_regs_check(void)
-{
- BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
- offsetof(struct user_pt_regs, gpr));
- BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
- offsetof(struct user_pt_regs, nip));
- BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
- offsetof(struct user_pt_regs, msr));
- BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
- offsetof(struct user_pt_regs, msr));
- BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
- offsetof(struct user_pt_regs, orig_gpr3));
- BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
- offsetof(struct user_pt_regs, ctr));
- BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
- offsetof(struct user_pt_regs, link));
- BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
- offsetof(struct user_pt_regs, xer));
- BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
- offsetof(struct user_pt_regs, ccr));
-#ifdef __powerpc64__
- BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
- offsetof(struct user_pt_regs, softe));
-#else
- BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
- offsetof(struct user_pt_regs, mq));
-#endif
- BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
- offsetof(struct user_pt_regs, trap));
- BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
- offsetof(struct user_pt_regs, dar));
- BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
- offsetof(struct user_pt_regs, dsisr));
- BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
- offsetof(struct user_pt_regs, result));
-
- BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
-}
diff --git a/arch/powerpc/kernel/ptrace/Makefile b/arch/powerpc/kernel/ptrace/Makefile
new file mode 100644
index 0000000..c2f2402
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+CFLAGS_ptrace-view.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
+obj-y += ptrace.o ptrace-view.o
+obj-$(CONFIG_COMPAT) += ptrace32.o
+obj-$(CONFIG_VSX) += ptrace-vsx.o
+ifneq ($(CONFIG_VSX),y)
+obj-y += ptrace-novsx.o
+endif
+obj-$(CONFIG_ALTIVEC) += ptrace-altivec.o
+obj-$(CONFIG_SPE) += ptrace-spe.o
+obj-$(CONFIG_PPC_TRANSACTIONAL_MEM) += ptrace-tm.o
+obj-$(CONFIG_PPC_ADV_DEBUG_REGS) += ptrace-adv.o
+ifneq ($(CONFIG_PPC_ADV_DEBUG_REGS),y)
+obj-y += ptrace-noadv.o
+endif
diff --git a/arch/powerpc/kernel/ptrace/ptrace-adv.c b/arch/powerpc/kernel/ptrace/ptrace-adv.c
new file mode 100644
index 0000000..3990c01
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-adv.c
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ task->thread.debug.dbcr0 &= ~DBCR0_BT;
+ task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+ regs->msr |= MSR_DE;
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ task->thread.debug.dbcr0 &= ~DBCR0_IC;
+ task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT;
+ regs->msr |= MSR_DE;
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ /*
+ * The logic to disable single stepping should be as
+ * simple as turning off the Instruction Complete flag.
+ * And, after doing so, if all debug flags are off, turn
+ * off DBCR0(IDM) and MSR(DE) .... Torez
+ */
+ task->thread.debug.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
+ /*
+ * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
+ */
+ if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+ task->thread.debug.dbcr1)) {
+ /*
+ * All debug events were off.....
+ */
+ task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ regs->msr &= ~MSR_DE;
+ }
+ }
+ clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+ dbginfo->version = 1;
+ dbginfo->num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
+ dbginfo->num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
+ dbginfo->num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
+ dbginfo->data_bp_alignment = 4;
+ dbginfo->sizeof_condition = 4;
+ dbginfo->features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
+ PPC_DEBUG_FEATURE_INSN_BP_MASK;
+ if (IS_ENABLED(CONFIG_PPC_ADV_DEBUG_DAC_RANGE))
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_RANGE |
+ PPC_DEBUG_FEATURE_DATA_BP_MASK;
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp)
+{
+ /* We only support one DABR and no IABRS at the moment */
+ if (addr > 0)
+ return -EINVAL;
+ return put_user(child->thread.debug.dac1, datalp);
+}
+
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret;
+ struct thread_struct *thread = &task->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+ * For embedded processors we support one DAC and no IAC's at the
+ * moment.
+ */
+ if (addr > 0)
+ return -EINVAL;
+
+ /* The bottom 3 bits in dabr are flags */
+ if ((data & ~0x7UL) >= TASK_SIZE)
+ return -EIO;
+
+ /* As described above, it was assumed 3 bits were passed with the data
+ * address, but we will assume only the mode bits will be passed
+ * as to not cause alignment restrictions for DAC-based processors.
+ */
+
+ /* DAC's hold the whole address without any mode flags */
+ task->thread.debug.dac1 = data & ~0x3UL;
+
+ if (task->thread.debug.dac1 == 0) {
+ dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+ if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+ task->thread.debug.dbcr1)) {
+ task->thread.regs->msr &= ~MSR_DE;
+ task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ }
+ return 0;
+ }
+
+ /* Read or Write bits must be set */
+
+ if (!(data & 0x3UL))
+ return -EINVAL;
+
+ /* Set the Internal Debugging flag (IDM bit 1) for the DBCR0 register */
+ task->thread.debug.dbcr0 |= DBCR0_IDM;
+
+ /* Check for write and read flags and set DBCR0 accordingly */
+ dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+ if (data & 0x1UL)
+ dbcr_dac(task) |= DBCR_DAC1R;
+ if (data & 0x2UL)
+ dbcr_dac(task) |= DBCR_DAC1W;
+ task->thread.regs->msr |= MSR_DE;
+ return 0;
+}
+
+static long set_instruction_bp(struct task_struct *child,
+ struct ppc_hw_breakpoint *bp_info)
+{
+ int slot;
+ int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0);
+ int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0);
+ int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0);
+ int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0);
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+ slot2_in_use = 1;
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+ slot4_in_use = 1;
+
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+ /* Make sure range is valid. */
+ if (bp_info->addr2 >= TASK_SIZE)
+ return -EIO;
+
+ /* We need a pair of IAC regsisters */
+ if (!slot1_in_use && !slot2_in_use) {
+ slot = 1;
+ child->thread.debug.iac1 = bp_info->addr;
+ child->thread.debug.iac2 = bp_info->addr2;
+ child->thread.debug.dbcr0 |= DBCR0_IAC1;
+ if (bp_info->addr_mode ==
+ PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ dbcr_iac_range(child) |= DBCR_IAC12X;
+ else
+ dbcr_iac_range(child) |= DBCR_IAC12I;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ } else if ((!slot3_in_use) && (!slot4_in_use)) {
+ slot = 3;
+ child->thread.debug.iac3 = bp_info->addr;
+ child->thread.debug.iac4 = bp_info->addr2;
+ child->thread.debug.dbcr0 |= DBCR0_IAC3;
+ if (bp_info->addr_mode ==
+ PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ dbcr_iac_range(child) |= DBCR_IAC34X;
+ else
+ dbcr_iac_range(child) |= DBCR_IAC34I;
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ } else {
+ /* We only need one. If possible leave a pair free in
+ * case a range is needed later
+ */
+ if (!slot1_in_use) {
+ /*
+ * Don't use iac1 if iac1-iac2 are free and either
+ * iac3 or iac4 (but not both) are free
+ */
+ if (slot2_in_use || slot3_in_use == slot4_in_use) {
+ slot = 1;
+ child->thread.debug.iac1 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC1;
+ goto out;
+ }
+ }
+ if (!slot2_in_use) {
+ slot = 2;
+ child->thread.debug.iac2 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC2;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ } else if (!slot3_in_use) {
+ slot = 3;
+ child->thread.debug.iac3 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC3;
+ } else if (!slot4_in_use) {
+ slot = 4;
+ child->thread.debug.iac4 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC4;
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ }
+out:
+ child->thread.debug.dbcr0 |= DBCR0_IDM;
+ child->thread.regs->msr |= MSR_DE;
+
+ return slot;
+}
+
+static int del_instruction_bp(struct task_struct *child, int slot)
+{
+ switch (slot) {
+ case 1:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
+ /* address range - clear slots 1 & 2 */
+ child->thread.debug.iac2 = 0;
+ dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
+ }
+ child->thread.debug.iac1 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC1;
+ break;
+ case 2:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+ /* used in a range */
+ return -EINVAL;
+ child->thread.debug.iac2 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC2;
+ break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ case 3:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
+ /* address range - clear slots 3 & 4 */
+ child->thread.debug.iac4 = 0;
+ dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
+ }
+ child->thread.debug.iac3 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC3;
+ break;
+ case 4:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+ /* Used in a range */
+ return -EINVAL;
+ child->thread.debug.iac4 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC4;
+ break;
+#endif
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ int byte_enable =
+ (bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
+ & 0xf;
+ int condition_mode =
+ bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
+ int slot;
+
+ if (byte_enable && condition_mode == 0)
+ return -EINVAL;
+
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
+ slot = 1;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ dbcr_dac(child) |= DBCR_DAC1R;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ dbcr_dac(child) |= DBCR_DAC1W;
+ child->thread.debug.dac1 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ if (byte_enable) {
+ child->thread.debug.dvc1 =
+ (unsigned long)bp_info->condition_value;
+ child->thread.debug.dbcr2 |=
+ ((byte_enable << DBCR2_DVC1BE_SHIFT) |
+ (condition_mode << DBCR2_DVC1M_SHIFT));
+ }
+#endif
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ } else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+ /* Both dac1 and dac2 are part of a range */
+ return -ENOSPC;
+#endif
+ } else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
+ slot = 2;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ dbcr_dac(child) |= DBCR_DAC2R;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ dbcr_dac(child) |= DBCR_DAC2W;
+ child->thread.debug.dac2 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ if (byte_enable) {
+ child->thread.debug.dvc2 =
+ (unsigned long)bp_info->condition_value;
+ child->thread.debug.dbcr2 |=
+ ((byte_enable << DBCR2_DVC2BE_SHIFT) |
+ (condition_mode << DBCR2_DVC2M_SHIFT));
+ }
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ child->thread.debug.dbcr0 |= DBCR0_IDM;
+ child->thread.regs->msr |= MSR_DE;
+
+ return slot + 4;
+}
+
+static int del_dac(struct task_struct *child, int slot)
+{
+ if (slot == 1) {
+ if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
+ return -ENOENT;
+
+ child->thread.debug.dac1 = 0;
+ dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+ child->thread.debug.dac2 = 0;
+ child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
+ }
+ child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ child->thread.debug.dvc1 = 0;
+#endif
+ } else if (slot == 2) {
+ if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
+ return -ENOENT;
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE)
+ /* Part of a range */
+ return -EINVAL;
+ child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ child->thread.debug.dvc2 = 0;
+#endif
+ child->thread.debug.dac2 = 0;
+ dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+static int set_dac_range(struct task_struct *child,
+ struct ppc_hw_breakpoint *bp_info)
+{
+ int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
+
+ /* We don't allow range watchpoints to be used with DVC */
+ if (bp_info->condition_mode)
+ return -EINVAL;
+
+ /*
+ * Best effort to verify the address range. The user/supervisor bits
+ * prevent trapping in kernel space, but let's fail on an obvious bad
+ * range. The simple test on the mask is not fool-proof, and any
+ * exclusive range will spill over into kernel space.
+ */
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+ if (mode == PPC_BREAKPOINT_MODE_MASK) {
+ /*
+ * dac2 is a bitmask. Don't allow a mask that makes a
+ * kernel space address from a valid dac1 value
+ */
+ if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
+ return -EIO;
+ } else {
+ /*
+ * For range breakpoints, addr2 must also be a valid address
+ */
+ if (bp_info->addr2 >= TASK_SIZE)
+ return -EIO;
+ }
+
+ if (child->thread.debug.dbcr0 &
+ (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
+ return -ENOSPC;
+
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
+ child->thread.debug.dac1 = bp_info->addr;
+ child->thread.debug.dac2 = bp_info->addr2;
+ if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+ child->thread.debug.dbcr2 |= DBCR2_DAC12M;
+ else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ child->thread.debug.dbcr2 |= DBCR2_DAC12MX;
+ else /* PPC_BREAKPOINT_MODE_MASK */
+ child->thread.debug.dbcr2 |= DBCR2_DAC12MM;
+ child->thread.regs->msr |= MSR_DE;
+
+ return 5;
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ if (bp_info->version != 1)
+ return -ENOTSUPP;
+ /*
+ * Check for invalid flags and combinations
+ */
+ if (bp_info->trigger_type == 0 ||
+ (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
+ PPC_BREAKPOINT_TRIGGER_RW)) ||
+ (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
+ (bp_info->condition_mode &
+ ~(PPC_BREAKPOINT_CONDITION_MODE |
+ PPC_BREAKPOINT_CONDITION_BE_ALL)))
+ return -EINVAL;
+#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
+ if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+#endif
+
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
+ if (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE ||
+ bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+ return set_instruction_bp(child, bp_info);
+ }
+ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ return set_dac(child, bp_info);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ return set_dac_range(child, bp_info);
+#else
+ return -EINVAL;
+#endif
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+ int rc;
+
+ if (data <= 4)
+ rc = del_instruction_bp(child, (int)data);
+ else
+ rc = del_dac(child, (int)data - 4);
+
+ if (!rc) {
+ if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0,
+ child->thread.debug.dbcr1)) {
+ child->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ child->thread.regs->msr &= ~MSR_DE;
+ }
+ }
+ return rc;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-altivec.c b/arch/powerpc/kernel/ptrace/ptrace-altivec.c
new file mode 100644
index 0000000..0d9bc4b
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-altivec.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go.
+ * The transfer totals 34 quadword. Quadwords 0-31 contain the
+ * corresponding vector registers. Quadword 32 contains the vscr as the
+ * last word (offset 12) within that quadword. Quadword 33 contains the
+ * vrsave as the first word (offset 0) within the quadword.
+ *
+ * This definition of the VMX state is compatible with the current PPC32
+ * ptrace interface. This allows signal handling and ptrace to use the
+ * same structures. This also simplifies the implementation of a bi-arch
+ * (combined (32- and 64-bit) gdb.
+ */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_altivec_to_thread(target);
+ return target->thread.used_vr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ * };
+ */
+int vr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+
+ flush_altivec_to_thread(target);
+
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
+
+ membuf_write(&to, &target->thread.vr_state, 33 * sizeof(vector128));
+ /*
+ * Copy out only the low-order word of vrsave.
+ */
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.vrsave;
+ return membuf_write(&to, &vrsave, sizeof(vrsave));
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ * };
+ */
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ flush_altivec_to_thread(target);
+
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.vr_state, 0,
+ 33 * sizeof(vector128));
+ if (!ret && count > 0) {
+ /*
+ * We use only the first word of vrsave.
+ */
+ int start, end;
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ memset(&vrsave, 0, sizeof(vrsave));
+
+ vrsave.word = target->thread.vrsave;
+
+ start = 33 * sizeof(vector128);
+ end = start + sizeof(vrsave);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+ start, end);
+ if (!ret)
+ target->thread.vrsave = vrsave.word;
+ }
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
new file mode 100644
index 0000000..67447a6
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+/*
+ * Set of msr bits that gdb can change on behalf of a process.
+ */
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#define MSR_DEBUGCHANGE 0
+#else
+#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE)
+#endif
+
+/*
+ * Max register writeable via put_reg
+ */
+#ifdef CONFIG_PPC32
+#define PT_MAX_PUT_REG PT_MQ
+#else
+#define PT_MAX_PUT_REG PT_CCR
+#endif
+
+#define TVSO(f) (offsetof(struct thread_vr_state, f))
+#define TFSO(f) (offsetof(struct thread_fp_state, f))
+#define TSO(f) (offsetof(struct thread_struct, f))
+
+/*
+ * These are our native regset flavors.
+ */
+enum powerpc_regset {
+ REGSET_GPR,
+ REGSET_FPR,
+#ifdef CONFIG_ALTIVEC
+ REGSET_VMX,
+#endif
+#ifdef CONFIG_VSX
+ REGSET_VSX,
+#endif
+#ifdef CONFIG_SPE
+ REGSET_SPE,
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ REGSET_TM_CGPR, /* TM checkpointed GPR registers */
+ REGSET_TM_CFPR, /* TM checkpointed FPR registers */
+ REGSET_TM_CVMX, /* TM checkpointed VMX registers */
+ REGSET_TM_CVSX, /* TM checkpointed VSX registers */
+ REGSET_TM_SPR, /* TM specific SPR registers */
+ REGSET_TM_CTAR, /* TM checkpointed TAR register */
+ REGSET_TM_CPPR, /* TM checkpointed PPR register */
+ REGSET_TM_CDSCR, /* TM checkpointed DSCR register */
+#endif
+#ifdef CONFIG_PPC64
+ REGSET_PPR, /* PPR register */
+ REGSET_DSCR, /* DSCR register */
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ REGSET_TAR, /* TAR register */
+ REGSET_EBB, /* EBB registers */
+ REGSET_PMR, /* Performance Monitor Registers */
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+ REGSET_PKEY, /* AMR register */
+#endif
+};
+
+/* ptrace-(no)vsx */
+
+user_regset_get2_fn fpr_get;
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-vsx */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn vsr_get;
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-altivec */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn vr_get;
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-spe */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn evr_get;
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace */
+
+int gpr32_get_common(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to,
+ unsigned long *regs);
+int gpr32_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ unsigned long *regs);
+
+/* ptrace-tm */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void flush_tmregs_to_thread(struct task_struct *tsk);
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cgpr_get;
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cfpr_get;
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cvmx_get;
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cvsx_get;
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_spr_get;
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_tar_get;
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_ppr_get;
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_dscr_get;
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+user_regset_get2_fn tm_cgpr32_get;
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-view */
+
+extern const struct user_regset_view user_ppc_native_view;
+
+/* ptrace-(no)adv */
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp);
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data);
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info);
+long ppc_del_hwdebug(struct task_struct *child, long data);
diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c
new file mode 100644
index 0000000..aa36fca
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include <asm/debug.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ regs->msr &= ~MSR_BE;
+ regs->msr |= MSR_SE;
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ regs->msr &= ~MSR_SE;
+ regs->msr |= MSR_BE;
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL)
+ regs->msr &= ~(MSR_SE | MSR_BE);
+
+ clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+ dbginfo->version = 1;
+ dbginfo->num_instruction_bps = 0;
+ if (ppc_breakpoint_available())
+ dbginfo->num_data_bps = nr_wp_slots();
+ else
+ dbginfo->num_data_bps = 0;
+ dbginfo->num_condition_regs = 0;
+ dbginfo->data_bp_alignment = sizeof(long);
+ dbginfo->sizeof_condition = 0;
+ if (IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT)) {
+ dbginfo->features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
+ if (dawr_enabled())
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
+ } else {
+ dbginfo->features = 0;
+ }
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_ARCH_31;
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp)
+{
+ unsigned long dabr_fake;
+
+ /* We only support one DABR and no IABRS at the moment */
+ if (addr > 0)
+ return -EINVAL;
+ dabr_fake = ((child->thread.hw_brk[0].address & (~HW_BRK_TYPE_DABR)) |
+ (child->thread.hw_brk[0].type & HW_BRK_TYPE_DABR));
+ return put_user(dabr_fake, datalp);
+}
+
+/*
+ * ptrace_set_debugreg() fakes DABR and DABR is only one. So even if
+ * internal hw supports more than one watchpoint, we support only one
+ * watchpoint with this interface.
+ */
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret;
+ struct thread_struct *thread = &task->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ bool set_bp = true;
+ struct arch_hw_breakpoint hw_brk;
+
+ /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+ * For embedded processors we support one DAC and no IAC's at the
+ * moment.
+ */
+ if (addr > 0)
+ return -EINVAL;
+
+ /* The bottom 3 bits in dabr are flags */
+ if ((data & ~0x7UL) >= TASK_SIZE)
+ return -EIO;
+
+ /* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
+ * It was assumed, on previous implementations, that 3 bits were
+ * passed together with the data address, fitting the design of the
+ * DABR register, as follows:
+ *
+ * bit 0: Read flag
+ * bit 1: Write flag
+ * bit 2: Breakpoint translation
+ *
+ * Thus, we use them here as so.
+ */
+
+ /* Ensure breakpoint translation bit is set */
+ if (data && !(data & HW_BRK_TYPE_TRANSLATE))
+ return -EIO;
+ hw_brk.address = data & (~HW_BRK_TYPE_DABR);
+ hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
+ hw_brk.len = DABR_MAX_LEN;
+ hw_brk.hw_len = DABR_MAX_LEN;
+ set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ bp = thread->ptrace_bps[0];
+ if (!set_bp) {
+ if (bp) {
+ unregister_hw_breakpoint(bp);
+ thread->ptrace_bps[0] = NULL;
+ }
+ return 0;
+ }
+ if (bp) {
+ attr = bp->attr;
+ attr.bp_addr = hw_brk.address;
+ attr.bp_len = DABR_MAX_LEN;
+ arch_bp_generic_fields(hw_brk.type, &attr.bp_type);
+
+ /* Enable breakpoint */
+ attr.disabled = false;
+
+ ret = modify_user_hw_breakpoint(bp, &attr);
+ if (ret)
+ return ret;
+
+ thread->ptrace_bps[0] = bp;
+ thread->hw_brk[0] = hw_brk;
+ return 0;
+ }
+
+ /* Create a new breakpoint request if one doesn't exist already */
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = hw_brk.address;
+ attr.bp_len = DABR_MAX_LEN;
+ arch_bp_generic_fields(hw_brk.type,
+ &attr.bp_type);
+
+ thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
+ ptrace_triggered, NULL, task);
+ if (IS_ERR(bp)) {
+ thread->ptrace_bps[0] = NULL;
+ return PTR_ERR(bp);
+ }
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+ if (set_bp && (!ppc_breakpoint_available()))
+ return -ENODEV;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ task->thread.hw_brk[0] = hw_brk;
+ return 0;
+}
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static int find_empty_ptrace_bp(struct thread_struct *thread)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!thread->ptrace_bps[i])
+ return i;
+ }
+ return -1;
+}
+#endif
+
+static int find_empty_hw_brk(struct thread_struct *thread)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!thread->hw_brk[i].address)
+ return i;
+ }
+ return -1;
+}
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ int i;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int len = 0;
+ struct thread_struct *thread = &child->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ struct arch_hw_breakpoint brk;
+
+ if (bp_info->version != 1)
+ return -ENOTSUPP;
+ /*
+ * We only support one data breakpoint
+ */
+ if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
+ (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
+ bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+
+ if ((unsigned long)bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE);
+ brk.type = HW_BRK_TYPE_TRANSLATE | HW_BRK_TYPE_PRIV_ALL;
+ brk.len = DABR_MAX_LEN;
+ brk.hw_len = DABR_MAX_LEN;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ brk.type |= HW_BRK_TYPE_READ;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ brk.type |= HW_BRK_TYPE_WRITE;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+ len = bp_info->addr2 - bp_info->addr;
+ else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ len = 1;
+ else
+ return -EINVAL;
+
+ i = find_empty_ptrace_bp(thread);
+ if (i < 0)
+ return -ENOSPC;
+
+ /* Create a new breakpoint request if one doesn't exist already */
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = (unsigned long)bp_info->addr;
+ attr.bp_len = len;
+ arch_bp_generic_fields(brk.type, &attr.bp_type);
+
+ bp = register_user_hw_breakpoint(&attr, ptrace_triggered, NULL, child);
+ thread->ptrace_bps[i] = bp;
+ if (IS_ERR(bp)) {
+ thread->ptrace_bps[i] = NULL;
+ return PTR_ERR(bp);
+ }
+
+ return i + 1;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT)
+ return -EINVAL;
+
+ i = find_empty_hw_brk(&child->thread);
+ if (i < 0)
+ return -ENOSPC;
+
+ if (!ppc_breakpoint_available())
+ return -ENODEV;
+
+ child->thread.hw_brk[i] = brk;
+
+ return i + 1;
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret = 0;
+ struct thread_struct *thread = &child->thread;
+ struct perf_event *bp;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ if (data < 1 || data > nr_wp_slots())
+ return -EINVAL;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ bp = thread->ptrace_bps[data - 1];
+ if (bp) {
+ unregister_hw_breakpoint(bp);
+ thread->ptrace_bps[data - 1] = NULL;
+ } else {
+ ret = -ENOENT;
+ }
+ return ret;
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
+ if (!(child->thread.hw_brk[data - 1].flags & HW_BRK_FLAG_DISABLED) &&
+ child->thread.hw_brk[data - 1].address == 0)
+ return -ENOENT;
+
+ child->thread.hw_brk[data - 1].address = 0;
+ child->thread.hw_brk[data - 1].type = 0;
+ child->thread.hw_brk[data - 1].flags = 0;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-novsx.c b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
new file mode 100644
index 0000000..b3b3683
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32]));
+
+ flush_fp_to_thread(target);
+
+ return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64));
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32]));
+
+ flush_fp_to_thread(target);
+
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.fp_state, 0, -1);
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-spe.c b/arch/powerpc/kernel/ptrace/ptrace-spe.c
new file mode 100644
index 0000000..47034d0
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-spe.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * For get_evrregs/set_evrregs functions 'data' has the following layout:
+ *
+ * struct {
+ * u32 evr[32];
+ * u64 acc;
+ * u32 spefscr;
+ * }
+ */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_spe_to_thread(target);
+ return target->thread.used_spe ? regset->n : 0;
+}
+
+int evr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ flush_spe_to_thread(target);
+
+ membuf_write(&to, &target->thread.evr, sizeof(target->thread.evr));
+
+ BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+ offsetof(struct thread_struct, spefscr));
+
+ return membuf_write(&to, &target->thread.acc,
+ sizeof(u64) + sizeof(u32));
+}
+
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ flush_spe_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.evr,
+ 0, sizeof(target->thread.evr));
+
+ BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+ offsetof(struct thread_struct, spefscr));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.acc,
+ sizeof(target->thread.evr), -1);
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
new file mode 100644
index 0000000..54f2d07
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c
@@ -0,0 +1,787 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/asm-prototypes.h>
+
+#include "ptrace-decl.h"
+
+void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+ /*
+ * If task is not current, it will have been flushed already to
+ * it's thread_struct during __switch_to().
+ *
+ * A reclaim flushes ALL the state or if not in TM save TM SPRs
+ * in the appropriate thread structures from live.
+ */
+
+ if (!cpu_has_feature(CPU_FTR_TM) || tsk != current)
+ return;
+
+ if (MSR_TM_SUSPENDED(mfmsr())) {
+ tm_reclaim_current(TM_CAUSE_SIGNAL);
+ } else {
+ tm_enable();
+ tm_save_sprs(&tsk->thread);
+ }
+}
+
+static unsigned long get_user_ckpt_msr(struct task_struct *task)
+{
+ return task->thread.ckpt_regs.msr | task->thread.fpexc_mode;
+}
+
+static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr)
+{
+ task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE;
+ task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE;
+ return 0;
+}
+
+static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap)
+{
+ set_trap(&task->thread.ckpt_regs, trap);
+ return 0;
+}
+
+/**
+ * tm_cgpr_active - get active number of registers in CGPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed GPR category.
+ */
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cgpr_get - get CGPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds all the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function gets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ membuf_write(&to, &target->thread.ckpt_regs,
+ offsetof(struct pt_regs, msr));
+ membuf_store(&to, get_user_ckpt_msr(target));
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ membuf_write(&to, &target->thread.ckpt_regs.orig_gpr3,
+ sizeof(struct user_pt_regs) -
+ offsetof(struct pt_regs, orig_gpr3));
+ return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
+ sizeof(struct user_pt_regs));
+}
+
+/*
+ * tm_cgpr_set - set the CGPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function sets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ unsigned long reg;
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ckpt_regs,
+ 0, PT_MSR * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
+ PT_MSR * sizeof(reg),
+ (PT_MSR + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_ckpt_msr(target, reg);
+ }
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ckpt_regs.orig_gpr3,
+ PT_ORIG_R3 * sizeof(reg),
+ (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+ if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+ ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
+ PT_TRAP * sizeof(reg),
+ (PT_TRAP + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_ckpt_trap(target, reg);
+ }
+
+ if (!ret)
+ ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+
+ return ret;
+}
+
+/**
+ * tm_cfpr_active - get active number of registers in CFPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed FPR category.
+ */
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cfpr_get - get CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed FPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ *};
+ */
+int tm_cfpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[33];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* copy to local buffer then write that out */
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_CKFPR(i);
+ buf[32] = target->thread.ckfp_state.fpscr;
+ return membuf_write(&to, buf, sizeof(buf));
+}
+
+/**
+ * tm_cfpr_set - set CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * FPR register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ *};
+ */
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[33];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ for (i = 0; i < 32; i++)
+ buf[i] = target->thread.TS_CKFPR(i);
+ buf[32] = target->thread.ckfp_state.fpscr;
+
+ /* copy to local buffer then write that out */
+ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+ if (i)
+ return i;
+ for (i = 0; i < 32 ; i++)
+ target->thread.TS_CKFPR(i) = buf[i];
+ target->thread.ckfp_state.fpscr = buf[32];
+ return 0;
+}
+
+/**
+ * tm_cvmx_active - get active number of registers in CVMX
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in checkpointed VMX category.
+ */
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cvmx_get - get CMVX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ *};
+ */
+int tm_cvmx_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ membuf_write(&to, &target->thread.ckvr_state, 33 * sizeof(vector128));
+ /*
+ * Copy out only the low-order word of vrsave.
+ */
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.ckvrsave;
+ return membuf_write(&to, &vrsave, sizeof(vrsave));
+}
+
+/**
+ * tm_cvmx_set - set CMVX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ *};
+ */
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ckvr_state,
+ 0, 33 * sizeof(vector128));
+ if (!ret && count > 0) {
+ /*
+ * We use only the low-order word of vrsave.
+ */
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.ckvrsave;
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+ 33 * sizeof(vector128), -1);
+ if (!ret)
+ target->thread.ckvrsave = vrsave.word;
+ }
+
+ return ret;
+}
+
+/**
+ * tm_cvsx_active - get active number of registers in CVSX
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed VSX category.
+ */
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ flush_vsx_to_thread(target);
+ return target->thread.used_vsr ? regset->n : 0;
+}
+
+/**
+ * tm_cvsx_get - get CVSX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed VSX registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 vsx[32];
+ *};
+ */
+int tm_cvsx_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[32];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+ return membuf_write(&to, buf, 32 * sizeof(double));
+}
+
+/**
+ * tm_cvsx_set - set CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * VSX register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 vsx[32];
+ *};
+ */
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[32];
+ int ret, i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ buf, 0, 32 * sizeof(double));
+ if (!ret)
+ for (i = 0; i < 32 ; i++)
+ target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+ return ret;
+}
+
+/**
+ * tm_spr_active - get active number of registers in TM SPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks the active number of available
+ * regisers in the transactional memory SPR category.
+ */
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+/**
+ * tm_spr_get - get the TM related SPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ * u64 tm_tfhar;
+ * u64 tm_texasr;
+ * u64 tm_tfiar;
+ * };
+ */
+int tm_spr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+ BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+ BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ /* Flush the states */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* TFHAR register */
+ membuf_write(&to, &target->thread.tm_tfhar, sizeof(u64));
+ /* TEXASR register */
+ membuf_write(&to, &target->thread.tm_texasr, sizeof(u64));
+ /* TFIAR register */
+ return membuf_write(&to, &target->thread.tm_tfiar, sizeof(u64));
+}
+
+/**
+ * tm_spr_set - set the TM related SPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ * u64 tm_tfhar;
+ * u64 tm_texasr;
+ * u64 tm_tfiar;
+ * };
+ */
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+ BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+ BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ /* Flush the states */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* TFHAR register */
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tfhar, 0, sizeof(u64));
+
+ /* TEXASR register */
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_texasr, sizeof(u64),
+ 2 * sizeof(u64));
+
+ /* TFIAR register */
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tfiar,
+ 2 * sizeof(u64), 3 * sizeof(u64));
+ return ret;
+}
+
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+int tm_tar_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_tar, sizeof(u64));
+}
+
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tar, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+
+int tm_ppr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_ppr, sizeof(u64));
+}
+
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_ppr, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+int tm_dscr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_dscr, sizeof(u64));
+}
+
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_dscr, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_cgpr32_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ gpr32_get_common(target, regset, to,
+ &target->thread.ckpt_regs.gpr[0]);
+ return membuf_zero(&to, ELF_NGREG * sizeof(u32));
+}
+
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+ &target->thread.ckpt_regs.gpr[0]);
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
new file mode 100644
index 0000000..7e6478e
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -0,0 +1,859 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/nospec.h>
+#include <linux/pkeys.h>
+
+#include "ptrace-decl.h"
+
+struct pt_regs_offset {
+ const char *name;
+ int offset;
+};
+
+#define STR(s) #s /* convert to string */
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define GPR_OFFSET_NAME(num) \
+ {.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
+ {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+ GPR_OFFSET_NAME(0),
+ GPR_OFFSET_NAME(1),
+ GPR_OFFSET_NAME(2),
+ GPR_OFFSET_NAME(3),
+ GPR_OFFSET_NAME(4),
+ GPR_OFFSET_NAME(5),
+ GPR_OFFSET_NAME(6),
+ GPR_OFFSET_NAME(7),
+ GPR_OFFSET_NAME(8),
+ GPR_OFFSET_NAME(9),
+ GPR_OFFSET_NAME(10),
+ GPR_OFFSET_NAME(11),
+ GPR_OFFSET_NAME(12),
+ GPR_OFFSET_NAME(13),
+ GPR_OFFSET_NAME(14),
+ GPR_OFFSET_NAME(15),
+ GPR_OFFSET_NAME(16),
+ GPR_OFFSET_NAME(17),
+ GPR_OFFSET_NAME(18),
+ GPR_OFFSET_NAME(19),
+ GPR_OFFSET_NAME(20),
+ GPR_OFFSET_NAME(21),
+ GPR_OFFSET_NAME(22),
+ GPR_OFFSET_NAME(23),
+ GPR_OFFSET_NAME(24),
+ GPR_OFFSET_NAME(25),
+ GPR_OFFSET_NAME(26),
+ GPR_OFFSET_NAME(27),
+ GPR_OFFSET_NAME(28),
+ GPR_OFFSET_NAME(29),
+ GPR_OFFSET_NAME(30),
+ GPR_OFFSET_NAME(31),
+ REG_OFFSET_NAME(nip),
+ REG_OFFSET_NAME(msr),
+ REG_OFFSET_NAME(ctr),
+ REG_OFFSET_NAME(link),
+ REG_OFFSET_NAME(xer),
+ REG_OFFSET_NAME(ccr),
+#ifdef CONFIG_PPC64
+ REG_OFFSET_NAME(softe),
+#else
+ REG_OFFSET_NAME(mq),
+#endif
+ REG_OFFSET_NAME(trap),
+ REG_OFFSET_NAME(dar),
+ REG_OFFSET_NAME(dsisr),
+ REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name: the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->offset;
+ return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset: the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (roff->offset == offset)
+ return roff->name;
+ return NULL;
+}
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+static unsigned long get_user_msr(struct task_struct *task)
+{
+ return task->thread.regs->msr | task->thread.fpexc_mode;
+}
+
+static int set_user_msr(struct task_struct *task, unsigned long msr)
+{
+ task->thread.regs->msr &= ~MSR_DEBUGCHANGE;
+ task->thread.regs->msr |= msr & MSR_DEBUGCHANGE;
+ return 0;
+}
+
+#ifdef CONFIG_PPC64
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+ *data = task->thread.dscr;
+ return 0;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+ task->thread.dscr = dscr;
+ task->thread.dscr_inherit = 1;
+ return 0;
+}
+#else
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+ return -EIO;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+ return -EIO;
+}
+#endif
+
+/*
+ * We prevent mucking around with the reserved area of trap
+ * which are used internally by the kernel.
+ */
+static int set_user_trap(struct task_struct *task, unsigned long trap)
+{
+ set_trap(task->thread.regs, trap);
+ return 0;
+}
+
+/*
+ * Get contents of register REGNO in task TASK.
+ */
+int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
+{
+ unsigned int regs_max;
+
+ if (task->thread.regs == NULL || !data)
+ return -EIO;
+
+ if (regno == PT_MSR) {
+ *data = get_user_msr(task);
+ return 0;
+ }
+
+ if (regno == PT_DSCR)
+ return get_user_dscr(task, data);
+
+ /*
+ * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
+ * no more used as a flag, lets force usr to alway see the softe value as 1
+ * which means interrupts are not soft disabled.
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && regno == PT_SOFTE) {
+ *data = 1;
+ return 0;
+ }
+
+ regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
+ if (regno < regs_max) {
+ regno = array_index_nospec(regno, regs_max);
+ *data = ((unsigned long *)task->thread.regs)[regno];
+ return 0;
+ }
+
+ return -EIO;
+}
+
+/*
+ * Write contents of register REGNO in task TASK.
+ */
+int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
+{
+ if (task->thread.regs == NULL)
+ return -EIO;
+
+ if (regno == PT_MSR)
+ return set_user_msr(task, data);
+ if (regno == PT_TRAP)
+ return set_user_trap(task, data);
+ if (regno == PT_DSCR)
+ return set_user_dscr(task, data);
+
+ if (regno <= PT_MAX_PUT_REG) {
+ regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
+ ((unsigned long *)task->thread.regs)[regno] = data;
+ return 0;
+ }
+ return -EIO;
+}
+
+static int gpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ int i;
+
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ if (!FULL_REGS(target->thread.regs)) {
+ /* We have a partial register set. Fill 14-31 with bogus values */
+ for (i = 14; i < 32; i++)
+ target->thread.regs->gpr[i] = NV_REG_POISON;
+ }
+
+ membuf_write(&to, target->thread.regs, offsetof(struct pt_regs, msr));
+ membuf_store(&to, get_user_msr(target));
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ membuf_write(&to, &target->thread.regs->orig_gpr3,
+ sizeof(struct user_pt_regs) -
+ offsetof(struct pt_regs, orig_gpr3));
+ return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
+ sizeof(struct user_pt_regs));
+}
+
+static int gpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ unsigned long reg;
+ int ret;
+
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ CHECK_FULL_REGS(target->thread.regs);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ target->thread.regs,
+ 0, PT_MSR * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
+ PT_MSR * sizeof(reg),
+ (PT_MSR + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_msr(target, reg);
+ }
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.regs->orig_gpr3,
+ PT_ORIG_R3 * sizeof(reg),
+ (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+ if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+ ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®,
+ PT_TRAP * sizeof(reg),
+ (PT_TRAP + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_trap(target, reg);
+ }
+
+ if (!ret)
+ ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+
+ return ret;
+}
+
+#ifdef CONFIG_PPC64
+static int ppr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ return membuf_write(&to, &target->thread.regs->ppr, sizeof(u64));
+}
+
+static int ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.regs->ppr, 0, sizeof(u64));
+}
+
+static int dscr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ return membuf_write(&to, &target->thread.dscr, sizeof(u64));
+}
+static int dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.dscr, 0, sizeof(u64));
+}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+static int tar_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ return membuf_write(&to, &target->thread.tar, sizeof(u64));
+}
+static int tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tar, 0, sizeof(u64));
+}
+
+static int ebb_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (target->thread.used_ebb)
+ return regset->n;
+
+ return 0;
+}
+
+static int ebb_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+ BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (!target->thread.used_ebb)
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.ebbrr, 3 * sizeof(unsigned long));
+}
+
+static int ebb_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ int ret = 0;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+ BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (target->thread.used_ebb)
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ebbrr,
+ 0, sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ebbhr, sizeof(unsigned long),
+ 2 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.bescr, 2 * sizeof(unsigned long),
+ 3 * sizeof(unsigned long));
+
+ return ret;
+}
+static int pmu_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int pmu_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+ BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+ BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+ BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return membuf_write(&to, &target->thread.siar, 5 * sizeof(unsigned long));
+}
+
+static int pmu_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ int ret = 0;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+ BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+ BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+ BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.siar,
+ 0, sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.sdar, sizeof(unsigned long),
+ 2 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.sier, 2 * sizeof(unsigned long),
+ 3 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.mmcr2, 3 * sizeof(unsigned long),
+ 4 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.mmcr0, 4 * sizeof(unsigned long),
+ 5 * sizeof(unsigned long));
+ return ret;
+}
+#endif
+
+#ifdef CONFIG_PPC_MEM_KEYS
+static int pkey_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int pkey_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
+
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ membuf_write(&to, &target->thread.amr, 2 * sizeof(unsigned long));
+ return membuf_store(&to, default_uamor);
+}
+
+static int pkey_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ u64 new_amr;
+ int ret;
+
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ /* Only the AMR can be set from userspace */
+ if (pos != 0 || count != sizeof(new_amr))
+ return -EINVAL;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &new_amr, 0, sizeof(new_amr));
+ if (ret)
+ return ret;
+
+ /*
+ * UAMOR determines which bits of the AMR can be set from userspace.
+ * UAMOR value 0b11 indicates that the AMR value can be modified
+ * from userspace. If the kernel is using a specific key, we avoid
+ * userspace modifying the AMR value for that key by masking them
+ * via UAMOR 0b00.
+ *
+ * Pick the AMR values for the keys that kernel is using. This
+ * will be indicated by the ~default_uamor bits.
+ */
+ target->thread.amr = (new_amr & default_uamor) | (target->thread.amr & ~default_uamor);
+
+ return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
+static const struct user_regset native_regsets[] = {
+ [REGSET_GPR] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .regset_get = gpr_get, .set = gpr_set
+ },
+ [REGSET_FPR] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .regset_get = fpr_get, .set = fpr_set
+ },
+#ifdef CONFIG_ALTIVEC
+ [REGSET_VMX] = {
+ .core_note_type = NT_PPC_VMX, .n = 34,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = vr_active, .regset_get = vr_get, .set = vr_set
+ },
+#endif
+#ifdef CONFIG_VSX
+ [REGSET_VSX] = {
+ .core_note_type = NT_PPC_VSX, .n = 32,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = vsr_active, .regset_get = vsr_get, .set = vsr_set
+ },
+#endif
+#ifdef CONFIG_SPE
+ [REGSET_SPE] = {
+ .core_note_type = NT_PPC_SPE, .n = 35,
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = evr_active, .regset_get = evr_get, .set = evr_set
+ },
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ [REGSET_TM_CGPR] = {
+ .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .active = tm_cgpr_active, .regset_get = tm_cgpr_get, .set = tm_cgpr_set
+ },
+ [REGSET_TM_CFPR] = {
+ .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
+ },
+ [REGSET_TM_CVMX] = {
+ .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
+ },
+ [REGSET_TM_CVSX] = {
+ .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
+ },
+ [REGSET_TM_SPR] = {
+ .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
+ },
+ [REGSET_TM_CTAR] = {
+ .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
+ },
+ [REGSET_TM_CPPR] = {
+ .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
+ },
+ [REGSET_TM_CDSCR] = {
+ .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC64
+ [REGSET_PPR] = {
+ .core_note_type = NT_PPC_PPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = ppr_get, .set = ppr_set
+ },
+ [REGSET_DSCR] = {
+ .core_note_type = NT_PPC_DSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = dscr_get, .set = dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ [REGSET_TAR] = {
+ .core_note_type = NT_PPC_TAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = tar_get, .set = tar_set
+ },
+ [REGSET_EBB] = {
+ .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = ebb_active, .regset_get = ebb_get, .set = ebb_set
+ },
+ [REGSET_PMR] = {
+ .core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = pmu_active, .regset_get = pmu_get, .set = pmu_set
+ },
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+ [REGSET_PKEY] = {
+ .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = pkey_active, .regset_get = pkey_get, .set = pkey_set
+ },
+#endif
+};
+
+const struct user_regset_view user_ppc_native_view = {
+ .name = UTS_MACHINE, .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI,
+ .regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
+};
+
+#include <linux/compat.h>
+
+int gpr32_get_common(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to, unsigned long *regs)
+{
+ int i;
+
+ for (i = 0; i < PT_MSR; i++)
+ membuf_store(&to, (u32)regs[i]);
+ membuf_store(&to, (u32)get_user_msr(target));
+ for (i++ ; i < PT_REGS_COUNT; i++)
+ membuf_store(&to, (u32)regs[i]);
+ return membuf_zero(&to, (ELF_NGREG - PT_REGS_COUNT) * sizeof(u32));
+}
+
+int gpr32_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ unsigned long *regs)
+{
+ const compat_ulong_t *k = kbuf;
+ const compat_ulong_t __user *u = ubuf;
+ compat_ulong_t reg;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ if (kbuf)
+ for (; count > 0 && pos < PT_MSR; --count)
+ regs[pos++] = *k++;
+ else
+ for (; count > 0 && pos < PT_MSR; --count) {
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ regs[pos++] = reg;
+ }
+
+
+ if (count > 0 && pos == PT_MSR) {
+ if (kbuf)
+ reg = *k++;
+ else if (__get_user(reg, u++))
+ return -EFAULT;
+ set_user_msr(target, reg);
+ ++pos;
+ --count;
+ }
+
+ if (kbuf) {
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
+ regs[pos++] = *k++;
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ ++k;
+ } else {
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ regs[pos++] = reg;
+ }
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ if (__get_user(reg, u++))
+ return -EFAULT;
+ }
+
+ if (count > 0 && pos == PT_TRAP) {
+ if (kbuf)
+ reg = *k++;
+ else if (__get_user(reg, u++))
+ return -EFAULT;
+ set_user_trap(target, reg);
+ ++pos;
+ --count;
+ }
+
+ kbuf = k;
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+}
+
+static int gpr32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ int i;
+
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ if (!FULL_REGS(target->thread.regs)) {
+ /*
+ * We have a partial register set.
+ * Fill 14-31 with bogus values.
+ */
+ for (i = 14; i < 32; i++)
+ target->thread.regs->gpr[i] = NV_REG_POISON;
+ }
+ return gpr32_get_common(target, regset, to,
+ &target->thread.regs->gpr[0]);
+}
+
+static int gpr32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ CHECK_FULL_REGS(target->thread.regs);
+ return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+ &target->thread.regs->gpr[0]);
+}
+
+/*
+ * These are the regset flavors matching the CONFIG_PPC32 native set.
+ */
+static const struct user_regset compat_regsets[] = {
+ [REGSET_GPR] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
+ .regset_get = gpr32_get, .set = gpr32_set
+ },
+ [REGSET_FPR] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .regset_get = fpr_get, .set = fpr_set
+ },
+#ifdef CONFIG_ALTIVEC
+ [REGSET_VMX] = {
+ .core_note_type = NT_PPC_VMX, .n = 34,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = vr_active, .regset_get = vr_get, .set = vr_set
+ },
+#endif
+#ifdef CONFIG_SPE
+ [REGSET_SPE] = {
+ .core_note_type = NT_PPC_SPE, .n = 35,
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = evr_active, .regset_get = evr_get, .set = evr_set
+ },
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ [REGSET_TM_CGPR] = {
+ .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .active = tm_cgpr_active,
+ .regset_get = tm_cgpr32_get, .set = tm_cgpr32_set
+ },
+ [REGSET_TM_CFPR] = {
+ .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
+ },
+ [REGSET_TM_CVMX] = {
+ .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
+ },
+ [REGSET_TM_CVSX] = {
+ .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
+ },
+ [REGSET_TM_SPR] = {
+ .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
+ },
+ [REGSET_TM_CTAR] = {
+ .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
+ },
+ [REGSET_TM_CPPR] = {
+ .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
+ },
+ [REGSET_TM_CDSCR] = {
+ .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC64
+ [REGSET_PPR] = {
+ .core_note_type = NT_PPC_PPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = ppr_get, .set = ppr_set
+ },
+ [REGSET_DSCR] = {
+ .core_note_type = NT_PPC_DSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = dscr_get, .set = dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ [REGSET_TAR] = {
+ .core_note_type = NT_PPC_TAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = tar_get, .set = tar_set
+ },
+ [REGSET_EBB] = {
+ .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = ebb_active, .regset_get = ebb_get, .set = ebb_set
+ },
+#endif
+};
+
+static const struct user_regset_view user_ppc_compat_view = {
+ .name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
+ .regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ if (IS_ENABLED(CONFIG_PPC64) && test_tsk_thread_flag(task, TIF_32BIT))
+ return &user_ppc_compat_view;
+ return &user_ppc_native_view;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
new file mode 100644
index 0000000..1da4303
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[33];
+ int i;
+
+ flush_fp_to_thread(target);
+
+ /* copy to local buffer then write that out */
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_FPR(i);
+ buf[32] = target->thread.fp_state.fpscr;
+ return membuf_write(&to, buf, 33 * sizeof(u64));
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[33];
+ int i;
+
+ flush_fp_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_FPR(i);
+ buf[32] = target->thread.fp_state.fpscr;
+
+ /* copy to local buffer then write that out */
+ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+ if (i)
+ return i;
+
+ for (i = 0; i < 32 ; i++)
+ target->thread.TS_FPR(i) = buf[i];
+ target->thread.fp_state.fpscr = buf[32];
+ return 0;
+}
+
+/*
+ * Currently to set and and get all the vsx state, you need to call
+ * the fp and VMX calls as well. This only get/sets the lower 32
+ * 128bit VSX registers.
+ */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_vsx_to_thread(target);
+ return target->thread.used_vsr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 vsx[32];
+ * };
+ */
+int vsr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[32];
+ int i;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ return membuf_write(&to, buf, 32 * sizeof(double));
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 vsx[32];
+ * };
+ */
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[32];
+ int ret, i;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ buf, 0, 32 * sizeof(double));
+ if (!ret)
+ for (i = 0; i < 32 ; i++)
+ target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
new file mode 100644
index 0000000..f6e51be
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -0,0 +1,481 @@
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/m68k/kernel/ptrace.c"
+ * Copyright (C) 1994 by Hamish Macdonald
+ * Taken from linux/kernel/ptrace.c and modified for M680x0.
+ * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
+ *
+ * Modified by Cort Dougan (cort@hq.fsmlabs.com)
+ * and Paul Mackerras (paulus@samba.org).
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/regset.h>
+#include <linux/tracehook.h>
+#include <linux/audit.h>
+#include <linux/context_tracking.h>
+#include <linux/syscalls.h>
+
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+#include <asm/debug.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure single step bits etc are not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ /* make sure the single step bit is not set. */
+ user_disable_single_step(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
+{
+ int ret = -EPERM;
+ void __user *datavp = (void __user *) data;
+ unsigned long __user *datalp = datavp;
+
+ switch (request) {
+ /* read the word at location addr in the USER area. */
+ case PTRACE_PEEKUSR: {
+ unsigned long index, tmp;
+
+ ret = -EIO;
+ /* convert to index and check */
+#ifdef CONFIG_PPC32
+ index = addr >> 2;
+ if ((addr & 3) || (index > PT_FPSCR)
+ || (child->thread.regs == NULL))
+#else
+ index = addr >> 3;
+ if ((addr & 7) || (index > PT_FPSCR))
+#endif
+ break;
+
+ CHECK_FULL_REGS(child->thread.regs);
+ if (index < PT_FPR0) {
+ ret = ptrace_get_reg(child, (int) index, &tmp);
+ if (ret)
+ break;
+ } else {
+ unsigned int fpidx = index - PT_FPR0;
+
+ flush_fp_to_thread(child);
+ if (fpidx < (PT_FPSCR - PT_FPR0))
+ memcpy(&tmp, &child->thread.TS_FPR(fpidx),
+ sizeof(long));
+ else
+ tmp = child->thread.fp_state.fpscr;
+ }
+ ret = put_user(tmp, datalp);
+ break;
+ }
+
+ /* write the word at location addr in the USER area */
+ case PTRACE_POKEUSR: {
+ unsigned long index;
+
+ ret = -EIO;
+ /* convert to index and check */
+#ifdef CONFIG_PPC32
+ index = addr >> 2;
+ if ((addr & 3) || (index > PT_FPSCR)
+ || (child->thread.regs == NULL))
+#else
+ index = addr >> 3;
+ if ((addr & 7) || (index > PT_FPSCR))
+#endif
+ break;
+
+ CHECK_FULL_REGS(child->thread.regs);
+ if (index < PT_FPR0) {
+ ret = ptrace_put_reg(child, index, data);
+ } else {
+ unsigned int fpidx = index - PT_FPR0;
+
+ flush_fp_to_thread(child);
+ if (fpidx < (PT_FPSCR - PT_FPR0))
+ memcpy(&child->thread.TS_FPR(fpidx), &data,
+ sizeof(long));
+ else
+ child->thread.fp_state.fpscr = data;
+ ret = 0;
+ }
+ break;
+ }
+
+ case PPC_PTRACE_GETHWDBGINFO: {
+ struct ppc_debug_info dbginfo;
+
+ ppc_gethwdinfo(&dbginfo);
+
+ if (copy_to_user(datavp, &dbginfo,
+ sizeof(struct ppc_debug_info)))
+ return -EFAULT;
+ return 0;
+ }
+
+ case PPC_PTRACE_SETHWDEBUG: {
+ struct ppc_hw_breakpoint bp_info;
+
+ if (copy_from_user(&bp_info, datavp,
+ sizeof(struct ppc_hw_breakpoint)))
+ return -EFAULT;
+ return ppc_set_hwdebug(child, &bp_info);
+ }
+
+ case PPC_PTRACE_DELHWDEBUG: {
+ ret = ppc_del_hwdebug(child, data);
+ break;
+ }
+
+ case PTRACE_GET_DEBUGREG:
+ ret = ptrace_get_debugreg(child, addr, datalp);
+ break;
+
+ case PTRACE_SET_DEBUGREG:
+ ret = ptrace_set_debugreg(child, addr, data);
+ break;
+
+#ifdef CONFIG_PPC64
+ case PTRACE_GETREGS64:
+#endif
+ case PTRACE_GETREGS: /* Get all pt_regs from the child. */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_GPR,
+ 0, sizeof(struct user_pt_regs),
+ datavp);
+
+#ifdef CONFIG_PPC64
+ case PTRACE_SETREGS64:
+#endif
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_GPR,
+ 0, sizeof(struct user_pt_regs),
+ datavp);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_FPR,
+ 0, sizeof(elf_fpregset_t),
+ datavp);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state (FPR0...31 + FPSCR) */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_FPR,
+ 0, sizeof(elf_fpregset_t),
+ datavp);
+
+#ifdef CONFIG_ALTIVEC
+ case PTRACE_GETVRREGS:
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_VMX,
+ 0, (33 * sizeof(vector128) +
+ sizeof(u32)),
+ datavp);
+
+ case PTRACE_SETVRREGS:
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_VMX,
+ 0, (33 * sizeof(vector128) +
+ sizeof(u32)),
+ datavp);
+#endif
+#ifdef CONFIG_VSX
+ case PTRACE_GETVSRREGS:
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_VSX,
+ 0, 32 * sizeof(double),
+ datavp);
+
+ case PTRACE_SETVSRREGS:
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_VSX,
+ 0, 32 * sizeof(double),
+ datavp);
+#endif
+#ifdef CONFIG_SPE
+ case PTRACE_GETEVRREGS:
+ /* Get the child spe register state. */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_SPE, 0, 35 * sizeof(u32),
+ datavp);
+
+ case PTRACE_SETEVRREGS:
+ /* Set the child spe register state. */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_SPE, 0, 35 * sizeof(u32),
+ datavp);
+#endif
+
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+ return ret;
+}
+
+#ifdef CONFIG_SECCOMP
+static int do_seccomp(struct pt_regs *regs)
+{
+ if (!test_thread_flag(TIF_SECCOMP))
+ return 0;
+
+ /*
+ * The ABI we present to seccomp tracers is that r3 contains
+ * the syscall return value and orig_gpr3 contains the first
+ * syscall parameter. This is different to the ptrace ABI where
+ * both r3 and orig_gpr3 contain the first syscall parameter.
+ */
+ regs->gpr[3] = -ENOSYS;
+
+ /*
+ * We use the __ version here because we have already checked
+ * TIF_SECCOMP. If this fails, there is nothing left to do, we
+ * have already loaded -ENOSYS into r3, or seccomp has put
+ * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
+ */
+ if (__secure_computing(NULL))
+ return -1;
+
+ /*
+ * The syscall was allowed by seccomp, restore the register
+ * state to what audit expects.
+ * Note that we use orig_gpr3, which means a seccomp tracer can
+ * modify the first syscall parameter (in orig_gpr3) and also
+ * allow the syscall to proceed.
+ */
+ regs->gpr[3] = regs->orig_gpr3;
+
+ return 0;
+}
+#else
+static inline int do_seccomp(struct pt_regs *regs) { return 0; }
+#endif /* CONFIG_SECCOMP */
+
+/**
+ * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
+ * @regs: the pt_regs of the task to trace (current)
+ *
+ * Performs various types of tracing on syscall entry. This includes seccomp,
+ * ptrace, syscall tracepoints and audit.
+ *
+ * The pt_regs are potentially visible to userspace via ptrace, so their
+ * contents is ABI.
+ *
+ * One or more of the tracers may modify the contents of pt_regs, in particular
+ * to modify arguments or even the syscall number itself.
+ *
+ * It's also possible that a tracer can choose to reject the system call. In
+ * that case this function will return an illegal syscall number, and will put
+ * an appropriate return value in regs->r3.
+ *
+ * Return: the (possibly changed) syscall number.
+ */
+long do_syscall_trace_enter(struct pt_regs *regs)
+{
+ u32 flags;
+
+ user_exit();
+
+ flags = READ_ONCE(current_thread_info()->flags) &
+ (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
+
+ if (flags) {
+ int rc = tracehook_report_syscall_entry(regs);
+
+ if (unlikely(flags & _TIF_SYSCALL_EMU)) {
+ /*
+ * A nonzero return code from
+ * tracehook_report_syscall_entry() tells us to prevent
+ * the syscall execution, but we are not going to
+ * execute it anyway.
+ *
+ * Returning -1 will skip the syscall execution. We want
+ * to avoid clobbering any registers, so we don't goto
+ * the skip label below.
+ */
+ return -1;
+ }
+
+ if (rc) {
+ /*
+ * The tracer decided to abort the syscall. Note that
+ * the tracer may also just change regs->gpr[0] to an
+ * invalid syscall number, that is handled below on the
+ * exit path.
+ */
+ goto skip;
+ }
+ }
+
+ /* Run seccomp after ptrace; allow it to set gpr[3]. */
+ if (do_seccomp(regs))
+ return -1;
+
+ /* Avoid trace and audit when syscall is invalid. */
+ if (regs->gpr[0] >= NR_syscalls)
+ goto skip;
+
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->gpr[0]);
+
+ if (!is_32bit_task())
+ audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
+ regs->gpr[5], regs->gpr[6]);
+ else
+ audit_syscall_entry(regs->gpr[0],
+ regs->gpr[3] & 0xffffffff,
+ regs->gpr[4] & 0xffffffff,
+ regs->gpr[5] & 0xffffffff,
+ regs->gpr[6] & 0xffffffff);
+
+ /* Return the possibly modified but valid syscall number */
+ return regs->gpr[0];
+
+skip:
+ /*
+ * If we are aborting explicitly, or if the syscall number is
+ * now invalid, set the return value to -ENOSYS.
+ */
+ regs->gpr[3] = -ENOSYS;
+ return -1;
+}
+
+void do_syscall_trace_leave(struct pt_regs *regs)
+{
+ int step;
+
+ audit_syscall_exit(regs);
+
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_exit(regs, regs->result);
+
+ step = test_thread_flag(TIF_SINGLESTEP);
+ if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, step);
+
+ user_enter();
+}
+
+void __init pt_regs_check(void);
+
+/*
+ * Dummy function, its purpose is to break the build if struct pt_regs and
+ * struct user_pt_regs don't match.
+ */
+void __init pt_regs_check(void)
+{
+ BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
+ offsetof(struct user_pt_regs, gpr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
+ offsetof(struct user_pt_regs, nip));
+ BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+ offsetof(struct user_pt_regs, msr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+ offsetof(struct user_pt_regs, msr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct user_pt_regs, orig_gpr3));
+ BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
+ offsetof(struct user_pt_regs, ctr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
+ offsetof(struct user_pt_regs, link));
+ BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
+ offsetof(struct user_pt_regs, xer));
+ BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
+ offsetof(struct user_pt_regs, ccr));
+#ifdef __powerpc64__
+ BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
+ offsetof(struct user_pt_regs, softe));
+#else
+ BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
+ offsetof(struct user_pt_regs, mq));
+#endif
+ BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
+ offsetof(struct user_pt_regs, trap));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
+ offsetof(struct user_pt_regs, dar));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
+ offsetof(struct user_pt_regs, dsisr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
+ offsetof(struct user_pt_regs, result));
+
+ BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
+
+ // Now check that the pt_regs offsets match the uapi #defines
+ #define CHECK_REG(_pt, _reg) \
+ BUILD_BUG_ON(_pt != (offsetof(struct user_pt_regs, _reg) / \
+ sizeof(unsigned long)));
+
+ CHECK_REG(PT_R0, gpr[0]);
+ CHECK_REG(PT_R1, gpr[1]);
+ CHECK_REG(PT_R2, gpr[2]);
+ CHECK_REG(PT_R3, gpr[3]);
+ CHECK_REG(PT_R4, gpr[4]);
+ CHECK_REG(PT_R5, gpr[5]);
+ CHECK_REG(PT_R6, gpr[6]);
+ CHECK_REG(PT_R7, gpr[7]);
+ CHECK_REG(PT_R8, gpr[8]);
+ CHECK_REG(PT_R9, gpr[9]);
+ CHECK_REG(PT_R10, gpr[10]);
+ CHECK_REG(PT_R11, gpr[11]);
+ CHECK_REG(PT_R12, gpr[12]);
+ CHECK_REG(PT_R13, gpr[13]);
+ CHECK_REG(PT_R14, gpr[14]);
+ CHECK_REG(PT_R15, gpr[15]);
+ CHECK_REG(PT_R16, gpr[16]);
+ CHECK_REG(PT_R17, gpr[17]);
+ CHECK_REG(PT_R18, gpr[18]);
+ CHECK_REG(PT_R19, gpr[19]);
+ CHECK_REG(PT_R20, gpr[20]);
+ CHECK_REG(PT_R21, gpr[21]);
+ CHECK_REG(PT_R22, gpr[22]);
+ CHECK_REG(PT_R23, gpr[23]);
+ CHECK_REG(PT_R24, gpr[24]);
+ CHECK_REG(PT_R25, gpr[25]);
+ CHECK_REG(PT_R26, gpr[26]);
+ CHECK_REG(PT_R27, gpr[27]);
+ CHECK_REG(PT_R28, gpr[28]);
+ CHECK_REG(PT_R29, gpr[29]);
+ CHECK_REG(PT_R30, gpr[30]);
+ CHECK_REG(PT_R31, gpr[31]);
+ CHECK_REG(PT_NIP, nip);
+ CHECK_REG(PT_MSR, msr);
+ CHECK_REG(PT_ORIG_R3, orig_gpr3);
+ CHECK_REG(PT_CTR, ctr);
+ CHECK_REG(PT_LNK, link);
+ CHECK_REG(PT_XER, xer);
+ CHECK_REG(PT_CCR, ccr);
+#ifdef CONFIG_PPC64
+ CHECK_REG(PT_SOFTE, softe);
+#else
+ CHECK_REG(PT_MQ, mq);
+#endif
+ CHECK_REG(PT_TRAP, trap);
+ CHECK_REG(PT_DAR, dar);
+ CHECK_REG(PT_DSISR, dsisr);
+ CHECK_REG(PT_RESULT, result);
+ #undef CHECK_REG
+
+ BUILD_BUG_ON(PT_REGS_COUNT != sizeof(struct user_pt_regs) / sizeof(unsigned long));
+
+ /*
+ * PT_DSCR isn't a real reg, but it's important that it doesn't overlap the
+ * real registers.
+ */
+ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long));
+}
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace/ptrace32.c
similarity index 95%
rename from arch/powerpc/kernel/ptrace32.c
rename to arch/powerpc/kernel/ptrace/ptrace32.c
index f37eb53..7589a96 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace/ptrace32.c
@@ -17,21 +17,10 @@
* this archive for more details.
*/
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/regset.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/signal.h>
#include <linux/compat.h>
-#include <linux/uaccess.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
#include <asm/switch_to.h>
/*
@@ -270,8 +259,8 @@
ret = put_user(child->thread.debug.dac1, (u32 __user *)data);
#else
dabr_fake = (
- (child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) |
- (child->thread.hw_brk.type & HW_BRK_TYPE_DABR));
+ (child->thread.hw_brk[0].address & (~HW_BRK_TYPE_DABR)) |
+ (child->thread.hw_brk[0].type & HW_BRK_TYPE_DABR));
ret = put_user(dabr_fake, (u32 __user *)data);
#endif
break;
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 487dcd8..2d33f34 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -159,12 +159,12 @@
return single_open(file, ppc_rtas_poweron_show, NULL);
}
-static const struct file_operations ppc_rtas_poweron_operations = {
- .open = poweron_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = ppc_rtas_poweron_write,
- .release = single_release,
+static const struct proc_ops ppc_rtas_poweron_proc_ops = {
+ .proc_open = poweron_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_poweron_write,
+ .proc_release = single_release,
};
static int progress_open(struct inode *inode, struct file *file)
@@ -172,12 +172,12 @@
return single_open(file, ppc_rtas_progress_show, NULL);
}
-static const struct file_operations ppc_rtas_progress_operations = {
- .open = progress_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = ppc_rtas_progress_write,
- .release = single_release,
+static const struct proc_ops ppc_rtas_progress_proc_ops = {
+ .proc_open = progress_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_progress_write,
+ .proc_release = single_release,
};
static int clock_open(struct inode *inode, struct file *file)
@@ -185,12 +185,12 @@
return single_open(file, ppc_rtas_clock_show, NULL);
}
-static const struct file_operations ppc_rtas_clock_operations = {
- .open = clock_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = ppc_rtas_clock_write,
- .release = single_release,
+static const struct proc_ops ppc_rtas_clock_proc_ops = {
+ .proc_open = clock_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_clock_write,
+ .proc_release = single_release,
};
static int tone_freq_open(struct inode *inode, struct file *file)
@@ -198,12 +198,12 @@
return single_open(file, ppc_rtas_tone_freq_show, NULL);
}
-static const struct file_operations ppc_rtas_tone_freq_operations = {
- .open = tone_freq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = ppc_rtas_tone_freq_write,
- .release = single_release,
+static const struct proc_ops ppc_rtas_tone_freq_proc_ops = {
+ .proc_open = tone_freq_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_tone_freq_write,
+ .proc_release = single_release,
};
static int tone_volume_open(struct inode *inode, struct file *file)
@@ -211,12 +211,12 @@
return single_open(file, ppc_rtas_tone_volume_show, NULL);
}
-static const struct file_operations ppc_rtas_tone_volume_operations = {
- .open = tone_volume_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = ppc_rtas_tone_volume_write,
- .release = single_release,
+static const struct proc_ops ppc_rtas_tone_volume_proc_ops = {
+ .proc_open = tone_volume_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_tone_volume_write,
+ .proc_release = single_release,
};
static int ppc_rtas_find_all_sensors(void);
@@ -238,17 +238,17 @@
return -ENODEV;
proc_create("powerpc/rtas/progress", 0644, NULL,
- &ppc_rtas_progress_operations);
+ &ppc_rtas_progress_proc_ops);
proc_create("powerpc/rtas/clock", 0644, NULL,
- &ppc_rtas_clock_operations);
+ &ppc_rtas_clock_proc_ops);
proc_create("powerpc/rtas/poweron", 0644, NULL,
- &ppc_rtas_poweron_operations);
+ &ppc_rtas_poweron_proc_ops);
proc_create_single("powerpc/rtas/sensors", 0444, NULL,
ppc_rtas_sensors_show);
proc_create("powerpc/rtas/frequency", 0644, NULL,
- &ppc_rtas_tone_freq_operations);
+ &ppc_rtas_tone_freq_proc_ops);
proc_create("powerpc/rtas/volume", 0644, NULL,
- &ppc_rtas_tone_volume_operations);
+ &ppc_rtas_tone_volume_proc_ops);
proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
ppc_rtas_rmo_buf_show);
return 0;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index c1e2e35..cccb32c 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -41,6 +41,7 @@
#include <asm/time.h>
#include <asm/mmu.h>
#include <asm/topology.h>
+#include <asm/paca.h>
/* This is here deliberately so it's only used in this file */
void enter_rtas(unsigned long);
@@ -896,6 +897,57 @@
return atomic_read(&data.error);
}
+
+/**
+ * rtas_call_reentrant() - Used for reentrant rtas calls
+ * @token: Token for desired reentrant RTAS call
+ * @nargs: Number of Input Parameters
+ * @nret: Number of Output Parameters
+ * @outputs: Array of outputs
+ * @...: Inputs for desired RTAS call
+ *
+ * According to LoPAR documentation, only "ibm,int-on", "ibm,int-off",
+ * "ibm,get-xive" and "ibm,set-xive" are currently reentrant.
+ * Reentrant calls need their own rtas_args buffer, so not using rtas.args, but
+ * PACA one instead.
+ *
+ * Return: -1 on error,
+ * First output value of RTAS call if (nret > 0),
+ * 0 otherwise,
+ */
+int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
+{
+ va_list list;
+ struct rtas_args *args;
+ unsigned long flags;
+ int i, ret = 0;
+
+ if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
+ return -1;
+
+ local_irq_save(flags);
+ preempt_disable();
+
+ /* We use the per-cpu (PACA) rtas args buffer */
+ args = local_paca->rtas_args_reentrant;
+
+ va_start(list, outputs);
+ va_rtas_call_unlocked(args, token, nargs, nret, list);
+ va_end(list);
+
+ if (nret > 1 && outputs)
+ for (i = 0; i < nret - 1; ++i)
+ outputs[i] = be32_to_cpu(args->rets[i + 1]);
+
+ if (nret > 0)
+ ret = be32_to_cpu(args->rets[0]);
+
+ local_irq_restore(flags);
+ preempt_enable();
+
+ return ret;
+}
+
#else /* CONFIG_PPC_PSERIES */
int rtas_ibm_suspend_me(u64 handle)
{
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 84f7947..a99179d 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -655,7 +655,7 @@
const char *filename;
const char *rtas_call_name;
int *status;
- const struct file_operations fops;
+ const struct proc_ops ops;
};
static const struct rtas_flash_file rtas_flash_files[] = {
@@ -663,36 +663,36 @@
.filename = "powerpc/rtas/" FIRMWARE_FLASH_NAME,
.rtas_call_name = "ibm,update-flash-64-and-reboot",
.status = &rtas_update_flash_data.status,
- .fops.read = rtas_flash_read_msg,
- .fops.write = rtas_flash_write,
- .fops.release = rtas_flash_release,
- .fops.llseek = default_llseek,
+ .ops.proc_read = rtas_flash_read_msg,
+ .ops.proc_write = rtas_flash_write,
+ .ops.proc_release = rtas_flash_release,
+ .ops.proc_lseek = default_llseek,
},
{
.filename = "powerpc/rtas/" FIRMWARE_UPDATE_NAME,
.rtas_call_name = "ibm,update-flash-64-and-reboot",
.status = &rtas_update_flash_data.status,
- .fops.read = rtas_flash_read_num,
- .fops.write = rtas_flash_write,
- .fops.release = rtas_flash_release,
- .fops.llseek = default_llseek,
+ .ops.proc_read = rtas_flash_read_num,
+ .ops.proc_write = rtas_flash_write,
+ .ops.proc_release = rtas_flash_release,
+ .ops.proc_lseek = default_llseek,
},
{
.filename = "powerpc/rtas/" VALIDATE_FLASH_NAME,
.rtas_call_name = "ibm,validate-flash-image",
.status = &rtas_validate_flash_data.status,
- .fops.read = validate_flash_read,
- .fops.write = validate_flash_write,
- .fops.release = validate_flash_release,
- .fops.llseek = default_llseek,
+ .ops.proc_read = validate_flash_read,
+ .ops.proc_write = validate_flash_write,
+ .ops.proc_release = validate_flash_release,
+ .ops.proc_lseek = default_llseek,
},
{
.filename = "powerpc/rtas/" MANAGE_FLASH_NAME,
.rtas_call_name = "ibm,manage-flash-image",
.status = &rtas_manage_flash_data.status,
- .fops.read = manage_flash_read,
- .fops.write = manage_flash_write,
- .fops.llseek = default_llseek,
+ .ops.proc_read = manage_flash_read,
+ .ops.proc_write = manage_flash_write,
+ .ops.proc_lseek = default_llseek,
}
};
@@ -723,7 +723,7 @@
const struct rtas_flash_file *f = &rtas_flash_files[i];
int token;
- if (!proc_create(f->filename, 0600, NULL, &f->fops))
+ if (!proc_create(f->filename, 0600, NULL, &f->ops))
goto enomem;
/*
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index ae5e43e..781c186 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -13,9 +13,9 @@
#include <linux/pci.h>
#include <linux/string.h>
#include <linux/init.h>
+#include <linux/pgtable.h>
#include <asm/io.h>
-#include <asm/pgtable.h>
#include <asm/irq.h>
#include <asm/prom.h>
#include <asm/machdep.h>
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 8d02e04..8561dfb 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -273,37 +273,15 @@
}
}
-#ifdef CONFIG_PPC_PSERIES
-static void handle_prrn_event(s32 scope)
-{
- /*
- * For PRRN, we must pass the negative of the scope value in
- * the RTAS event.
- */
- pseries_devicetree_update(-scope);
- numa_update_cpu_topology(false);
-}
-
static void handle_rtas_event(const struct rtas_error_log *log)
{
- if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled())
+ if (!machine_is(pseries))
return;
- /* For PRRN Events the extended log length is used to denote
- * the scope for calling rtas update-nodes.
- */
- handle_prrn_event(rtas_error_extended_log_length(log));
+ if (rtas_error_type(log) == RTAS_TYPE_PRRN)
+ pr_info_ratelimited("Platform resource reassignment ignored.\n");
}
-#else
-
-static void handle_rtas_event(const struct rtas_error_log *log)
-{
- return;
-}
-
-#endif
-
static int rtas_log_open(struct inode * inode, struct file * file)
{
return 0;
@@ -385,12 +363,12 @@
return 0;
}
-static const struct file_operations proc_rtas_log_operations = {
- .read = rtas_log_read,
- .poll = rtas_log_poll,
- .open = rtas_log_open,
- .release = rtas_log_release,
- .llseek = noop_llseek,
+static const struct proc_ops rtas_log_proc_ops = {
+ .proc_read = rtas_log_read,
+ .proc_poll = rtas_log_poll,
+ .proc_open = rtas_log_open,
+ .proc_release = rtas_log_release,
+ .proc_lseek = noop_llseek,
};
static int enable_surveillance(int timeout)
@@ -572,7 +550,7 @@
return -ENODEV;
entry = proc_create("powerpc/rtas/error_log", 0400, NULL,
- &proc_rtas_log_operations);
+ &rtas_log_proc_ops);
if (!entry)
printk(KERN_ERR "Failed to create error_log proc entry\n");
diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c
new file mode 100644
index 0000000..f9af305
--- /dev/null
+++ b/arch/powerpc/kernel/secure_boot.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ */
+#include <linux/types.h>
+#include <linux/of.h>
+#include <asm/secure_boot.h>
+
+static struct device_node *get_ppc_fw_sb_node(void)
+{
+ static const struct of_device_id ids[] = {
+ { .compatible = "ibm,secureboot", },
+ { .compatible = "ibm,secureboot-v1", },
+ { .compatible = "ibm,secureboot-v2", },
+ {},
+ };
+
+ return of_find_matching_node(NULL, ids);
+}
+
+bool is_ppc_secureboot_enabled(void)
+{
+ struct device_node *node;
+ bool enabled = false;
+ u32 secureboot;
+
+ node = get_ppc_fw_sb_node();
+ enabled = of_property_read_bool(node, "os-secureboot-enforcing");
+ of_node_put(node);
+
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot))
+ enabled = (secureboot > 1);
+
+out:
+ pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled");
+
+ return enabled;
+}
+
+bool is_ppc_trustedboot_enabled(void)
+{
+ struct device_node *node;
+ bool enabled = false;
+ u32 trustedboot;
+
+ node = get_ppc_fw_sb_node();
+ enabled = of_property_read_bool(node, "trusted-enabled");
+ of_node_put(node);
+
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot))
+ enabled = (trustedboot > 0);
+
+out:
+ pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled");
+
+ return enabled;
+}
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index 1740a66..3f510c9 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -7,6 +7,8 @@
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
#include <linux/seq_buf.h>
#include <asm/asm-prototypes.h>
@@ -14,17 +16,18 @@
#include <asm/debugfs.h>
#include <asm/security_features.h>
#include <asm/setup.h>
+#include <asm/inst.h>
u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
-enum count_cache_flush_type {
- COUNT_CACHE_FLUSH_NONE = 0x1,
- COUNT_CACHE_FLUSH_SW = 0x2,
- COUNT_CACHE_FLUSH_HW = 0x4,
+enum branch_cache_flush_type {
+ BRANCH_CACHE_FLUSH_NONE = 0x1,
+ BRANCH_CACHE_FLUSH_SW = 0x2,
+ BRANCH_CACHE_FLUSH_HW = 0x4,
};
-static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
-static bool link_stack_flush_enabled;
+static enum branch_cache_flush_type count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
+static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
bool barrier_nospec_enabled;
static bool no_nospec;
@@ -95,13 +98,14 @@
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_barrier_nospec,
- barrier_nospec_get, barrier_nospec_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_barrier_nospec, barrier_nospec_get,
+ barrier_nospec_set, "%llu\n");
static __init int barrier_nospec_debugfs_init(void)
{
- debugfs_create_file("barrier_nospec", 0600, powerpc_debugfs_root, NULL,
- &fops_barrier_nospec);
+ debugfs_create_file_unsafe("barrier_nospec", 0600,
+ powerpc_debugfs_root, NULL,
+ &fops_barrier_nospec);
return 0;
}
device_initcall(barrier_nospec_debugfs_init);
@@ -215,24 +219,25 @@
if (ccd)
seq_buf_printf(&s, "Indirect branch cache disabled");
- if (link_stack_flush_enabled)
- seq_buf_printf(&s, ", Software link stack flush");
-
- } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+ } else if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
seq_buf_printf(&s, "Mitigation: Software count cache flush");
- if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW)
seq_buf_printf(&s, " (hardware accelerated)");
- if (link_stack_flush_enabled)
- seq_buf_printf(&s, ", Software link stack flush");
-
} else if (btb_flush_enabled) {
seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
} else {
seq_buf_printf(&s, "Vulnerable");
}
+ if (bcs || ccd || count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ seq_buf_printf(&s, ", Software link stack flush");
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_HW)
+ seq_buf_printf(&s, " (hardware accelerated)");
+ }
+
seq_buf_printf(&s, "\n");
return s.len;
@@ -256,6 +261,11 @@
early_param("no_stf_barrier", handle_no_stf_barrier);
+enum stf_barrier_type stf_barrier_type_get(void)
+{
+ return stf_enabled_flush_types;
+}
+
/* This is the generic flag used by other architectures */
static int __init handle_ssbd(char *p)
{
@@ -352,6 +362,40 @@
return sprintf(buf, "Vulnerable\n");
}
+static int ssb_prctl_get(struct task_struct *task)
+{
+ if (stf_enabled_flush_types == STF_BARRIER_NONE)
+ /*
+ * We don't have an explicit signal from firmware that we're
+ * vulnerable or not, we only have certain CPU revisions that
+ * are known to be vulnerable.
+ *
+ * We assume that if we're on another CPU, where the barrier is
+ * NONE, then we are not vulnerable.
+ */
+ return PR_SPEC_NOT_AFFECTED;
+ else
+ /*
+ * If we do have a barrier type then we are vulnerable. The
+ * barrier is not a global or per-process mitigation, so the
+ * only value we can report here is PR_SPEC_ENABLE, which
+ * appears as "vulnerable" in /proc.
+ */
+ return PR_SPEC_ENABLE;
+
+ return -EINVAL;
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_get(task);
+ default:
+ return -ENODEV;
+ }
+}
+
#ifdef CONFIG_DEBUG_FS
static int stf_barrier_set(void *data, u64 val)
{
@@ -377,68 +421,105 @@
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set,
+ "%llu\n");
static __init int stf_barrier_debugfs_init(void)
{
- debugfs_create_file("stf_barrier", 0600, powerpc_debugfs_root, NULL, &fops_stf_barrier);
+ debugfs_create_file_unsafe("stf_barrier", 0600, powerpc_debugfs_root,
+ NULL, &fops_stf_barrier);
return 0;
}
device_initcall(stf_barrier_debugfs_init);
#endif /* CONFIG_DEBUG_FS */
-static void no_count_cache_flush(void)
+static void update_branch_cache_flush(void)
{
- count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
- pr_info("count-cache-flush: software flush disabled.\n");
+ u32 *site;
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ site = &patch__call_kvm_flush_link_stack;
+ // This controls the branch from guest_exit_cont to kvm_flush_link_stack
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+ } else {
+ // Could use HW flush, but that could also flush count cache
+ patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+ }
+#endif
+
+ // Patch out the bcctr first, then nop the rest
+ site = &patch__call_flush_branch_caches3;
+ patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+ site = &patch__call_flush_branch_caches2;
+ patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+ site = &patch__call_flush_branch_caches1;
+ patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+
+ // This controls the branch from _switch to flush_branch_caches
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ // Nothing to be done
+
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ // Patch in the bcctr last
+ site = &patch__call_flush_branch_caches1;
+ patch_instruction_site(site, ppc_inst(0x39207fff)); // li r9,0x7fff
+ site = &patch__call_flush_branch_caches2;
+ patch_instruction_site(site, ppc_inst(0x7d2903a6)); // mtctr r9
+ site = &patch__call_flush_branch_caches3;
+ patch_instruction_site(site, ppc_inst(PPC_INST_BCCTR_FLUSH));
+
+ } else {
+ patch_branch_site(site, (u64)&flush_branch_caches, BRANCH_SET_LINK);
+
+ // If we just need to flush the link stack, early return
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(&patch__flush_link_stack_return,
+ ppc_inst(PPC_INST_BLR));
+
+ // If we have flush instruction, early return
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ patch_instruction_site(&patch__flush_count_cache_return,
+ ppc_inst(PPC_INST_BLR));
+ }
+ }
}
-static void toggle_count_cache_flush(bool enable)
+static void toggle_branch_cache_flush(bool enable)
{
- if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) &&
- !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK))
- enable = false;
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+ if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
- if (!enable) {
- patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP);
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP);
-#endif
- pr_info("link-stack-flush: software flush disabled.\n");
- link_stack_flush_enabled = false;
- no_count_cache_flush();
- return;
+ pr_info("count-cache-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("count-cache-flush: hardware flush enabled.\n");
+ } else {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("count-cache-flush: software flush enabled.\n");
+ }
}
- // This enables the branch from _switch to flush_count_cache
- patch_branch_site(&patch__call_flush_count_cache,
- (u64)&flush_count_cache, BRANCH_SET_LINK);
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- // This enables the branch from guest_exit_cont to kvm_flush_link_stack
- patch_branch_site(&patch__call_kvm_flush_link_stack,
- (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
-#endif
-
- pr_info("link-stack-flush: software flush enabled.\n");
- link_stack_flush_enabled = true;
-
- // If we just need to flush the link stack, patch an early return
- if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
- patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR);
- no_count_cache_flush();
- return;
+ pr_info("link-stack-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST)) {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("link-stack-flush: hardware flush enabled.\n");
+ } else {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("link-stack-flush: software flush enabled.\n");
+ }
}
- if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
- count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
- pr_info("count-cache-flush: full software flush sequence enabled.\n");
- return;
- }
-
- patch_instruction_site(&patch__flush_count_cache_return, PPC_INST_BLR);
- count_cache_flush_type = COUNT_CACHE_FLUSH_HW;
- pr_info("count-cache-flush: hardware assisted flush sequence enabled\n");
+ update_branch_cache_flush();
}
void setup_count_cache_flush(void)
@@ -462,7 +543,7 @@
security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
- toggle_count_cache_flush(enable);
+ toggle_branch_cache_flush(enable);
}
#ifdef CONFIG_DEBUG_FS
@@ -477,14 +558,14 @@
else
return -EINVAL;
- toggle_count_cache_flush(enable);
+ toggle_branch_cache_flush(enable);
return 0;
}
static int count_cache_flush_get(void *data, u64 *val)
{
- if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE)
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE)
*val = 0;
else
*val = 1;
@@ -492,13 +573,14 @@
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
- count_cache_flush_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
+ count_cache_flush_set, "%llu\n");
static __init int count_cache_flush_debugfs_init(void)
{
- debugfs_create_file("count_cache_flush", 0600, powerpc_debugfs_root,
- NULL, &fops_count_cache_flush);
+ debugfs_create_file_unsafe("count_cache_flush", 0600,
+ powerpc_debugfs_root, NULL,
+ &fops_count_cache_flush);
return 0;
}
device_initcall(count_cache_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/secvar-ops.c b/arch/powerpc/kernel/secvar-ops.c
new file mode 100644
index 0000000..6a29777
--- /dev/null
+++ b/arch/powerpc/kernel/secvar-ops.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ *
+ * This file initializes secvar operations for PowerPC Secureboot
+ */
+
+#include <linux/cache.h>
+#include <asm/secvar.h>
+
+const struct secvar_operations *secvar_ops __ro_after_init;
+
+void set_secvar_ops(const struct secvar_operations *ops)
+{
+ secvar_ops = ops;
+}
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
new file mode 100644
index 0000000..a0a78ab
--- /dev/null
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 IBM Corporation <nayna@linux.ibm.com>
+ *
+ * This code exposes secure variables to user via sysfs
+ */
+
+#define pr_fmt(fmt) "secvar-sysfs: "fmt
+
+#include <linux/slab.h>
+#include <linux/compat.h>
+#include <linux/string.h>
+#include <linux/of.h>
+#include <asm/secvar.h>
+
+#define NAME_MAX_SIZE 1024
+
+static struct kobject *secvar_kobj;
+static struct kset *secvar_kset;
+
+static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ ssize_t rc = 0;
+ struct device_node *node;
+ const char *format;
+
+ node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
+ if (!of_device_is_available(node))
+ return -ENODEV;
+
+ rc = of_property_read_string(node, "format", &format);
+ if (rc)
+ return rc;
+
+ rc = sprintf(buf, "%s\n", format);
+
+ of_node_put(node);
+
+ return rc;
+}
+
+
+static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ uint64_t dsize;
+ int rc;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
+ if (rc) {
+ pr_err("Error retrieving %s variable size %d\n", kobj->name,
+ rc);
+ return rc;
+ }
+
+ return sprintf(buf, "%llu\n", dsize);
+}
+
+static ssize_t data_read(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf, loff_t off,
+ size_t count)
+{
+ uint64_t dsize;
+ char *data;
+ int rc;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
+ if (rc) {
+ pr_err("Error getting %s variable size %d\n", kobj->name, rc);
+ return rc;
+ }
+ pr_debug("dsize is %llu\n", dsize);
+
+ data = kzalloc(dsize, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, data, &dsize);
+ if (rc) {
+ pr_err("Error getting %s variable %d\n", kobj->name, rc);
+ goto data_fail;
+ }
+
+ rc = memory_read_from_buffer(buf, count, &off, data, dsize);
+
+data_fail:
+ kfree(data);
+ return rc;
+}
+
+static ssize_t update_write(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf, loff_t off,
+ size_t count)
+{
+ int rc;
+
+ pr_debug("count is %ld\n", count);
+ rc = secvar_ops->set(kobj->name, strlen(kobj->name) + 1, buf, count);
+ if (rc) {
+ pr_err("Error setting the %s variable %d\n", kobj->name, rc);
+ return rc;
+ }
+
+ return count;
+}
+
+static struct kobj_attribute format_attr = __ATTR_RO(format);
+
+static struct kobj_attribute size_attr = __ATTR_RO(size);
+
+static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0);
+
+static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0);
+
+static struct bin_attribute *secvar_bin_attrs[] = {
+ &data_attr,
+ &update_attr,
+ NULL,
+};
+
+static struct attribute *secvar_attrs[] = {
+ &size_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group secvar_attr_group = {
+ .attrs = secvar_attrs,
+ .bin_attrs = secvar_bin_attrs,
+};
+__ATTRIBUTE_GROUPS(secvar_attr);
+
+static struct kobj_type secvar_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = secvar_attr_groups,
+};
+
+static int update_kobj_size(void)
+{
+
+ struct device_node *node;
+ u64 varsize;
+ int rc = 0;
+
+ node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
+ if (!of_device_is_available(node)) {
+ rc = -ENODEV;
+ goto out;
+ }
+
+ rc = of_property_read_u64(node, "max-var-size", &varsize);
+ if (rc)
+ goto out;
+
+ data_attr.size = varsize;
+ update_attr.size = varsize;
+
+out:
+ of_node_put(node);
+
+ return rc;
+}
+
+static int secvar_sysfs_load(void)
+{
+ char *name;
+ uint64_t namesize = 0;
+ struct kobject *kobj;
+ int rc;
+
+ name = kzalloc(NAME_MAX_SIZE, GFP_KERNEL);
+ if (!name)
+ return -ENOMEM;
+
+ do {
+ rc = secvar_ops->get_next(name, &namesize, NAME_MAX_SIZE);
+ if (rc) {
+ if (rc != -ENOENT)
+ pr_err("error getting secvar from firmware %d\n",
+ rc);
+ break;
+ }
+
+ kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
+ if (!kobj) {
+ rc = -ENOMEM;
+ break;
+ }
+
+ kobject_init(kobj, &secvar_ktype);
+
+ rc = kobject_add(kobj, &secvar_kset->kobj, "%s", name);
+ if (rc) {
+ pr_warn("kobject_add error %d for attribute: %s\n", rc,
+ name);
+ kobject_put(kobj);
+ kobj = NULL;
+ }
+
+ if (kobj)
+ kobject_uevent(kobj, KOBJ_ADD);
+
+ } while (!rc);
+
+ kfree(name);
+ return rc;
+}
+
+static int secvar_sysfs_init(void)
+{
+ int rc;
+
+ if (!secvar_ops) {
+ pr_warn("secvar: failed to retrieve secvar operations.\n");
+ return -ENODEV;
+ }
+
+ secvar_kobj = kobject_create_and_add("secvar", firmware_kobj);
+ if (!secvar_kobj) {
+ pr_err("secvar: Failed to create firmware kobj\n");
+ return -ENOMEM;
+ }
+
+ rc = sysfs_create_file(secvar_kobj, &format_attr.attr);
+ if (rc) {
+ kobject_put(secvar_kobj);
+ return -ENOMEM;
+ }
+
+ secvar_kset = kset_create_and_add("vars", NULL, secvar_kobj);
+ if (!secvar_kset) {
+ pr_err("secvar: sysfs kobject registration failed.\n");
+ kobject_put(secvar_kobj);
+ return -ENOMEM;
+ }
+
+ rc = update_kobj_size();
+ if (rc) {
+ pr_err("Cannot read the size of the attribute\n");
+ return rc;
+ }
+
+ secvar_sysfs_load();
+
+ return 0;
+}
+
+late_initcall(secvar_sysfs_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index f281d01..da8c71f 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -31,13 +31,13 @@
#include <linux/memblock.h>
#include <linux/of_platform.h>
#include <linux/hugetlb.h>
+#include <linux/pgtable.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>
@@ -306,15 +306,12 @@
}
} 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 */
+ case 0x0080: /* POWER10 bit 12 gives SMT8/4 */
maj = (pvr >> 8) & 0x0F;
min = pvr & 0xFF;
break;
@@ -715,8 +712,28 @@
.priority = INT_MIN /* may not return; must be done last */
};
+/*
+ * Dump out kernel offset information on panic.
+ */
+static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
+ void *p)
+{
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+ kaslr_offset(), KERNELBASE);
+
+ return 0;
+}
+
+static struct notifier_block kernel_offset_notifier = {
+ .notifier_call = dump_kernel_offset
+};
+
void __init setup_panic(void)
{
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0)
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &kernel_offset_notifier);
+
/* PPC64 always does a hard irq disable in its panic handler */
if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
return;
@@ -767,8 +784,7 @@
static int powerpc_debugfs_init(void)
{
powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL);
-
- return powerpc_debugfs_root == NULL;
+ return 0;
}
arch_initcall(powerpc_debugfs_init);
#endif
@@ -911,6 +927,9 @@
/* Reserve large chunks of memory for use by CMA for KVM. */
kvm_cma_reserve();
+ /* Reserve large chunks of memory for us by CMA for hugetlb */
+ gigantic_hugetlb_cma_reserve();
+
klp_init_thread_info(&init_task);
init_mm.start_code = (unsigned long)_stext;
@@ -929,9 +948,6 @@
early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
- if (IS_ENABLED(CONFIG_DUMMY_CONSOLE))
- conswitchp = &dummy_con;
-
if (ppc_md.setup_arch)
ppc_md.setup_arch();
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index c82577c..2dd0d9c 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -35,7 +35,7 @@
static inline void exc_lvl_early_init(void) { };
#endif
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK)
void emergency_stack_init(void);
#else
static inline void emergency_stack_init(void) { };
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index a7541ed..e7f2eb7 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -19,11 +19,11 @@
#include <linux/memblock.h>
#include <linux/export.h>
#include <linux/nvram.h>
+#include <linux/pgtable.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/processor.h>
-#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/smp.h>
#include <asm/elf.h>
@@ -44,6 +44,7 @@
#include <asm/asm-prototypes.h>
#include <asm/kdump.h>
#include <asm/feature-fixups.h>
+#include <asm/early_ioremap.h>
#include "setup.h"
@@ -57,7 +58,6 @@
int smp_hw_index[NR_CPUS];
EXPORT_SYMBOL(smp_hw_index);
-unsigned long ISA_DMA_THRESHOLD;
unsigned int DMA_MODE_READ;
unsigned int DMA_MODE_WRITE;
@@ -74,18 +74,20 @@
*/
notrace void __init machine_init(u64 dt_ptr)
{
- unsigned int *addr = (unsigned int *)patch_site_addr(&patch__memset_nocache);
- unsigned long insn;
+ struct ppc_inst *addr = (struct ppc_inst *)patch_site_addr(&patch__memset_nocache);
+ struct ppc_inst insn;
/* Configure static keys first, now that we're relocated. */
setup_feature_keys();
+ early_ioremap_init();
+
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
- patch_instruction_site(&patch__memcpy_nocache, PPC_INST_NOP);
+ patch_instruction_site(&patch__memcpy_nocache, ppc_inst(PPC_INST_NOP));
- insn = create_cond_branch(addr, branch_target(addr), 0x820000);
+ create_cond_branch(&insn, addr, branch_target(addr), 0x820000);
patch_instruction(addr, insn); /* replace b by bne cr0 */
/* Do some early initialization based on the flat device tree */
@@ -137,7 +139,7 @@
static void *__init alloc_stack(void)
{
- void *ptr = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
+ void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
if (!ptr)
panic("cannot allocate %d bytes for stack at %pS\n",
@@ -150,6 +152,9 @@
{
unsigned int i;
+ if (IS_ENABLED(CONFIG_VMAP_STACK))
+ return;
+
/* interrupt stacks must be in lowmem, we get that for free on ppc32
* as the memblock is limited to lowmem by default */
for_each_possible_cpu(i) {
@@ -158,6 +163,18 @@
}
}
+#ifdef CONFIG_VMAP_STACK
+void *emergency_ctx[NR_CPUS] __ro_after_init = {[0] = &init_stack};
+
+void __init emergency_stack_init(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ emergency_ctx[i] = alloc_stack();
+}
+#endif
+
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
void __init exc_lvl_early_init(void)
{
@@ -206,6 +223,6 @@
dcache_bsize = cur_cpu_spec->dcache_bsize;
icache_bsize = cur_cpu_spec->icache_bsize;
ucache_bsize = 0;
- if (IS_ENABLED(CONFIG_PPC_BOOK3S_601) || IS_ENABLED(CONFIG_E200))
+ if (IS_ENABLED(CONFIG_E200))
ucache_bsize = icache_bsize = dcache_bsize;
}
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5bc7e75..3f8426b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -30,13 +30,13 @@
#include <linux/lockdep.h>
#include <linux/memory.h>
#include <linux/nmi.h>
+#include <linux/pgtable.h>
#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/prom.h>
#include <asm/processor.h>
-#include <asm/pgtable.h>
#include <asm/smp.h>
#include <asm/elf.h>
#include <asm/machdep.h>
@@ -65,15 +65,11 @@
#include <asm/hw_irq.h>
#include <asm/feature-fixups.h>
#include <asm/kup.h>
+#include <asm/early_ioremap.h>
+#include <asm/pgalloc.h>
#include "setup.h"
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
int spinning_secondaries;
u64 ppc64_pft_size;
@@ -201,7 +197,10 @@
/* Under a PAPR hypervisor, we need hypercalls */
if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
/* Enable AIL if possible */
- pseries_enable_reloc_on_exc();
+ if (!pseries_enable_reloc_on_exc()) {
+ init_task.thread.fscr &= ~FSCR_SCV;
+ cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+ }
/*
* Tell the hypervisor that we want our exceptions to
@@ -232,10 +231,23 @@
* If we are not in hypervisor mode the job is done once for
* the whole partition in configure_exceptions().
*/
- if (cpu_has_feature(CPU_FTR_HVMODE) &&
- cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
unsigned long lpcr = mfspr(SPRN_LPCR);
- mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
+ unsigned long new_lpcr = lpcr;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ /* P10 DD1 does not have HAIL */
+ if (pvr_version_is(PVR_POWER10) &&
+ (mfspr(SPRN_PVR) & 0xf00) == 0x100)
+ new_lpcr |= LPCR_AIL_3;
+ else
+ new_lpcr |= LPCR_HAIL;
+ } else if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ new_lpcr |= LPCR_AIL_3;
+ }
+
+ if (new_lpcr != lpcr)
+ mtspr(SPRN_LPCR, new_lpcr);
}
/*
@@ -323,7 +335,7 @@
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
- DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
+ udbg_printf(" -> %s(), dt_ptr: 0x%lx\n", __func__, dt_ptr);
/*
* Do early initialization using the flattened device
@@ -359,6 +371,8 @@
/* Initialize the hash table or TLB handling */
early_init_mmu();
+ early_ioremap_setup();
+
/*
* After firmware and early platform setup code has set things up,
* we note the SPR values for configurable control/performance
@@ -380,11 +394,11 @@
*/
this_cpu_enable_ftrace();
- DBG(" <- early_setup()\n");
+ udbg_printf(" <- %s()\n", __func__);
#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
/*
- * This needs to be done *last* (after the above DBG() even)
+ * This needs to be done *last* (after the above udbg_printf() even)
*
* Right after we return from this function, we turn on the MMU
* which means the real-mode access trick that btext does will
@@ -454,8 +468,6 @@
if (!use_spinloop())
return;
- DBG(" -> smp_release_cpus()\n");
-
/* All secondary cpus are spinning on a common spinloop, release them
* all now so they can start to spin on their individual paca
* spinloops. For non SMP kernels, the secondary cpus never get out
@@ -474,9 +486,7 @@
break;
udelay(1);
}
- DBG("spinning_secondaries = %d\n", spinning_secondaries);
-
- DBG(" <- smp_release_cpus()\n");
+ pr_debug("spinning_secondaries = %d\n", spinning_secondaries);
}
#endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */
@@ -571,8 +581,6 @@
struct device_node *cpu = NULL, *l2, *l3 = NULL;
u32 pvr;
- DBG(" -> initialize_cache_info()\n");
-
/*
* All shipping POWER8 machines have a firmware bug that
* puts incorrect information in the device-tree. This will
@@ -596,10 +604,10 @@
*/
if (cpu) {
if (!parse_cache_info(cpu, false, &ppc64_caches.l1d))
- DBG("Argh, can't find dcache properties !\n");
+ pr_warn("Argh, can't find dcache properties !\n");
if (!parse_cache_info(cpu, true, &ppc64_caches.l1i))
- DBG("Argh, can't find icache properties !\n");
+ pr_warn("Argh, can't find icache properties !\n");
/*
* Try to find the L2 and L3 if any. Assume they are
@@ -624,8 +632,6 @@
cur_cpu_spec->dcache_bsize = dcache_bsize;
cur_cpu_spec->icache_bsize = icache_bsize;
-
- DBG(" <- initialize_cache_info()\n");
}
/*
@@ -664,7 +670,7 @@
BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
- ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE,
+ ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN,
MEMBLOCK_LOW_LIMIT, limit,
early_cpu_to_node(cpu));
if (!ptr)
@@ -722,7 +728,7 @@
*/
void __init emergency_stack_init(void)
{
- u64 limit;
+ u64 limit, mce_limit;
unsigned int i;
/*
@@ -739,7 +745,16 @@
* initialized in kernel/irq.c. These are initialized here in order
* to have emergency stacks available as early as possible.
*/
- limit = min(ppc64_bolted_size(), ppc64_rma_size);
+ limit = mce_limit = min(ppc64_bolted_size(), ppc64_rma_size);
+
+ /*
+ * Machine check on pseries calls rtas, but can't use the static
+ * rtas_args due to a machine check hitting while the lock is held.
+ * rtas args have to be under 4GB, so the machine check stack is
+ * limited to 4GB so args can be put on stack.
+ */
+ if (firmware_has_feature(FW_FEATURE_LPAR) && mce_limit > SZ_4G)
+ mce_limit = SZ_4G;
for_each_possible_cpu(i) {
paca_ptrs[i]->emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
@@ -749,23 +764,52 @@
paca_ptrs[i]->nmi_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
- paca_ptrs[i]->mc_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
+ paca_ptrs[i]->mc_emergency_sp = alloc_stack(mce_limit, i) + THREAD_SIZE;
#endif
}
}
#ifdef CONFIG_SMP
-#define PCPU_DYN_SIZE ()
-
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
+ size_t align)
{
- return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
- MEMBLOCK_ALLOC_ACCESSIBLE,
- early_cpu_to_node(cpu));
+ const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ int node = early_cpu_to_node(cpu);
+ void *ptr;
+ if (!node_online(node) || !NODE_DATA(node)) {
+ ptr = memblock_alloc_from(size, align, goal);
+ pr_info("cpu %d has no node %d or node-local memory\n",
+ cpu, node);
+ pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+ cpu, size, __pa(ptr));
+ } else {
+ ptr = memblock_alloc_try_nid(size, align, goal,
+ MEMBLOCK_ALLOC_ACCESSIBLE, node);
+ pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
+ "%016lx\n", cpu, size, node, __pa(ptr));
+ }
+ return ptr;
+#else
+ return memblock_alloc_from(size, align, goal);
+#endif
}
-static void __init pcpu_fc_free(void *ptr, size_t size)
+static void __init pcpu_free_bootmem(void *ptr, size_t size)
{
memblock_free(__pa(ptr), size);
}
@@ -781,13 +825,58 @@
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
+static void __init pcpu_populate_pte(unsigned long addr)
+{
+ pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d)) {
+ pud_t *new;
+
+ new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ p4d_populate(&init_mm, p4d, new);
+ }
+
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud)) {
+ pmd_t *new;
+
+ new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ pud_populate(&init_mm, pud, new);
+ }
+
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd)) {
+ pte_t *new;
+
+ new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+ if (!new)
+ goto err_alloc;
+ pmd_populate_kernel(&init_mm, pmd, new);
+ }
+
+ return;
+
+err_alloc:
+ panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+}
+
+
void __init setup_per_cpu_areas(void)
{
const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
size_t atom_size;
unsigned long delta;
unsigned int cpu;
- int rc;
+ int rc = -EINVAL;
/*
* Linear mapping is one of 4K, 1M and 16M. For 4K, no need
@@ -799,8 +888,18 @@
else
atom_size = 1 << 20;
- rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
- pcpu_fc_alloc, pcpu_fc_free);
+ if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+ rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+ pcpu_alloc_bootmem, pcpu_free_bootmem);
+ if (rc)
+ pr_warn("PERCPU: %s allocator failed (%d), "
+ "falling back to page size\n",
+ pcpu_fc_names[pcpu_chosen_fc], rc);
+ }
+
+ if (rc < 0)
+ rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem,
+ pcpu_populate_pte);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index d215f95..d2c356f 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -18,12 +18,153 @@
#include <linux/syscalls.h>
#include <asm/hw_breakpoint.h>
#include <linux/uaccess.h>
+#include <asm/switch_to.h>
#include <asm/unistd.h>
#include <asm/debug.h>
#include <asm/tm.h>
#include "signal.h"
+#ifdef CONFIG_VSX
+unsigned long copy_fpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ buf[i] = task->thread.TS_FPR(i);
+ buf[i] = task->thread.fp_state.fpscr;
+ return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_fpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ task->thread.TS_FPR(i) = buf[i];
+ task->thread.fp_state.fpscr = buf[i];
+
+ return 0;
+}
+
+unsigned long copy_vsx_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < ELF_NVSRHALFREG; i++)
+ buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+ return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_vsx_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < ELF_NVSRHALFREG ; i++)
+ task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ return 0;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+unsigned long copy_ckfpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ buf[i] = task->thread.TS_CKFPR(i);
+ buf[i] = task->thread.ckfp_state.fpscr;
+ return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_ckfpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ task->thread.TS_CKFPR(i) = buf[i];
+ task->thread.ckfp_state.fpscr = buf[i];
+
+ return 0;
+}
+
+unsigned long copy_ckvsx_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < ELF_NVSRHALFREG; i++)
+ buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+ return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_ckvsx_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < ELF_NVSRHALFREG ; i++)
+ task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ return 0;
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#else
+inline unsigned long copy_fpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ return __copy_to_user(to, task->thread.fp_state.fpr,
+ ELF_NFPREG * sizeof(double));
+}
+
+inline unsigned long copy_fpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ return __copy_from_user(task->thread.fp_state.fpr, from,
+ ELF_NFPREG * sizeof(double));
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+inline unsigned long copy_ckfpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ return __copy_to_user(to, task->thread.ckfp_state.fpr,
+ ELF_NFPREG * sizeof(double));
+}
+
+inline unsigned long copy_ckfpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ return __copy_from_user(task->thread.ckfp_state.fpr, from,
+ ELF_NFPREG * sizeof(double));
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#endif
+
/* Log an error when sending an unhandled signal to a process. Controlled
* through debug.exception-trace sysctl.
*/
@@ -57,12 +198,21 @@
int restart = 1;
/* syscall ? */
- if (TRAP(regs) != 0x0C00)
+ if (!trap_is_syscall(regs))
+ return;
+
+ if (trap_norestart(regs))
return;
/* error signalled ? */
- if (!(regs->ccr & 0x10000000))
+ if (trap_is_scv(regs)) {
+ /* 32-bit compat mode sign extend? */
+ if (!IS_ERR_VALUE(ret))
+ return;
+ ret = -ret;
+ } else if (!(regs->ccr & 0x10000000)) {
return;
+ }
switch (ret) {
case ERESTART_RESTARTBLOCK:
@@ -95,9 +245,14 @@
regs->nip -= 4;
regs->result = 0;
} else {
- regs->result = -EINTR;
- regs->gpr[3] = EINTR;
- regs->ccr |= 0x10000000;
+ if (trap_is_scv(regs)) {
+ regs->result = -EINTR;
+ regs->gpr[3] = -EINTR;
+ } else {
+ regs->result = -EINTR;
+ regs->gpr[3] = EINTR;
+ regs->ccr |= 0x10000000;
+ }
}
}
@@ -106,7 +261,6 @@
sigset_t *oldset = sigmask_to_save();
struct ksignal ksig = { .sig = 0 };
int ret;
- int is32 = is_32bit_task();
BUG_ON(tsk != current);
@@ -118,25 +272,30 @@
if (ksig.sig <= 0) {
/* No signal to deliver -- put the saved sigmask back */
restore_saved_sigmask();
- tsk->thread.regs->trap = 0;
+ set_trap_norestart(tsk->thread.regs);
return; /* no signals delivered */
}
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
/*
* Reenable the DABR before delivering the signal to
* user space. The DABR will have been cleared if it
* triggered inside the kernel.
*/
- if (tsk->thread.hw_brk.address && tsk->thread.hw_brk.type)
- __set_breakpoint(&tsk->thread.hw_brk);
-#endif
+ if (!IS_ENABLED(CONFIG_PPC_ADV_DEBUG_REGS)) {
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (tsk->thread.hw_brk[i].address && tsk->thread.hw_brk[i].type)
+ __set_breakpoint(i, &tsk->thread.hw_brk[i]);
+ }
+ }
+
/* Re-enable the breakpoints for the signal stack */
thread_change_pc(tsk, tsk->thread.regs);
rseq_signal_deliver(&ksig, tsk->thread.regs);
- if (is32) {
+ if (is_32bit_task()) {
if (ksig.ka.sa.sa_flags & SA_SIGINFO)
ret = handle_rt_signal32(&ksig, oldset, tsk);
else
@@ -145,7 +304,7 @@
ret = handle_rt_signal64(&ksig, oldset, tsk);
}
- tsk->thread.regs->trap = 0;
+ set_trap_norestart(tsk->thread.regs);
signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP));
}
@@ -153,9 +312,6 @@
{
user_exit();
- /* Check valid addr_limit, TIF check is done there */
- addr_limit_user_check();
-
if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
@@ -168,7 +324,6 @@
}
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index 8004336..d396efc 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -10,8 +10,6 @@
#ifndef _POWERPC_ARCH_SIGNAL_H
#define _POWERPC_ARCH_SIGNAL_H
-extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
-
extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp,
size_t frame_size, int is_32);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 1b090a7..96950f1 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -47,7 +47,6 @@
#include <asm/unistd.h>
#else
#include <asm/ucontext.h>
-#include <asm/pgtable.h>
#endif
#include "signal.h"
@@ -103,22 +102,18 @@
struct mcontext __user *frame)
{
elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
- int i;
- /* Force usr to alway see softe as 1 (interrupts enabled) */
- elf_greg_t64 softe = 0x1;
+ int val, i;
WARN_ON(!FULL_REGS(regs));
for (i = 0; i <= PT_RESULT; i ++) {
- if (i == 14 && !FULL_REGS(regs))
- i = 32;
- if ( i == PT_SOFTE) {
- if(__put_user((unsigned int)softe, &frame->mc_gregs[i]))
- return -EFAULT;
- else
- continue;
- }
- if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i]))
+ /* Force usr to alway see softe as 1 (interrupts enabled) */
+ if (i == PT_SOFTE)
+ val = 1;
+ else
+ val = gregs[i];
+
+ if (__put_user(val, &frame->mc_gregs[i]))
return -EFAULT;
}
return 0;
@@ -235,146 +230,6 @@
int abigap[56];
};
-#ifdef CONFIG_VSX
-unsigned long copy_fpr_to_user(void __user *to,
- struct task_struct *task)
-{
- u64 buf[ELF_NFPREG];
- int i;
-
- /* save FPR copy to local buffer then write to the thread_struct */
- for (i = 0; i < (ELF_NFPREG - 1) ; i++)
- buf[i] = task->thread.TS_FPR(i);
- buf[i] = task->thread.fp_state.fpscr;
- return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
-}
-
-unsigned long copy_fpr_from_user(struct task_struct *task,
- void __user *from)
-{
- u64 buf[ELF_NFPREG];
- int i;
-
- if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
- return 1;
- for (i = 0; i < (ELF_NFPREG - 1) ; i++)
- task->thread.TS_FPR(i) = buf[i];
- task->thread.fp_state.fpscr = buf[i];
-
- return 0;
-}
-
-unsigned long copy_vsx_to_user(void __user *to,
- struct task_struct *task)
-{
- u64 buf[ELF_NVSRHALFREG];
- int i;
-
- /* save FPR copy to local buffer then write to the thread_struct */
- for (i = 0; i < ELF_NVSRHALFREG; i++)
- buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
- return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
-}
-
-unsigned long copy_vsx_from_user(struct task_struct *task,
- void __user *from)
-{
- u64 buf[ELF_NVSRHALFREG];
- int i;
-
- if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
- return 1;
- for (i = 0; i < ELF_NVSRHALFREG ; i++)
- task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
- return 0;
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-unsigned long copy_ckfpr_to_user(void __user *to,
- struct task_struct *task)
-{
- u64 buf[ELF_NFPREG];
- int i;
-
- /* save FPR copy to local buffer then write to the thread_struct */
- for (i = 0; i < (ELF_NFPREG - 1) ; i++)
- buf[i] = task->thread.TS_CKFPR(i);
- buf[i] = task->thread.ckfp_state.fpscr;
- return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
-}
-
-unsigned long copy_ckfpr_from_user(struct task_struct *task,
- void __user *from)
-{
- u64 buf[ELF_NFPREG];
- int i;
-
- if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
- return 1;
- for (i = 0; i < (ELF_NFPREG - 1) ; i++)
- task->thread.TS_CKFPR(i) = buf[i];
- task->thread.ckfp_state.fpscr = buf[i];
-
- return 0;
-}
-
-unsigned long copy_ckvsx_to_user(void __user *to,
- struct task_struct *task)
-{
- u64 buf[ELF_NVSRHALFREG];
- int i;
-
- /* save FPR copy to local buffer then write to the thread_struct */
- for (i = 0; i < ELF_NVSRHALFREG; i++)
- buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
- return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
-}
-
-unsigned long copy_ckvsx_from_user(struct task_struct *task,
- void __user *from)
-{
- u64 buf[ELF_NVSRHALFREG];
- int i;
-
- if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
- return 1;
- for (i = 0; i < ELF_NVSRHALFREG ; i++)
- task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
- return 0;
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-#else
-inline unsigned long copy_fpr_to_user(void __user *to,
- struct task_struct *task)
-{
- return __copy_to_user(to, task->thread.fp_state.fpr,
- ELF_NFPREG * sizeof(double));
-}
-
-inline unsigned long copy_fpr_from_user(struct task_struct *task,
- void __user *from)
-{
- return __copy_from_user(task->thread.fp_state.fpr, from,
- ELF_NFPREG * sizeof(double));
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-inline unsigned long copy_ckfpr_to_user(void __user *to,
- struct task_struct *task)
-{
- return __copy_to_user(to, task->thread.ckfp_state.fpr,
- ELF_NFPREG * sizeof(double));
-}
-
-inline unsigned long copy_ckfpr_from_user(struct task_struct *task,
- void __user *from)
-{
- return __copy_from_user(task->thread.ckfp_state.fpr, from,
- ELF_NFPREG * sizeof(double));
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-#endif
-
/*
* Save the current user registers on the user stack.
* We only save the altivec/spe registers if the process has used
@@ -640,7 +495,7 @@
if (!sig)
save_r2 = (unsigned int)regs->gpr[2];
err = restore_general_regs(regs, sr);
- regs->trap = 0;
+ set_trap_norestart(regs);
err |= __get_user(msr, &sr->mc_gregs[PT_MSR]);
if (!sig)
regs->gpr[2] = (unsigned long) save_r2;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index adfde59..bfc9393 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -21,11 +21,11 @@
#include <linux/ptrace.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
+#include <linux/pagemap.h>
#include <asm/sigcontext.h>
#include <asm/ucontext.h>
#include <linux/uaccess.h>
-#include <asm/pgtable.h>
#include <asm/unistd.h>
#include <asm/cacheflush.h>
#include <asm/syscalls.h>
@@ -40,8 +40,8 @@
#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
#define FP_REGS_SIZE sizeof(elf_fpregset_t)
-#define TRAMP_TRACEBACK 3
-#define TRAMP_SIZE 6
+#define TRAMP_TRACEBACK 4
+#define TRAMP_SIZE 7
/*
* When we have signals to deliver, we set up on the user stack,
@@ -350,8 +350,8 @@
err |= __get_user(regs->link, &sc->gp_regs[PT_LNK]);
err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]);
err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]);
- /* skip SOFTE */
- regs->trap = 0;
+ /* Don't allow userspace to set SOFTE */
+ set_trap_norestart(regs);
err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
@@ -472,10 +472,8 @@
&sc->gp_regs[PT_XER]);
err |= __get_user(tsk->thread.ckpt_regs.ccr,
&sc->gp_regs[PT_CCR]);
-
- /* Don't allow userspace to set the trap value */
- regs->trap = 0;
-
+ /* Don't allow userspace to set SOFTE */
+ set_trap_norestart(regs);
/* These regs are not checkpointed; they can go in 'regs'. */
err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
@@ -603,13 +601,15 @@
int i;
long err = 0;
+ /* bctrl # call the handler */
+ err |= __put_user(PPC_INST_BCTRL, &tramp[0]);
/* addi r1, r1, __SIGNAL_FRAMESIZE # Pop the dummy stackframe */
err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) |
- (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
+ (__SIGNAL_FRAMESIZE & 0xffff), &tramp[1]);
/* li r0, __NR_[rt_]sigreturn| */
- err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]);
+ err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[2]);
/* sc */
- err |= __put_user(PPC_INST_SC, &tramp[2]);
+ err |= __put_user(PPC_INST_SC, &tramp[3]);
/* Minimal traceback info */
for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
@@ -635,7 +635,6 @@
SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, long, ctx_size)
{
- unsigned char tmp;
sigset_t set;
unsigned long new_msr = 0;
int ctx_has_vsx_region = 0;
@@ -670,9 +669,8 @@
}
if (new_ctx == NULL)
return 0;
- if (!access_ok(new_ctx, ctx_size)
- || __get_user(tmp, (u8 __user *) new_ctx)
- || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1))
+ if (!access_ok(new_ctx, ctx_size) ||
+ fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
return -EFAULT;
/*
@@ -867,12 +865,12 @@
/* Set up to return from userspace. */
if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) {
- regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
+ regs->nip = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
} else {
err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
if (err)
goto badframe;
- regs->link = (unsigned long) &frame->tramp[0];
+ regs->nip = (unsigned long) &frame->tramp[0];
}
/* Allocate a dummy caller frame for the signal handler. */
@@ -881,8 +879,8 @@
/* Set up "regs" so we "return" to the signal handler. */
if (is_elf2_task()) {
- regs->nip = (unsigned long) ksig->ka.sa.sa_handler;
- regs->gpr[12] = regs->nip;
+ regs->ctr = (unsigned long) ksig->ka.sa.sa_handler;
+ regs->gpr[12] = regs->ctr;
} else {
/* Handler is *really* a pointer to the function descriptor for
* the signal routine. The first entry in the function
@@ -892,7 +890,7 @@
func_descr_t __user *funct_desc_ptr =
(func_descr_t __user *) ksig->ka.sa.sa_handler;
- err |= get_user(regs->nip, &funct_desc_ptr->entry);
+ err |= get_user(regs->ctr, &funct_desc_ptr->entry);
err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index c06cac5..cf99f57 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -33,6 +33,7 @@
#include <linux/processor.h>
#include <linux/random.h>
#include <linux/stackprotector.h>
+#include <linux/pgtable.h>
#include <asm/ptrace.h>
#include <linux/atomic.h>
@@ -41,7 +42,6 @@
#include <asm/kvm_ppc.h>
#include <asm/dbell.h>
#include <asm/page.h>
-#include <asm/pgtable.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/time.h>
@@ -59,6 +59,8 @@
#include <asm/asm-prototypes.h>
#include <asm/cpu_has_feature.h>
#include <asm/ftrace.h>
+#include <asm/kup.h>
+#include <asm/fadump.h>
#ifdef DEBUG
#include <asm/udbg.h>
@@ -74,17 +76,28 @@
struct task_struct *secondary_current;
bool has_big_cores;
+bool coregroup_enabled;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
EXPORT_SYMBOL_GPL(has_big_cores);
+enum {
+#ifdef CONFIG_SCHED_SMT
+ smt_idx,
+#endif
+ cache_idx,
+ mc_idx,
+ die_idx,
+};
+
#define MAX_THREAD_LIST_SIZE 8
#define THREAD_GROUP_SHARE_L1 1
struct thread_groups {
@@ -583,6 +596,45 @@
#endif
#ifdef CONFIG_NMI_IPI
+static void crash_stop_this_cpu(struct pt_regs *regs)
+#else
+static void crash_stop_this_cpu(void *dummy)
+#endif
+{
+ /*
+ * Just busy wait here and avoid marking CPU as offline to ensure
+ * register data is captured appropriately.
+ */
+ while (1)
+ cpu_relax();
+}
+
+void crash_smp_send_stop(void)
+{
+ static bool stopped = false;
+
+ /*
+ * In case of fadump, register data for all CPUs is captured by f/w
+ * on ibm,os-term rtas call. Skip IPI callbacks to other CPUs before
+ * this rtas call to avoid tricky post processing of those CPUs'
+ * backtraces.
+ */
+ if (should_fadump_crash())
+ return;
+
+ if (stopped)
+ return;
+
+ stopped = true;
+
+#ifdef CONFIG_NMI_IPI
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_stop_this_cpu, 1000000);
+#else
+ smp_call_function(crash_stop_this_cpu, NULL, 0);
+#endif /* CONFIG_NMI_IPI */
+}
+
+#ifdef CONFIG_NMI_IPI
static void nmi_stop_this_cpu(struct pt_regs *regs)
{
/*
@@ -670,6 +722,28 @@
#endif
/*
+ * Extends set_cpus_related. Instead of setting one CPU at a time in
+ * dstmask, set srcmask at oneshot. dstmask should be super set of srcmask.
+ */
+static void or_cpumasks_related(int i, int j, struct cpumask *(*srcmask)(int),
+ struct cpumask *(*dstmask)(int))
+{
+ struct cpumask *mask;
+ int k;
+
+ mask = srcmask(j);
+ for_each_cpu(k, srcmask(i))
+ cpumask_or(dstmask(k), dstmask(k), mask);
+
+ if (i == j)
+ return;
+
+ mask = srcmask(i);
+ for_each_cpu(k, srcmask(j))
+ cpumask_or(dstmask(k), dstmask(k), mask);
+}
+
+/*
* parse_thread_groups: Parses the "ibm,thread-groups" device tree
* property for the CPU device node @dn and stores
* the parsed output in the thread_groups
@@ -799,10 +873,6 @@
if (err)
goto out;
- zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
- GFP_KERNEL,
- cpu_to_node(cpu));
-
cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
if (unlikely(cpu_group_start == -1)) {
@@ -811,6 +881,9 @@
goto out;
}
+ zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
for (i = first_thread; i < first_thread + threads_per_core; i++) {
int i_group_start = get_cpu_thread_group_start(i, &tg);
@@ -829,7 +902,75 @@
return err;
}
-static int init_big_cores(void)
+static bool shared_caches;
+
+#ifdef CONFIG_SCHED_SMT
+/* cpumask of CPUs with asymmetric SMT dependency */
+static int powerpc_smt_flags(void)
+{
+ int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+
+ if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+ printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+ flags |= SD_ASYM_PACKING;
+ }
+ return flags;
+}
+#endif
+
+/*
+ * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
+ * This topology makes it *much* cheaper to migrate tasks between adjacent cores
+ * since the migrated task remains cache hot. We want to take advantage of this
+ * at the scheduler level so an extra topology level is required.
+ */
+static int powerpc_shared_cache_flags(void)
+{
+ return SD_SHARE_PKG_RESOURCES;
+}
+
+/*
+ * We can't just pass cpu_l2_cache_mask() directly because
+ * returns a non-const pointer and the compiler barfs on that.
+ */
+static const struct cpumask *shared_cache_mask(int cpu)
+{
+ return per_cpu(cpu_l2_cache_map, cpu);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+ return cpu_smallcore_mask(cpu);
+}
+#endif
+
+static struct cpumask *cpu_coregroup_mask(int cpu)
+{
+ return per_cpu(cpu_coregroup_map, cpu);
+}
+
+static bool has_coregroup_support(void)
+{
+ return coregroup_enabled;
+}
+
+static const struct cpumask *cpu_mc_mask(int cpu)
+{
+ return cpu_coregroup_mask(cpu);
+}
+
+static struct sched_domain_topology_level powerpc_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+ { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
+ { cpu_mc_mask, SD_INIT_NAME(MC) },
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
+static int __init init_big_cores(void)
{
int cpu;
@@ -871,6 +1012,11 @@
GFP_KERNEL, cpu_to_node(cpu));
zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
GFP_KERNEL, cpu_to_node(cpu));
+ if (has_coregroup_support())
+ zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
/*
* numa_node_id() works after this.
*/
@@ -879,6 +1025,7 @@
set_cpu_numa_mem(cpu,
local_memory_node(numa_cpu_lookup_table[cpu]));
}
+#endif
}
/* Init the cpumasks so the boot CPU is related to itself */
@@ -886,6 +1033,9 @@
cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+ if (has_coregroup_support())
+ cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid));
+
init_big_cores();
if (has_big_cores) {
cpumask_set_cpu(boot_cpuid,
@@ -1136,26 +1286,46 @@
return cache;
}
-static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int))
+static bool update_mask_by_l2(int cpu, cpumask_var_t *mask)
{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
struct device_node *l2_cache, *np;
int i;
- l2_cache = cpu_to_l2cache(cpu);
- if (!l2_cache)
- return false;
+ if (has_big_cores)
+ submask_fn = cpu_smallcore_mask;
- for_each_cpu(i, cpu_online_mask) {
+ l2_cache = cpu_to_l2cache(cpu);
+ if (!l2_cache || !*mask) {
+ /* Assume only core siblings share cache with this CPU */
+ for_each_cpu(i, submask_fn(cpu))
+ set_cpus_related(cpu, i, cpu_l2_cache_mask);
+
+ return false;
+ }
+
+ cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+
+ /* Update l2-cache mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask);
+
+ /* Skip all CPUs already part of current CPU l2-cache mask */
+ cpumask_andnot(*mask, *mask, cpu_l2_cache_mask(cpu));
+
+ for_each_cpu(i, *mask) {
/*
* when updating the marks the current CPU has not been marked
* online, but we need to update the cache masks
*/
np = cpu_to_l2cache(i);
- if (!np)
- continue;
- if (np == l2_cache)
- set_cpus_related(cpu, i, mask_fn);
+ /* Skip all CPUs already part of current CPU l2-cache */
+ if (np == l2_cache) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_l2_cache_mask);
+ cpumask_andnot(*mask, *mask, submask_fn(i));
+ } else {
+ cpumask_andnot(*mask, *mask, cpu_l2_cache_mask(i));
+ }
of_node_put(np);
}
@@ -1167,39 +1337,87 @@
#ifdef CONFIG_HOTPLUG_CPU
static void remove_cpu_from_masks(int cpu)
{
+ struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
int i;
- /* NB: cpu_core_mask is a superset of the others */
- for_each_cpu(i, cpu_core_mask(cpu)) {
- set_cpus_unrelated(cpu, i, cpu_core_mask);
+ if (shared_caches)
+ mask_fn = cpu_l2_cache_mask;
+
+ for_each_cpu(i, mask_fn(cpu)) {
set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
set_cpus_unrelated(cpu, i, cpu_sibling_mask);
if (has_big_cores)
set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
}
+
+ for_each_cpu(i, cpu_core_mask(cpu))
+ set_cpus_unrelated(cpu, i, cpu_core_mask);
+
+ if (has_coregroup_support()) {
+ for_each_cpu(i, cpu_coregroup_mask(cpu))
+ set_cpus_unrelated(cpu, i, cpu_coregroup_mask);
+ }
}
#endif
static inline void add_cpu_to_smallcore_masks(int cpu)
{
- struct cpumask *this_l1_cache_map = per_cpu(cpu_l1_cache_map, cpu);
- int i, first_thread = cpu_first_thread_sibling(cpu);
+ int i;
if (!has_big_cores)
return;
cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu));
- for (i = first_thread; i < first_thread + threads_per_core; i++) {
- if (cpu_online(i) && cpumask_test_cpu(i, this_l1_cache_map))
+ for_each_cpu(i, per_cpu(cpu_l1_cache_map, cpu)) {
+ if (cpu_online(i))
set_cpus_related(i, cpu, cpu_smallcore_mask);
}
}
+static void update_coregroup_mask(int cpu, cpumask_var_t *mask)
+{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
+ int coregroup_id = cpu_to_coregroup_id(cpu);
+ int i;
+
+ if (shared_caches)
+ submask_fn = cpu_l2_cache_mask;
+
+ if (!*mask) {
+ /* Assume only siblings are part of this CPU's coregroup */
+ for_each_cpu(i, submask_fn(cpu))
+ set_cpus_related(cpu, i, cpu_coregroup_mask);
+
+ return;
+ }
+
+ cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+
+ /* Update coregroup mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask);
+
+ /* Skip all CPUs already part of coregroup mask */
+ cpumask_andnot(*mask, *mask, cpu_coregroup_mask(cpu));
+
+ for_each_cpu(i, *mask) {
+ /* Skip all CPUs not part of this coregroup */
+ if (coregroup_id == cpu_to_coregroup_id(i)) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_coregroup_mask);
+ cpumask_andnot(*mask, *mask, submask_fn(i));
+ } else {
+ cpumask_andnot(*mask, *mask, cpu_coregroup_mask(i));
+ }
+ }
+}
+
static void add_cpu_to_masks(int cpu)
{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
int first_thread = cpu_first_thread_sibling(cpu);
- int chipid = cpu_to_chip_id(cpu);
+ int chip_id = cpu_to_chip_id(cpu);
+ cpumask_var_t mask;
+ bool ret;
int i;
/*
@@ -1207,49 +1425,57 @@
* add it to it's own thread sibling mask.
*/
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_core_mask(cpu));
for (i = first_thread; i < first_thread + threads_per_core; i++)
if (cpu_online(i))
set_cpus_related(i, cpu, cpu_sibling_mask);
add_cpu_to_smallcore_masks(cpu);
- /*
- * Copy the thread sibling mask into the cache sibling mask
- * and mark any CPUs that share an L2 with this CPU.
- */
- for_each_cpu(i, cpu_sibling_mask(cpu))
- set_cpus_related(cpu, i, cpu_l2_cache_mask);
- update_mask_by_l2(cpu, cpu_l2_cache_mask);
- /*
- * Copy the cache sibling mask into core sibling mask and mark
- * any CPUs on the same chip as this CPU.
- */
- for_each_cpu(i, cpu_l2_cache_mask(cpu))
- set_cpus_related(cpu, i, cpu_core_mask);
+ /* In CPU-hotplug path, hence use GFP_ATOMIC */
+ ret = alloc_cpumask_var_node(&mask, GFP_ATOMIC, cpu_to_node(cpu));
+ update_mask_by_l2(cpu, &mask);
- if (chipid == -1)
- return;
+ if (has_coregroup_support())
+ update_coregroup_mask(cpu, &mask);
- for_each_cpu(i, cpu_online_mask)
- if (cpu_to_chip_id(i) == chipid)
- set_cpus_related(cpu, i, cpu_core_mask);
+ if (shared_caches)
+ submask_fn = cpu_l2_cache_mask;
+
+ /* Update core_mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_core_mask);
+
+ /* Skip all CPUs already part of current CPU core mask */
+ cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
+
+ /* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+ if (chip_id == -1)
+ cpumask_and(mask, mask, cpu_cpu_mask(cpu));
+
+ for_each_cpu(i, mask) {
+ if (chip_id == cpu_to_chip_id(i)) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_core_mask);
+ cpumask_andnot(mask, mask, submask_fn(i));
+ } else {
+ cpumask_andnot(mask, mask, cpu_core_mask(i));
+ }
+ }
+
+ free_cpumask_var(mask);
}
-static bool shared_caches;
-
/* Activate a secondary processor. */
void start_secondary(void *unused)
{
- unsigned int cpu = smp_processor_id();
- struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+ unsigned int cpu = raw_smp_processor_id();
mmgrab(&init_mm);
current->active_mm = &init_mm;
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
- preempt_disable();
+ rcu_cpu_starting(cpu);
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
@@ -1271,14 +1497,20 @@
/* Update topology CPU masks */
add_cpu_to_masks(cpu);
- if (has_big_cores)
- sibling_mask = cpu_smallcore_mask;
/*
* Check for any shared caches. Note that this must be done on a
* per-core basis because one core in the pair might be disabled.
*/
- if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
- shared_caches = true;
+ if (!shared_caches) {
+ struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+ struct cpumask *mask = cpu_l2_cache_mask(cpu);
+
+ if (has_big_cores)
+ sibling_mask = cpu_smallcore_mask;
+
+ if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+ shared_caches = true;
+ }
smp_wmb();
notify_cpu_starting(cpu);
@@ -1296,69 +1528,52 @@
BUG();
}
+#ifdef CONFIG_PROFILING
int setup_profiling_timer(unsigned int multiplier)
{
return 0;
}
+#endif
+
+static void fixup_topology(void)
+{
+ int i;
#ifdef CONFIG_SCHED_SMT
-/* cpumask of CPUs with asymetric SMT dependancy */
-static int powerpc_smt_flags(void)
-{
- int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
-
- if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
- printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
- flags |= SD_ASYM_PACKING;
+ if (has_big_cores) {
+ pr_info("Big cores detected but using small core scheduling\n");
+ powerpc_topology[smt_idx].mask = smallcore_smt_mask;
}
- return flags;
-}
#endif
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+ if (!has_coregroup_support())
+ powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
+
+ /*
+ * Try to consolidate topology levels here instead of
+ * allowing scheduler to degenerate.
+ * - Dont consolidate if masks are different.
+ * - Dont consolidate if sd_flags exists and are different.
+ */
+ for (i = 1; i <= die_idx; i++) {
+ if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
+ continue;
+
+ if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
+ powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
+ continue;
+
+ if (!powerpc_topology[i - 1].sd_flags)
+ powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+
+ powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
+ powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
+#ifdef CONFIG_SCHED_DEBUG
+ powerpc_topology[i].name = powerpc_topology[i + 1].name;
#endif
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
-/*
- * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
- * This topology makes it *much* cheaper to migrate tasks between adjacent cores
- * since the migrated task remains cache hot. We want to take advantage of this
- * at the scheduler level so an extra topology level is required.
- */
-static int powerpc_shared_cache_flags(void)
-{
- return SD_SHARE_PKG_RESOURCES;
+ }
}
-/*
- * We can't just pass cpu_l2_cache_mask() directly because
- * returns a non-const pointer and the compiler barfs on that.
- */
-static const struct cpumask *shared_cache_mask(int cpu)
-{
- return cpu_l2_cache_mask(cpu);
-}
-
-#ifdef CONFIG_SCHED_SMT
-static const struct cpumask *smallcore_smt_mask(int cpu)
-{
- return cpu_smallcore_mask(cpu);
-}
-#endif
-
-static struct sched_domain_topology_level power9_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
void __init smp_cpus_done(unsigned int max_cpus)
{
/*
@@ -1370,31 +1585,10 @@
if (smp_ops && smp_ops->bringup_done)
smp_ops->bringup_done();
- /*
- * On a shared LPAR, associativity needs to be requested.
- * Hence, get numa topology before dumping cpu topology
- */
- shared_proc_topology_init();
dump_numa_cpu_topology();
-#ifdef CONFIG_SCHED_SMT
- if (has_big_cores) {
- pr_info("Using small cores at SMT level\n");
- power9_topology[0].mask = smallcore_smt_mask;
- powerpc_topology[0].mask = smallcore_smt_mask;
- }
-#endif
- /*
- * If any CPU detects that it's sharing a cache with another CPU then
- * use the deeper topology that is aware of this sharing.
- */
- if (shared_caches) {
- pr_info("Using shared cache scheduler topology\n");
- set_sched_topology(power9_topology);
- } else {
- pr_info("Using standard scheduler topology\n");
- set_sched_topology(powerpc_topology);
- }
+ fixup_topology();
+ set_sched_topology(powerpc_topology);
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -1424,7 +1618,7 @@
smp_ops->cpu_die(cpu);
}
-void cpu_die(void)
+void arch_cpu_idle_dead(void)
{
/*
* Disable on the down path. This will be re-enabled by
@@ -1432,8 +1626,8 @@
*/
this_cpu_disable_ftrace();
- if (ppc_md.cpu_die)
- ppc_md.cpu_die();
+ if (smp_ops->cpu_offline_self)
+ smp_ops->cpu_offline_self();
/* If we return, we re-enter start_secondary */
start_secondary_resume();
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 890f951..d4a66ce 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -59,7 +59,7 @@
{
unsigned long sp;
- sp = current_stack_pointer();
+ sp = current_stack_frame();
save_context_stack(trace, sp, current, 1);
}
@@ -73,7 +73,7 @@
return;
if (tsk == current)
- sp = current_stack_pointer();
+ sp = current_stack_frame();
else
sp = tsk->thread.ksp;
@@ -133,7 +133,7 @@
}
if (tsk == current)
- sp = current_stack_pointer();
+ sp = current_stack_frame();
else
sp = tsk->thread.ksp;
@@ -276,7 +276,7 @@
pr_cont(" current pointer corrupt? (%px)\n", p->__current);
pr_warn("Back trace of paca->saved_r1 (0x%016llx) (possibly stale):\n", p->saved_r1);
- show_stack(p->__current, (unsigned long *)p->saved_r1);
+ show_stack(p->__current, (unsigned long *)p->saved_r1, KERN_WARNING);
}
}
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
index cbdf862..f73f4d7 100644
--- a/arch/powerpc/kernel/swsusp_32.S
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -395,6 +395,7 @@
li r3,0
blr
+_ASM_NOKPROBE_SYMBOL(swsusp_arch_resume)
/* FIXME:This construct is actually not useful since we don't shut
* down the instruction MMU, we could just flip back MSR-DR on.
@@ -406,4 +407,5 @@
sync
isync
rfi
+_ASM_NOKPROBE_SYMBOL(turn_on_mmu)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
new file mode 100644
index 0000000..310bcd7
--- /dev/null
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -0,0 +1,407 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/err.h>
+#include <asm/asm-prototypes.h>
+#include <asm/kup.h>
+#include <asm/cputime.h>
+#include <asm/hw_irq.h>
+#include <asm/kprobes.h>
+#include <asm/paca.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/signal.h>
+#include <asm/switch_to.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/unistd.h>
+
+typedef long (*syscall_fn)(long, long, long, long, long, long);
+
+/* Has to run notrace because it is entered not completely "reconciled" */
+notrace long system_call_exception(long r3, long r4, long r5,
+ long r6, long r7, long r8,
+ unsigned long r0, struct pt_regs *regs)
+{
+ syscall_fn f;
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+
+ trace_hardirqs_off(); /* finish reconciling */
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+ BUG_ON(!(regs->msr & MSR_RI));
+ BUG_ON(!(regs->msr & MSR_PR));
+ BUG_ON(!FULL_REGS(regs));
+ BUG_ON(regs->softe != IRQS_ENABLED);
+
+ kuap_check_amr();
+
+ account_cpu_user_entry();
+
+#ifdef CONFIG_PPC_SPLPAR
+ if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
+ firmware_has_feature(FW_FEATURE_SPLPAR)) {
+ struct lppaca *lp = local_paca->lppaca_ptr;
+
+ if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+ accumulate_stolen_time();
+ }
+#endif
+
+ /*
+ * This is not required for the syscall exit path, but makes the
+ * stack frame look nicer. If this was initialised in the first stack
+ * frame, or if the unwinder was taught the first stack frame always
+ * returns to user with IRQS_ENABLED, this store could be avoided!
+ */
+ regs->softe = IRQS_ENABLED;
+
+ local_irq_enable();
+
+ if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
+ if (unlikely(regs->trap == 0x7ff0)) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ /*
+ * We use the return value of do_syscall_trace_enter() as the
+ * syscall number. If the syscall was rejected for any reason
+ * do_syscall_trace_enter() returns an invalid syscall number
+ * and the test against NR_syscalls will fail and the return
+ * value to be used is in regs->gpr[3].
+ */
+ r0 = do_syscall_trace_enter(regs);
+ if (unlikely(r0 >= NR_syscalls))
+ return regs->gpr[3];
+ r3 = regs->gpr[3];
+ r4 = regs->gpr[4];
+ r5 = regs->gpr[5];
+ r6 = regs->gpr[6];
+ r7 = regs->gpr[7];
+ r8 = regs->gpr[8];
+
+ } else if (unlikely(r0 >= NR_syscalls)) {
+ if (unlikely(regs->trap == 0x7ff0)) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ return -ENOSYS;
+ }
+
+ /* May be faster to do array_index_nospec? */
+ barrier_nospec();
+
+ if (unlikely(is_32bit_task())) {
+ f = (void *)compat_sys_call_table[r0];
+
+ r3 &= 0x00000000ffffffffULL;
+ r4 &= 0x00000000ffffffffULL;
+ r5 &= 0x00000000ffffffffULL;
+ r6 &= 0x00000000ffffffffULL;
+ r7 &= 0x00000000ffffffffULL;
+ r8 &= 0x00000000ffffffffULL;
+
+ } else {
+ f = (void *)sys_call_table[r0];
+ }
+
+ return f(r3, r4, r5, r6, r7, r8);
+}
+
+/*
+ * local irqs must be disabled. Returns false if the caller must re-enable
+ * them, check for new work, and try again.
+ */
+static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri)
+{
+ /* This must be done with RI=1 because tracing may touch vmaps */
+ trace_hardirqs_on();
+
+ /* This pattern matches prep_irq_for_idle */
+ if (clear_ri)
+ __hard_EE_RI_disable();
+ else
+ __hard_irq_disable();
+ if (unlikely(lazy_irq_pending_nocheck())) {
+ /* Took an interrupt, may have more exit work to do. */
+ if (clear_ri)
+ __hard_RI_enable();
+ trace_hardirqs_off();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ return false;
+ }
+ local_paca->irq_happened = 0;
+ irq_soft_mask_set(IRQS_ENABLED);
+
+ return true;
+}
+
+/*
+ * This should be called after a syscall returns, with r3 the return value
+ * from the syscall. If this function returns non-zero, the system call
+ * exit assembly should additionally load all GPR registers and CTR and XER
+ * from the interrupt frame.
+ *
+ * The function graph tracer can not trace the return side of this function,
+ * because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
+ */
+notrace unsigned long syscall_exit_prepare(unsigned long r3,
+ struct pt_regs *regs,
+ long scv)
+{
+ unsigned long *ti_flagsp = ¤t_thread_info()->flags;
+ unsigned long ti_flags;
+ unsigned long ret = 0;
+
+ kuap_check_amr();
+
+ regs->result = r3;
+
+ /* Check whether the syscall is issued inside a restartable sequence */
+ rseq_syscall(regs);
+
+ ti_flags = *ti_flagsp;
+
+ if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && !scv) {
+ if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
+ r3 = -r3;
+ regs->ccr |= 0x10000000; /* Set SO bit in CR */
+ }
+ }
+
+ if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
+ if (ti_flags & _TIF_RESTOREALL)
+ ret = _TIF_RESTOREALL;
+ else
+ regs->gpr[3] = r3;
+ clear_bits(_TIF_PERSYSCALL_MASK, ti_flagsp);
+ } else {
+ regs->gpr[3] = r3;
+ }
+
+ if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+ do_syscall_trace_leave(regs);
+ ret |= _TIF_RESTOREALL;
+ }
+
+again:
+ local_irq_disable();
+ ti_flags = READ_ONCE(*ti_flagsp);
+ while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+ local_irq_enable();
+ if (ti_flags & _TIF_NEED_RESCHED) {
+ schedule();
+ } else {
+ /*
+ * SIGPENDING must restore signal handler function
+ * argument GPRs, and some non-volatiles (e.g., r1).
+ * Restore all for now. This could be made lighter.
+ */
+ if (ti_flags & _TIF_SIGPENDING)
+ ret |= _TIF_RESTOREALL;
+ do_notify_resume(regs, ti_flags);
+ }
+ local_irq_disable();
+ ti_flags = READ_ONCE(*ti_flagsp);
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ unlikely((ti_flags & _TIF_RESTORE_TM))) {
+ restore_tm_state(regs);
+ } else {
+ unsigned long mathflags = MSR_FP;
+
+ if (cpu_has_feature(CPU_FTR_VSX))
+ mathflags |= MSR_VEC | MSR_VSX;
+ else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mathflags |= MSR_VEC;
+
+ /*
+ * If userspace MSR has all available FP bits set,
+ * then they are live and no need to restore. If not,
+ * it means the regs were given up and restore_math
+ * may decide to restore them (to avoid taking an FP
+ * fault).
+ */
+ if ((regs->msr & mathflags) != mathflags)
+ restore_math(regs);
+ }
+ }
+
+ /* scv need not set RI=0 because SRRs are not used */
+ if (unlikely(!prep_irq_for_enabled_exit(!scv))) {
+ local_irq_enable();
+ goto again;
+ }
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ local_paca->tm_scratch = regs->msr;
+#endif
+
+ account_cpu_user_exit();
+
+ return ret;
+}
+
+#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
+{
+#ifdef CONFIG_PPC_BOOK3E
+ struct thread_struct *ts = ¤t->thread;
+#endif
+ unsigned long *ti_flagsp = ¤t_thread_info()->flags;
+ unsigned long ti_flags;
+ unsigned long flags;
+ unsigned long ret = 0;
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+ BUG_ON(!(regs->msr & MSR_RI));
+ BUG_ON(!(regs->msr & MSR_PR));
+ BUG_ON(!FULL_REGS(regs));
+ BUG_ON(regs->softe != IRQS_ENABLED);
+
+ /*
+ * We don't need to restore AMR on the way back to userspace for KUAP.
+ * AMR can only have been unlocked if we interrupted the kernel.
+ */
+ kuap_check_amr();
+
+ local_irq_save(flags);
+
+again:
+ ti_flags = READ_ONCE(*ti_flagsp);
+ while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+ local_irq_enable(); /* returning to user: may enable */
+ if (ti_flags & _TIF_NEED_RESCHED) {
+ schedule();
+ } else {
+ if (ti_flags & _TIF_SIGPENDING)
+ ret |= _TIF_RESTOREALL;
+ do_notify_resume(regs, ti_flags);
+ }
+ local_irq_disable();
+ ti_flags = READ_ONCE(*ti_flagsp);
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ unlikely((ti_flags & _TIF_RESTORE_TM))) {
+ restore_tm_state(regs);
+ } else {
+ unsigned long mathflags = MSR_FP;
+
+ if (cpu_has_feature(CPU_FTR_VSX))
+ mathflags |= MSR_VEC | MSR_VSX;
+ else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mathflags |= MSR_VEC;
+
+ /* See above restore_math comment */
+ if ((regs->msr & mathflags) != mathflags)
+ restore_math(regs);
+ }
+ }
+
+ if (unlikely(!prep_irq_for_enabled_exit(true))) {
+ local_irq_enable();
+ local_irq_disable();
+ goto again;
+ }
+
+#ifdef CONFIG_PPC_BOOK3E
+ if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
+ /*
+ * Check to see if the dbcr0 register is set up to debug.
+ * Use the internal debug mode bit to do this.
+ */
+ mtmsr(mfmsr() & ~MSR_DE);
+ mtspr(SPRN_DBCR0, ts->debug.dbcr0);
+ mtspr(SPRN_DBSR, -1);
+ }
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ local_paca->tm_scratch = regs->msr;
+#endif
+
+ account_cpu_user_exit();
+
+ return ret;
+}
+
+void unrecoverable_exception(struct pt_regs *regs);
+void preempt_schedule_irq(void);
+
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
+{
+ unsigned long *ti_flagsp = ¤t_thread_info()->flags;
+ unsigned long flags;
+ unsigned long ret = 0;
+ unsigned long amr;
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
+ unrecoverable_exception(regs);
+ BUG_ON(regs->msr & MSR_PR);
+ BUG_ON(!FULL_REGS(regs));
+
+ amr = kuap_get_and_check_amr();
+
+ if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
+ clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
+ ret = 1;
+ }
+
+ local_irq_save(flags);
+
+ if (regs->softe == IRQS_ENABLED) {
+ /* Returning to a kernel context with local irqs enabled. */
+ WARN_ON_ONCE(!(regs->msr & MSR_EE));
+again:
+ if (IS_ENABLED(CONFIG_PREEMPT)) {
+ /* Return to preemptible kernel context */
+ if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED)) {
+ if (preempt_count() == 0)
+ preempt_schedule_irq();
+ }
+ }
+
+ if (unlikely(!prep_irq_for_enabled_exit(true))) {
+ /*
+ * Can't local_irq_restore to replay if we were in
+ * interrupt context. Must replay directly.
+ */
+ if (irqs_disabled_flags(flags)) {
+ replay_soft_interrupts();
+ } else {
+ local_irq_restore(flags);
+ local_irq_save(flags);
+ }
+ /* Took an interrupt, may have more exit work to do. */
+ goto again;
+ }
+ } else {
+ /* Returning to a kernel context with local irqs disabled. */
+ __hard_EE_RI_disable();
+ if (regs->msr & MSR_EE)
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+ }
+
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ local_paca->tm_scratch = regs->msr;
+#endif
+
+ /*
+ * Don't want to mfspr(SPRN_AMR) here, because this comes after mtmsr,
+ * which would cause Read-After-Write stalls. Hence, we take the AMR
+ * value from the check above.
+ */
+ kuap_restore_amr(regs, amr);
+
+ return ret;
+}
+#endif
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 3bfb388..078608e 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -79,7 +79,7 @@
* sys_select() with the appropriate args. -- Cort
*/
int
-ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp)
+ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp)
{
if ( (unsigned long)n >= 4096 )
{
@@ -89,7 +89,7 @@
|| __get_user(inp, ((fd_set __user * __user *)(buffer+1)))
|| __get_user(outp, ((fd_set __user * __user *)(buffer+2)))
|| __get_user(exp, ((fd_set __user * __user *)(buffer+3)))
- || __get_user(tvp, ((struct timeval __user * __user *)(buffer+4))))
+ || __get_user(tvp, ((struct __kernel_old_timeval __user * __user *)(buffer+4))))
return -EFAULT;
}
return sys_select(n, inp, outp, exp, tvp);
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 43f736e..1275dae 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -9,7 +9,9 @@
#
0 nospu restart_syscall sys_restart_syscall
1 nospu exit sys_exit
-2 nospu fork ppc_fork
+2 32 fork ppc_fork sys_fork
+2 64 fork sys_fork
+2 spu fork sys_ni_syscall
3 common read sys_read
4 common write sys_write
5 common open sys_open compat_sys_open
@@ -32,7 +34,7 @@
18 spu oldstat sys_ni_syscall
19 common lseek sys_lseek compat_sys_lseek
20 common getpid sys_getpid
-21 nospu mount sys_mount compat_sys_mount
+21 nospu mount sys_mount
22 32 umount sys_oldumount
22 64 umount sys_ni_syscall
22 spu umount sys_ni_syscall
@@ -158,7 +160,9 @@
119 32 sigreturn sys_sigreturn compat_sys_sigreturn
119 64 sigreturn sys_ni_syscall
119 spu sigreturn sys_ni_syscall
-120 nospu clone ppc_clone
+120 32 clone ppc_clone sys_clone
+120 64 clone sys_clone
+120 spu clone sys_ni_syscall
121 common setdomainname sys_setdomainname
122 common uname sys_newuname
123 common modify_ldt sys_ni_syscall
@@ -189,11 +193,11 @@
142 common _newselect sys_select compat_sys_select
143 common flock sys_flock
144 common msync sys_msync
-145 common readv sys_readv compat_sys_readv
-146 common writev sys_writev compat_sys_writev
+145 common readv sys_readv
+146 common writev sys_writev
147 common getsid sys_getsid
148 common fdatasync sys_fdatasync
-149 nospu _sysctl sys_sysctl compat_sys_sysctl
+149 nospu _sysctl sys_ni_syscall
150 common mlock sys_mlock
151 common munlock sys_munlock
152 common mlockall sys_mlockall
@@ -240,7 +244,9 @@
186 spu sendfile sys_sendfile64
187 common getpmsg sys_ni_syscall
188 common putpmsg sys_ni_syscall
-189 nospu vfork ppc_vfork
+189 32 vfork ppc_vfork sys_vfork
+189 64 vfork sys_vfork
+189 spu vfork sys_ni_syscall
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
191 common readahead sys_readahead compat_sys_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
@@ -316,8 +322,8 @@
248 32 clock_nanosleep sys_clock_nanosleep_time32
248 64 clock_nanosleep sys_clock_nanosleep
248 spu clock_nanosleep sys_clock_nanosleep
-249 32 swapcontext ppc_swapcontext ppc32_swapcontext
-249 64 swapcontext ppc64_swapcontext
+249 32 swapcontext ppc_swapcontext compat_sys_swapcontext
+249 64 swapcontext sys_swapcontext
249 spu swapcontext sys_ni_syscall
250 common tgkill sys_tgkill
251 32 utimes sys_utimes_time32
@@ -363,7 +369,7 @@
282 common unshare sys_unshare
283 common splice sys_splice
284 common tee sys_tee
-285 common vmsplice sys_vmsplice compat_sys_vmsplice
+285 common vmsplice sys_vmsplice
286 common openat sys_openat compat_sys_openat
287 common mkdirat sys_mkdirat
288 common mknodat sys_mknodat
@@ -427,8 +433,8 @@
336 common recv sys_recv compat_sys_recv
337 common recvfrom sys_recvfrom compat_sys_recvfrom
338 common shutdown sys_shutdown
-339 common setsockopt sys_setsockopt compat_sys_setsockopt
-340 common getsockopt sys_getsockopt compat_sys_getsockopt
+339 common setsockopt sys_setsockopt sys_setsockopt
+340 common getsockopt sys_getsockopt sys_getsockopt
341 common sendmsg sys_sendmsg compat_sys_sendmsg
342 common recvmsg sys_recvmsg compat_sys_recvmsg
343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32
@@ -443,8 +449,8 @@
348 common syncfs sys_syncfs
349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg
350 common setns sys_setns
-351 nospu process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
-352 nospu process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
+351 nospu process_vm_readv sys_process_vm_readv
+352 nospu process_vm_writev sys_process_vm_writev
353 nospu finit_module sys_finit_module
354 nospu kcmp sys_kcmp
355 common sched_setattr sys_sched_setattr
@@ -456,7 +462,7 @@
361 common bpf sys_bpf
362 nospu execveat sys_execveat compat_sys_execveat
363 32 switch_endian sys_ni_syscall
-363 64 switch_endian ppc_switch_endian
+363 64 switch_endian sys_switch_endian
363 spu switch_endian sys_ni_syscall
364 common userfaultfd sys_userfaultfd
365 common membarrier sys_membarrier
@@ -516,4 +522,11 @@
432 common fsmount sys_fsmount
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
-435 nospu clone3 ppc_clone3
+435 32 clone3 ppc_clone3 sys_clone3
+435 64 clone3 sys_clone3
+435 spu clone3 sys_ni_syscall
+436 common close_range sys_close_range
+437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
+439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
diff --git a/arch/powerpc/kernel/syscalls/syscallhdr.sh b/arch/powerpc/kernel/syscalls/syscallhdr.sh
index c0a9a32..02d6751 100644
--- a/arch/powerpc/kernel/syscalls/syscallhdr.sh
+++ b/arch/powerpc/kernel/syscalls/syscallhdr.sh
@@ -32,6 +32,5 @@
printf "#define __NR_syscalls\t%s\n" "${nxt}"
printf "#endif\n"
printf "\n"
- printf "#endif /* %s */" "${fileguard}"
- printf "\n"
+ printf "#endif /* %s */\n" "${fileguard}"
) > "$out"
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index f08ca60..d36e71b 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -19,6 +19,7 @@
#include <asm/smp.h>
#include <asm/pmc.h>
#include <asm/firmware.h>
+#include <asm/idle.h>
#include <asm/svm.h>
#include "cacheinfo.h"
@@ -79,6 +80,154 @@
#endif /* CONFIG_PPC64 */
+#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
+static void read_##NAME(void *val) \
+{ \
+ *(unsigned long *)val = mfspr(ADDRESS); \
+} \
+static void write_##NAME(void *val) \
+{ \
+ EXTRA; \
+ mtspr(ADDRESS, *(unsigned long *)val); \
+}
+
+#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+static ssize_t show_##NAME(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ struct cpu *cpu = container_of(dev, struct cpu, dev); \
+ unsigned long val; \
+ smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1); \
+ return sprintf(buf, "%lx\n", val); \
+} \
+static ssize_t __used \
+ store_##NAME(struct device *dev, struct device_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ struct cpu *cpu = container_of(dev, struct cpu, dev); \
+ unsigned long val; \
+ int ret = sscanf(buf, "%lx", &val); \
+ if (ret != 1) \
+ return -EINVAL; \
+ smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \
+ return count; \
+}
+
+#define SYSFS_PMCSETUP(NAME, ADDRESS) \
+ __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+#define SYSFS_SPRSETUP(NAME, ADDRESS) \
+ __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#ifdef CONFIG_PPC64
+
+/*
+ * This is the system wide DSCR register default value. Any
+ * change to this default value through the sysfs interface
+ * will update all per cpu DSCR default values across the
+ * system stored in their respective PACA structures.
+ */
+static unsigned long dscr_default;
+
+/**
+ * read_dscr() - Fetch the cpu specific DSCR default
+ * @val: Returned cpu specific DSCR default value
+ *
+ * This function returns the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void read_dscr(void *val)
+{
+ *(unsigned long *)val = get_paca()->dscr_default;
+}
+
+
+/**
+ * write_dscr() - Update the cpu specific DSCR default
+ * @val: New cpu specific DSCR default value to update
+ *
+ * This function updates the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void write_dscr(void *val)
+{
+ get_paca()->dscr_default = *(unsigned long *)val;
+ if (!current->thread.dscr_inherit) {
+ current->thread.dscr = *(unsigned long *)val;
+ mtspr(SPRN_DSCR, *(unsigned long *)val);
+ }
+}
+
+SYSFS_SPRSETUP_SHOW_STORE(dscr);
+static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
+
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+ attr->attr.mode |= 0200;
+}
+
+/**
+ * show_dscr_default() - Fetch the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ *
+ * This function returns the system wide DSCR default value.
+ */
+static ssize_t show_dscr_default(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lx\n", dscr_default);
+}
+
+/**
+ * store_dscr_default() - Update the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ * @count: Size of the update
+ *
+ * This function updates the system wide DSCR default value.
+ */
+static ssize_t __used store_dscr_default(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int ret = 0;
+
+ ret = sscanf(buf, "%lx", &val);
+ if (ret != 1)
+ return -EINVAL;
+ dscr_default = val;
+
+ on_each_cpu(write_dscr, &val, 1);
+
+ return count;
+}
+
+static DEVICE_ATTR(dscr_default, 0600,
+ show_dscr_default, store_dscr_default);
+
+static void sysfs_create_dscr_default(void)
+{
+ if (cpu_has_feature(CPU_FTR_DSCR)) {
+ int cpu;
+
+ dscr_default = spr_default_dscr;
+ for_each_possible_cpu(cpu)
+ paca_ptrs[cpu]->dscr_default = dscr_default;
+
+ device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
+ }
+}
+#endif /* CONFIG_PPC64 */
+
#ifdef CONFIG_PPC_FSL_BOOK3E
#define MAX_BIT 63
@@ -399,84 +548,35 @@
}
EXPORT_SYMBOL(ppc_enable_pmcs);
-#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
-static void read_##NAME(void *val) \
-{ \
- *(unsigned long *)val = mfspr(ADDRESS); \
-} \
-static void write_##NAME(void *val) \
-{ \
- EXTRA; \
- mtspr(ADDRESS, *(unsigned long *)val); \
-}
-#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
-static ssize_t show_##NAME(struct device *dev, \
- struct device_attribute *attr, \
- char *buf) \
-{ \
- struct cpu *cpu = container_of(dev, struct cpu, dev); \
- unsigned long val; \
- smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1); \
- return sprintf(buf, "%lx\n", val); \
-} \
-static ssize_t __used \
- store_##NAME(struct device *dev, struct device_attribute *attr, \
- const char *buf, size_t count) \
-{ \
- struct cpu *cpu = container_of(dev, struct cpu, dev); \
- unsigned long val; \
- int ret = sscanf(buf, "%lx", &val); \
- if (ret != 1) \
- return -EINVAL; \
- smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \
- return count; \
-}
-
-#define SYSFS_PMCSETUP(NAME, ADDRESS) \
- __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
- __SYSFS_SPRSETUP_SHOW_STORE(NAME)
-#define SYSFS_SPRSETUP(NAME, ADDRESS) \
- __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
- __SYSFS_SPRSETUP_SHOW_STORE(NAME)
-
-#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
- __SYSFS_SPRSETUP_SHOW_STORE(NAME)
/* Let's define all possible registers, we'll only hook up the ones
* that are implemented on the current processor
*/
-#if defined(CONFIG_PPC64)
+#ifdef CONFIG_PMU_SYSFS
+#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32)
#define HAS_PPC_PMC_CLASSIC 1
#define HAS_PPC_PMC_IBM 1
-#define HAS_PPC_PMC_PA6T 1
-#elif defined(CONFIG_PPC_BOOK3S_32)
-#define HAS_PPC_PMC_CLASSIC 1
-#define HAS_PPC_PMC_IBM 1
-#define HAS_PPC_PMC_G4 1
-#endif
-
-
-#ifdef HAS_PPC_PMC_CLASSIC
-SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
-SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
-SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
-SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
-SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
-SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
-SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
-SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
-
-#ifdef HAS_PPC_PMC_G4
-SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
#endif
#ifdef CONFIG_PPC64
-SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
-SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+#define HAS_PPC_PMC_PA6T 1
+#define HAS_PPC_PMC56 1
+#endif
-SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+#ifdef CONFIG_PPC_BOOK3S_32
+#define HAS_PPC_PMC_G4 1
+#endif
+#endif /* CONFIG_PMU_SYSFS */
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_DEBUG_MISC)
+#define HAS_PPC_PA6T
+#endif
+/*
+ * SPRs which are not related to PMU.
+ */
+#ifdef CONFIG_PPC64
SYSFS_SPRSETUP(purr, SPRN_PURR);
SYSFS_SPRSETUP(spurr, SPRN_SPURR);
SYSFS_SPRSETUP(pir, SPRN_PIR);
@@ -487,116 +587,41 @@
enable write when needed with a separate function.
Lets be conservative and default to pseries.
*/
-static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
static DEVICE_ATTR(pir, 0400, show_pir, NULL);
static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
-
-/*
- * This is the system wide DSCR register default value. Any
- * change to this default value through the sysfs interface
- * will update all per cpu DSCR default values across the
- * system stored in their respective PACA structures.
- */
-static unsigned long dscr_default;
-
-/**
- * read_dscr() - Fetch the cpu specific DSCR default
- * @val: Returned cpu specific DSCR default value
- *
- * This function returns the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
- */
-static void read_dscr(void *val)
-{
- *(unsigned long *)val = get_paca()->dscr_default;
-}
-
-
-/**
- * write_dscr() - Update the cpu specific DSCR default
- * @val: New cpu specific DSCR default value to update
- *
- * This function updates the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
- */
-static void write_dscr(void *val)
-{
- get_paca()->dscr_default = *(unsigned long *)val;
- if (!current->thread.dscr_inherit) {
- current->thread.dscr = *(unsigned long *)val;
- mtspr(SPRN_DSCR, *(unsigned long *)val);
- }
-}
-
-SYSFS_SPRSETUP_SHOW_STORE(dscr);
-static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-
-static void add_write_permission_dev_attr(struct device_attribute *attr)
-{
- attr->attr.mode |= 0200;
-}
-
-/**
- * show_dscr_default() - Fetch the system wide DSCR default
- * @dev: Device structure
- * @attr: Device attribute structure
- * @buf: Interface buffer
- *
- * This function returns the system wide DSCR default value.
- */
-static ssize_t show_dscr_default(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- return sprintf(buf, "%lx\n", dscr_default);
-}
-
-/**
- * store_dscr_default() - Update the system wide DSCR default
- * @dev: Device structure
- * @attr: Device attribute structure
- * @buf: Interface buffer
- * @count: Size of the update
- *
- * This function updates the system wide DSCR default value.
- */
-static ssize_t __used store_dscr_default(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long val;
- int ret = 0;
-
- ret = sscanf(buf, "%lx", &val);
- if (ret != 1)
- return -EINVAL;
- dscr_default = val;
-
- on_each_cpu(write_dscr, &val, 1);
-
- return count;
-}
-
-static DEVICE_ATTR(dscr_default, 0600,
- show_dscr_default, store_dscr_default);
-
-static void sysfs_create_dscr_default(void)
-{
- if (cpu_has_feature(CPU_FTR_DSCR)) {
- int err = 0;
- int cpu;
-
- dscr_default = spr_default_dscr;
- for_each_possible_cpu(cpu)
- paca_ptrs[cpu]->dscr_default = dscr_default;
-
- err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
- }
-}
-
#endif /* CONFIG_PPC64 */
+#ifdef HAS_PPC_PMC_CLASSIC
+SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
+SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
+SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
+SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
+SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
+SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
+SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
+SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
+#endif
+
+#ifdef HAS_PPC_PMC_G4
+SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
+#endif
+
+#ifdef HAS_PPC_PMC56
+SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
+SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+
+SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+SYSFS_PMCSETUP(mmcr3, SPRN_MMCR3);
+
+static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static DEVICE_ATTR(mmcr3, 0600, show_mmcr3, store_mmcr3);
+#endif /* HAS_PPC_PMC56 */
+
+
+
+
#ifdef HAS_PPC_PMC_PA6T
SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0);
SYSFS_PMCSETUP(pa6t_pmc1, SPRN_PA6T_PMC1);
@@ -604,7 +629,9 @@
SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);
-#ifdef CONFIG_DEBUG_MISC
+#endif
+
+#ifdef HAS_PPC_PA6T
SYSFS_SPRSETUP(hid0, SPRN_HID0);
SYSFS_SPRSETUP(hid1, SPRN_HID1);
SYSFS_SPRSETUP(hid4, SPRN_HID4);
@@ -633,15 +660,14 @@
SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1);
SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2);
SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3);
-#endif /* CONFIG_DEBUG_MISC */
-#endif /* HAS_PPC_PMC_PA6T */
+#endif /* HAS_PPC_PA6T */
#ifdef HAS_PPC_PMC_IBM
static struct device_attribute ibm_common_attrs[] = {
__ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
__ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
};
-#endif /* HAS_PPC_PMC_G4 */
+#endif /* HAS_PPC_PMC_IBM */
#ifdef HAS_PPC_PMC_G4
static struct device_attribute g4_common_attrs[] = {
@@ -651,6 +677,7 @@
};
#endif /* HAS_PPC_PMC_G4 */
+#ifdef HAS_PPC_PMC_CLASSIC
static struct device_attribute classic_pmc_attrs[] = {
__ATTR(pmc1, 0600, show_pmc1, store_pmc1),
__ATTR(pmc2, 0600, show_pmc2, store_pmc2),
@@ -658,14 +685,16 @@
__ATTR(pmc4, 0600, show_pmc4, store_pmc4),
__ATTR(pmc5, 0600, show_pmc5, store_pmc5),
__ATTR(pmc6, 0600, show_pmc6, store_pmc6),
-#ifdef CONFIG_PPC64
+#ifdef HAS_PPC_PMC56
__ATTR(pmc7, 0600, show_pmc7, store_pmc7),
__ATTR(pmc8, 0600, show_pmc8, store_pmc8),
#endif
};
+#endif
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
static struct device_attribute pa6t_attrs[] = {
+#ifdef HAS_PPC_PMC_PA6T
__ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
__ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
__ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0),
@@ -674,7 +703,8 @@
__ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3),
__ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4),
__ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5),
-#ifdef CONFIG_DEBUG_MISC
+#endif
+#ifdef HAS_PPC_PA6T
__ATTR(hid0, 0600, show_hid0, store_hid0),
__ATTR(hid1, 0600, show_hid1, store_hid1),
__ATTR(hid4, 0600, show_hid4, store_hid4),
@@ -703,10 +733,9 @@
__ATTR(tsr1, 0600, show_tsr1, store_tsr1),
__ATTR(tsr2, 0600, show_tsr2, store_tsr2),
__ATTR(tsr3, 0600, show_tsr3, store_tsr3),
-#endif /* CONFIG_DEBUG_MISC */
+#endif /* HAS_PPC_PA6T */
};
-#endif /* HAS_PPC_PMC_PA6T */
-#endif /* HAS_PPC_PMC_CLASSIC */
+#endif
#ifdef CONFIG_PPC_SVM
static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char *buf)
@@ -725,6 +754,74 @@
}
#endif /* CONFIG_PPC_SVM */
+#ifdef CONFIG_PPC_PSERIES
+static void read_idle_purr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_purr();
+}
+
+static ssize_t idle_purr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
+
+static void create_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_purr);
+}
+
+static void remove_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_purr);
+}
+
+static void read_idle_spurr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_spurr();
+}
+
+static ssize_t idle_spurr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
+
+static void create_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_spurr);
+}
+
+static void remove_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_spurr);
+}
+
+#else /* CONFIG_PPC_PSERIES */
+#define create_idle_purr_file(s)
+#define remove_idle_purr_file(s)
+#define create_idle_spurr_file(s)
+#define remove_idle_spurr_file(s)
+#endif /* CONFIG_PPC_PSERIES */
+
static int register_cpu_online(unsigned int cpu)
{
struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -757,14 +854,14 @@
pmc_attrs = classic_pmc_attrs;
break;
#endif /* HAS_PPC_PMC_G4 */
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
case PPC_PMC_PA6T:
/* PA Semi starts counting at PMC0 */
attrs = pa6t_attrs;
nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute);
pmc_attrs = NULL;
break;
-#endif /* HAS_PPC_PMC_PA6T */
+#endif
default:
attrs = NULL;
nattrs = 0;
@@ -779,17 +876,25 @@
device_create_file(s, &pmc_attrs[i]);
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_create_file(s, &dev_attr_mmcra);
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_create_file(s, &dev_attr_mmcr3);
+#endif /* CONFIG_PMU_SYSFS */
+
if (cpu_has_feature(CPU_FTR_PURR)) {
if (!firmware_has_feature(FW_FEATURE_LPAR))
add_write_permission_dev_attr(&dev_attr_purr);
device_create_file(s, &dev_attr_purr);
+ create_idle_purr_file(s);
}
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_create_file(s, &dev_attr_spurr);
+ create_idle_spurr_file(s);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_create_file(s, &dev_attr_dscr);
@@ -846,14 +951,14 @@
pmc_attrs = classic_pmc_attrs;
break;
#endif /* HAS_PPC_PMC_G4 */
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
case PPC_PMC_PA6T:
/* PA Semi starts counting at PMC0 */
attrs = pa6t_attrs;
nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute);
pmc_attrs = NULL;
break;
-#endif /* HAS_PPC_PMC_PA6T */
+#endif
default:
attrs = NULL;
nattrs = 0;
@@ -868,14 +973,23 @@
device_remove_file(s, &pmc_attrs[i]);
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_remove_file(s, &dev_attr_mmcra);
- if (cpu_has_feature(CPU_FTR_PURR))
- device_remove_file(s, &dev_attr_purr);
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_remove_file(s, &dev_attr_mmcr3);
+#endif /* CONFIG_PMU_SYSFS */
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_PURR)) {
+ device_remove_file(s, &dev_attr_purr);
+ remove_idle_purr_file(s);
+ }
+
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_remove_file(s, &dev_attr_spurr);
+ remove_idle_spurr_file(s);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_remove_file(s, &dev_attr_dscr);
@@ -1045,6 +1159,7 @@
for_each_possible_cpu(cpu) {
struct cpu *c = &per_cpu(cpu_devices, cpu);
+#ifdef CONFIG_HOTPLUG_CPU
/*
* For now, we just see if the system supports making
* the RTAS calls for CPU hotplug. But, there may be a
@@ -1052,8 +1167,9 @@
* CPU. For instance, the boot cpu might never be valid
* for hotplugging.
*/
- if (ppc_md.cpu_die)
+ if (smp_ops && smp_ops->cpu_offline_self)
c->hotpluggable = 1;
+#endif
if (cpu_online(cpu) || c->hotpluggable) {
register_cpu(c, cpu);
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 5b905a2..d34276f 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -16,25 +16,22 @@
#ifdef CONFIG_PPC64
.p2align 3
+#define __SYSCALL(nr, entry) .8byte entry
+#else
+#define __SYSCALL(nr, entry) .long entry
#endif
.globl sys_call_table
sys_call_table:
#ifdef CONFIG_PPC64
-#define __SYSCALL(nr, entry) .8byte DOTSYM(entry)
#include <asm/syscall_table_64.h>
-#undef __SYSCALL
#else
-#define __SYSCALL(nr, entry) .long entry
#include <asm/syscall_table_32.h>
-#undef __SYSCALL
#endif
#ifdef CONFIG_COMPAT
.globl compat_sys_call_table
compat_sys_call_table:
#define compat_sys_sigsuspend sys_sigsuspend
-#define __SYSCALL(nr, entry) .8byte DOTSYM(entry)
#include <asm/syscall_table_c32.h>
-#undef __SYSCALL
#endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0e0a222..1d20f0f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -50,9 +50,10 @@
#include <linux/irq.h>
#include <linux/delay.h>
#include <linux/irq_work.h>
-#include <linux/clk-provider.h>
+#include <linux/of_clk.h>
#include <linux/suspend.h>
#include <linux/sched/cputime.h>
+#include <linux/sched/clock.h>
#include <linux/processor.h>
#include <asm/trace.h>
@@ -75,15 +76,6 @@
#include <linux/clockchips.h>
#include <linux/timekeeper_internal.h>
-static u64 rtc_read(struct clocksource *);
-static struct clocksource clocksource_rtc = {
- .name = "rtc",
- .rating = 400,
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
- .mask = CLOCKSOURCE_MASK(64),
- .read = rtc_read,
-};
-
static u64 timebase_read(struct clocksource *);
static struct clocksource clocksource_timebase = {
.name = "timebase",
@@ -183,6 +175,8 @@
#ifdef CONFIG_PPC_SPLPAR
+#include <asm/dtl.h>
+
/*
* Scan the dispatch trace log and count up the stolen time.
* Should be called with interrupts disabled.
@@ -338,7 +332,7 @@
return stime;
}
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
{
unsigned long stime, stime_scaled, steal_time;
struct cpu_accounting_data *acct = get_accounting(tsk);
@@ -366,7 +360,7 @@
#endif
}
}
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
void vtime_account_idle(struct task_struct *tsk)
{
@@ -395,7 +389,7 @@
/*
* Account the whole cputime accumulated in the paca
* Must be called with interrupts disabled.
- * Assumes that vtime_account_system/idle() has been called
+ * Assumes that vtime_account_kernel/idle() has been called
* recently (i.e. since the last entry from usermode) so that
* get_paca()->user_time_scaled is up to date.
*/
@@ -445,19 +439,9 @@
void __delay(unsigned long loops)
{
unsigned long start;
- int diff;
spin_begin();
- if (__USE_RTC()) {
- start = get_rtcl();
- do {
- /* the RTCL register wraps at 1000000000 */
- diff = get_rtcl() - start;
- if (diff < 0)
- diff += 1000000000;
- spin_cpu_relax();
- } while (diff < loops);
- } else if (tb_invalid) {
+ if (tb_invalid) {
/*
* TB is in error state and isn't ticking anymore.
* HMI handler was unable to recover from TB error.
@@ -465,8 +449,8 @@
*/
spin_cpu_relax();
} else {
- start = get_tbl();
- while (get_tbl() - start < loops)
+ start = mftb();
+ while (mftb() - start < loops)
spin_cpu_relax();
}
spin_end();
@@ -569,14 +553,11 @@
struct pt_regs *old_regs;
u64 now;
- /* Some implementations of hotplug will get timer interrupts while
- * offline, just ignore these and we also need to set
- * decrementers_next_tb as MAX to make sure __check_irq_replay
- * don't replay timer interrupt when return, otherwise we'll trap
- * here infinitely :(
+ /*
+ * Some implementations of hotplug will get timer interrupts while
+ * offline, just ignore these.
*/
if (unlikely(!cpu_online(smp_processor_id()))) {
- *next_tb = ~(u64)0;
set_dec(decrementer_max);
return;
}
@@ -612,7 +593,7 @@
irq_work_run();
}
- now = get_tb_or_rtc();
+ now = get_tb();
if (now >= *next_tb) {
*next_tb = ~(u64)0;
if (evt->event_handler)
@@ -645,15 +626,6 @@
}
#endif
-/*
- * Hypervisor decrementer interrupts shouldn't occur but are sometimes
- * left pending on exit from a KVM guest. We don't need to do anything
- * to clear them, as they are edge-triggered.
- */
-void hdec_interrupt(struct pt_regs *regs)
-{
-}
-
#ifdef CONFIG_SUSPEND
static void generic_suspend_disable_irqs(void)
{
@@ -703,8 +675,6 @@
*/
notrace unsigned long long sched_clock(void)
{
- if (__USE_RTC())
- return get_rtc();
return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
}
@@ -854,11 +824,6 @@
}
/* clocksource code */
-static notrace u64 rtc_read(struct clocksource *cs)
-{
- return (u64)get_rtc();
-}
-
static notrace u64 timebase_read(struct clocksource *cs)
{
return (u64)get_tb();
@@ -867,7 +832,7 @@
void update_vsyscall(struct timekeeper *tk)
{
- struct timespec xt;
+ struct timespec64 xt;
struct clocksource *clock = tk->tkr_mono.clock;
u32 mult = tk->tkr_mono.mult;
u32 shift = tk->tkr_mono.shift;
@@ -939,7 +904,8 @@
vdso_data->tb_to_xs = new_tb_to_xs;
vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
- vdso_data->stamp_xtime = xt;
+ vdso_data->stamp_xtime_sec = xt.tv_sec;
+ vdso_data->stamp_xtime_nsec = xt.tv_nsec;
vdso_data->stamp_sec_fraction = frac_sec;
vdso_data->hrtimer_res = hrtimer_resolution;
smp_wmb();
@@ -954,12 +920,7 @@
static void __init clocksource_init(void)
{
- struct clocksource *clock;
-
- if (__USE_RTC())
- clock = &clocksource_rtc;
- else
- clock = &clocksource_timebase;
+ struct clocksource *clock = &clocksource_timebase;
if (clocksource_register_hz(clock, tb_ticks_per_sec)) {
printk(KERN_ERR "clocksource: %s is already registered\n",
@@ -974,7 +935,7 @@
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev)
{
- __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
+ __this_cpu_write(decrementers_next_tb, get_tb() + evt);
set_dec(evt);
/* We may have raced with new irq work */
@@ -1077,17 +1038,12 @@
u64 scale;
unsigned shift;
- if (__USE_RTC()) {
- /* 601 processor: dec counts down by 128 every 128ns */
- ppc_tb_freq = 1000000000;
- } else {
- /* Normal PowerPC with timebase register */
- ppc_md.calibrate_decr();
- printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
- ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
- printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
- ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
- }
+ /* Normal PowerPC with timebase register */
+ ppc_md.calibrate_decr();
+ printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
+ ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
+ printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
+ ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
tb_ticks_per_jiffy = ppc_tb_freq / HZ;
tb_ticks_per_sec = ppc_tb_freq;
@@ -1113,7 +1069,7 @@
tb_to_ns_scale = scale;
tb_to_ns_shift = shift;
/* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
- boot_tb = get_tb_or_rtc();
+ boot_tb = get_tb();
/* If platform provided a timezone (pmac), we correct the time */
if (timezone_offset) {
@@ -1139,9 +1095,8 @@
init_decrementer_clockevent();
tick_setup_hrtimer_broadcast();
-#ifdef CONFIG_COMMON_CLK
of_clk_init(NULL);
-#endif
+ enable_sched_clock_irqtime();
}
/*
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 6ba0fdd..2b91f23 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -122,6 +122,13 @@
std r3, STK_PARAM(R3)(r1)
SAVE_NVGPRS(r1)
+ /*
+ * Save kernel live AMR since it will be clobbered by treclaim
+ * but can be used elsewhere later in kernel space.
+ */
+ mfspr r3, SPRN_AMR
+ std r3, TM_FRAME_L1(r1)
+
/* We need to setup MSR for VSX register save instructions. */
mfmsr r14
mr r15, r14
@@ -245,7 +252,7 @@
* but is used in signal return to 'wind back' to the abort handler.
*/
- /* ******************** CR,LR,CCR,MSR ********** */
+ /* ***************** CTR, LR, CR, XER ********** */
mfctr r3
mflr r4
mfcr r5
@@ -256,7 +263,6 @@
std r5, _CCR(r7)
std r6, _XER(r7)
-
/* ******************** TAR, DSCR ********** */
mfspr r3, SPRN_TAR
mfspr r4, SPRN_DSCR
@@ -264,6 +270,10 @@
std r3, THREAD_TM_TAR(r12)
std r4, THREAD_TM_DSCR(r12)
+ /* ******************** AMR **************** */
+ mfspr r3, SPRN_AMR
+ std r3, THREAD_TM_AMR(r12)
+
/*
* MSR and flags: We don't change CRs, and we don't need to alter MSR.
*/
@@ -308,7 +318,9 @@
std r3, THREAD_TM_TFHAR(r12)
std r4, THREAD_TM_TFIAR(r12)
- /* AMR is checkpointed too, but is unsupported by Linux. */
+ /* Restore kernel live AMR */
+ ld r8, TM_FRAME_L1(r1)
+ mtspr SPRN_AMR, r8
/* Restore original MSR/IRQ state & clear TM mode */
ld r14, TM_FRAME_L0(r1) /* Orig MSR */
@@ -355,6 +367,13 @@
*/
SAVE_NVGPRS(r1)
+ /*
+ * Save kernel live AMR since it will be clobbered for trechkpt
+ * but can be used elsewhere later in kernel space.
+ */
+ mfspr r8, SPRN_AMR
+ std r8, TM_FRAME_L0(r1)
+
/* Load complete register state from ts_ckpt* registers */
addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */
@@ -404,7 +423,7 @@
restore_gprs:
- /* ******************** CR,LR,CCR,MSR ********** */
+ /* ****************** CTR, LR, XER ************* */
ld r4, _CTR(r7)
ld r5, _LINK(r7)
ld r8, _XER(r7)
@@ -417,6 +436,10 @@
ld r4, THREAD_TM_TAR(r3)
mtspr SPRN_TAR, r4
+ /* ******************** AMR ******************** */
+ ld r4, THREAD_TM_AMR(r3)
+ mtspr SPRN_AMR, r4
+
/* Load up the PPR and DSCR in GPRs only at this stage */
ld r5, THREAD_TM_DSCR(r3)
ld r6, THREAD_TM_PPR(r3)
@@ -509,6 +532,10 @@
li r4, MSR_RI
mtmsrd r4, 1
+ /* Restore kernel live AMR */
+ ld r8, TM_FRAME_L0(r1)
+ mtspr SPRN_AMR, r8
+
REST_NVGPRS(r1)
addi r1, r1, TM_FRAME_SIZE
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 7ea0ca0..42761eb 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,6 +27,7 @@
#include <asm/code-patching.h>
#include <asm/ftrace.h>
#include <asm/syscall.h>
+#include <asm/inst.h>
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -40,23 +41,23 @@
#define NUM_FTRACE_TRAMPS 8
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
-static unsigned int
+static struct ppc_inst
ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
{
- unsigned int op;
+ struct ppc_inst op;
addr = ppc_function_entry((void *)addr);
/* if (link) set op to 'bl' else 'b' */
- op = create_branch((unsigned int *)ip, addr, link ? 1 : 0);
+ create_branch(&op, (struct ppc_inst *)ip, addr, link ? 1 : 0);
return op;
}
static int
-ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
+ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new)
{
- unsigned int replaced;
+ struct ppc_inst replaced;
/*
* Note:
@@ -67,18 +68,18 @@
*/
/* read the text we want to modify */
- if (probe_kernel_read(&replaced, (void *)ip, MCOUNT_INSN_SIZE))
+ if (probe_kernel_read_inst(&replaced, (void *)ip))
return -EFAULT;
/* Make sure it is what we expect it to be */
- if (replaced != old) {
- pr_err("%p: replaced (%#x) != old (%#x)",
- (void *)ip, replaced, old);
+ if (!ppc_inst_equal(replaced, old)) {
+ pr_err("%p: replaced (%s) != old (%s)",
+ (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old));
return -EINVAL;
}
/* replace the text with the new text */
- if (patch_instruction((unsigned int *)ip, new))
+ if (patch_instruction((struct ppc_inst *)ip, new))
return -EPERM;
return 0;
@@ -89,27 +90,28 @@
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
+ struct ppc_inst op;
addr = ppc_function_entry((void *)addr);
/* use the create_branch to verify that this offset can be branched */
- return create_branch((unsigned int *)ip, addr, 0);
+ return create_branch(&op, (struct ppc_inst *)ip, addr, 0) == 0;
}
-static int is_bl_op(unsigned int op)
+static int is_bl_op(struct ppc_inst op)
{
- return (op & 0xfc000003) == 0x48000001;
+ return (ppc_inst_val(op) & 0xfc000003) == 0x48000001;
}
-static int is_b_op(unsigned int op)
+static int is_b_op(struct ppc_inst op)
{
- return (op & 0xfc000003) == 0x48000000;
+ return (ppc_inst_val(op) & 0xfc000003) == 0x48000000;
}
-static unsigned long find_bl_target(unsigned long ip, unsigned int op)
+static unsigned long find_bl_target(unsigned long ip, struct ppc_inst op)
{
int offset;
- offset = (op & 0x03fffffc);
+ offset = (ppc_inst_val(op) & 0x03fffffc);
/* make it signed */
if (offset & 0x02000000)
offset |= 0xfe000000;
@@ -125,17 +127,17 @@
{
unsigned long entry, ptr, tramp;
unsigned long ip = rec->ip;
- unsigned int op, pop;
+ struct ppc_inst op, pop;
/* read where this goes */
- if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+ if (probe_kernel_read_inst(&op, (void *)ip)) {
pr_err("Fetching opcode failed.\n");
return -EFAULT;
}
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -160,16 +162,18 @@
#ifdef CONFIG_MPROFILE_KERNEL
/* When using -mkernel_profile there is no load to jump over */
- pop = PPC_INST_NOP;
+ pop = ppc_inst(PPC_INST_NOP);
- if (probe_kernel_read(&op, (void *)(ip - 4), 4)) {
+ if (probe_kernel_read_inst(&op, (void *)(ip - 4))) {
pr_err("Fetching instruction at %lx failed.\n", ip - 4);
return -EFAULT;
}
/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
- if (op != PPC_INST_MFLR && op != PPC_INST_STD_LR) {
- pr_err("Unexpected instruction %08x around bl _mcount\n", op);
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_MFLR)) &&
+ !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
+ pr_err("Unexpected instruction %s around bl _mcount\n",
+ ppc_inst_as_str(op));
return -EINVAL;
}
#else
@@ -187,24 +191,24 @@
* Use a b +8 to jump over the load.
*/
- pop = PPC_INST_BRANCH | 8; /* b +8 */
+ pop = ppc_inst(PPC_INST_BRANCH | 8); /* b +8 */
/*
* Check what is in the next instruction. We can see ld r2,40(r1), but
* on first pass after boot we will see mflr r0.
*/
- if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) {
+ if (probe_kernel_read_inst(&op, (void *)(ip + 4))) {
pr_err("Fetching op failed.\n");
return -EFAULT;
}
- if (op != PPC_INST_LD_TOC) {
- pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, op);
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
+ pr_err("Expected %08x found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op));
return -EINVAL;
}
#endif /* CONFIG_MPROFILE_KERNEL */
- if (patch_instruction((unsigned int *)ip, pop)) {
+ if (patch_instruction((struct ppc_inst *)ip, pop)) {
pr_err("Patching NOP failed.\n");
return -EPERM;
}
@@ -217,17 +221,17 @@
__ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned int op;
+ struct ppc_inst op;
unsigned int jmp[4];
unsigned long ip = rec->ip;
unsigned long tramp;
- if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -245,7 +249,7 @@
pr_devel("ip:%lx jumps to %lx", ip, tramp);
/* Find where the trampoline jumps to */
- if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+ if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) {
pr_err("Failed to read %lx\n", tramp);
return -EFAULT;
}
@@ -274,9 +278,9 @@
return -EINVAL;
}
- op = PPC_INST_NOP;
+ op = ppc_inst(PPC_INST_NOP);
- if (patch_instruction((unsigned int *)ip, op))
+ if (patch_instruction((struct ppc_inst *)ip, op))
return -EPERM;
return 0;
@@ -287,6 +291,7 @@
static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
+ struct ppc_inst instr;
/*
* We have the compiler generated long_branch tramps at the end
@@ -295,7 +300,8 @@
for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
if (!ftrace_tramps[i])
continue;
- else if (create_branch((void *)ip, ftrace_tramps[i], 0))
+ else if (create_branch(&instr, (void *)ip,
+ ftrace_tramps[i], 0) == 0)
return ftrace_tramps[i];
return 0;
@@ -322,8 +328,10 @@
*/
static int setup_mcount_compiler_tramp(unsigned long tramp)
{
- int i, op;
+ int i;
+ struct ppc_inst op;
unsigned long ptr;
+ struct ppc_inst instr;
static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS];
/* Is this a known long jump tramp? */
@@ -341,7 +349,7 @@
return -1;
/* New trampoline -- read where this goes */
- if (probe_kernel_read(&op, (void *)tramp, sizeof(int))) {
+ if (probe_kernel_read_inst(&op, (void *)tramp)) {
pr_debug("Fetching opcode failed.\n");
return -1;
}
@@ -366,13 +374,13 @@
#else
ptr = ppc_global_function_entry((void *)ftrace_caller);
#endif
- if (!create_branch((void *)tramp, ptr, 0)) {
+ if (create_branch(&instr, (void *)tramp, ptr, 0)) {
pr_debug("%ps is not reachable from existing mcount tramp\n",
(void *)ptr);
return -1;
}
- if (patch_branch((unsigned int *)tramp, ptr, 0)) {
+ if (patch_branch((struct ppc_inst *)tramp, ptr, 0)) {
pr_debug("REL24 out of range!\n");
return -1;
}
@@ -388,17 +396,17 @@
static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long tramp, ip = rec->ip;
- unsigned int op;
+ struct ppc_inst op;
/* Read where this goes */
- if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+ if (probe_kernel_read_inst(&op, (void *)ip)) {
pr_err("Fetching opcode failed.\n");
return -EFAULT;
}
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -416,7 +424,7 @@
}
}
- if (patch_instruction((unsigned int *)ip, PPC_INST_NOP)) {
+ if (patch_instruction((struct ppc_inst *)ip, ppc_inst(PPC_INST_NOP))) {
pr_err("Patching NOP failed.\n");
return -EPERM;
}
@@ -428,7 +436,7 @@
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
- unsigned int old, new;
+ struct ppc_inst old, new;
/*
* If the calling address is more that 24 bits away,
@@ -438,7 +446,7 @@
if (test_24bit_addr(ip, addr)) {
/* within range */
old = ftrace_call_replace(ip, addr, 1);
- new = PPC_INST_NOP;
+ new = ppc_inst(PPC_INST_NOP);
return ftrace_modify_code(ip, old, new);
} else if (core_kernel_text(ip))
return __ftrace_make_nop_kernel(rec, addr);
@@ -481,7 +489,7 @@
*/
#ifndef CONFIG_MPROFILE_KERNEL
static int
-expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
{
/*
* We expect to see:
@@ -492,16 +500,17 @@
* The load offset is different depending on the ABI. For simplicity
* just mask it out when doing the compare.
*/
- if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000))
+ if (!ppc_inst_equal(op0, ppc_inst(0x48000008)) ||
+ (ppc_inst_val(op1) & 0xffff0000) != 0xe8410000)
return 0;
return 1;
}
#else
static int
-expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
{
/* look for patched "NOP" on ppc64 with -mprofile-kernel */
- if (op0 != PPC_INST_NOP)
+ if (!ppc_inst_equal(op0, ppc_inst(PPC_INST_NOP)))
return 0;
return 1;
}
@@ -510,18 +519,22 @@
static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned int op[2];
+ struct ppc_inst op[2];
+ struct ppc_inst instr;
void *ip = (void *)rec->ip;
unsigned long entry, ptr, tramp;
struct module *mod = rec->arch.mod;
/* read where this goes */
- if (probe_kernel_read(op, ip, sizeof(op)))
+ if (probe_kernel_read_inst(op, ip))
+ return -EFAULT;
+
+ if (probe_kernel_read_inst(op + 1, ip + 4))
return -EFAULT;
if (!expected_nop_sequence(ip, op[0], op[1])) {
- pr_err("Unexpected call sequence at %p: %x %x\n",
- ip, op[0], op[1]);
+ pr_err("Unexpected call sequence at %p: %s %s\n",
+ ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1]));
return -EINVAL;
}
@@ -557,7 +570,7 @@
}
/* Ensure branch is within 24 bits */
- if (!create_branch(ip, tramp, BRANCH_SET_LINK)) {
+ if (create_branch(&instr, ip, tramp, BRANCH_SET_LINK)) {
pr_err("Branch out of range\n");
return -EINVAL;
}
@@ -574,16 +587,17 @@
static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned int op;
+ int err;
+ struct ppc_inst op;
unsigned long ip = rec->ip;
/* read where this goes */
- if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+ if (probe_kernel_read_inst(&op, (void *)ip))
return -EFAULT;
/* It should be pointing to a nop */
- if (op != PPC_INST_NOP) {
- pr_err("Expected NOP but have %x\n", op);
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) {
+ pr_err("Expected NOP but have %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -594,16 +608,16 @@
}
/* create the branch to the trampoline */
- op = create_branch((unsigned int *)ip,
- rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
- if (!op) {
+ err = create_branch(&op, (struct ppc_inst *)ip,
+ rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
+ if (err) {
pr_err("REL24 out of range!\n");
return -EINVAL;
}
pr_devel("write to %lx\n", rec->ip);
- if (patch_instruction((unsigned int *)ip, op))
+ if (patch_instruction((struct ppc_inst *)ip, op))
return -EPERM;
return 0;
@@ -613,7 +627,7 @@
static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned int op;
+ struct ppc_inst op;
void *ip = (void *)rec->ip;
unsigned long tramp, entry, ptr;
@@ -634,13 +648,13 @@
}
/* Make sure we have a nop */
- if (probe_kernel_read(&op, ip, sizeof(op))) {
+ if (probe_kernel_read_inst(&op, ip)) {
pr_err("Unable to read ftrace location %p\n", ip);
return -EFAULT;
}
- if (op != PPC_INST_NOP) {
- pr_err("Unexpected call sequence at %p: %x\n", ip, op);
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) {
+ pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op));
return -EINVAL;
}
@@ -661,7 +675,7 @@
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
- unsigned int old, new;
+ struct ppc_inst old, new;
/*
* If the calling address is more that 24 bits away,
@@ -670,7 +684,7 @@
*/
if (test_24bit_addr(ip, addr)) {
/* within range */
- old = PPC_INST_NOP;
+ old = ppc_inst(PPC_INST_NOP);
new = ftrace_call_replace(ip, addr, 1);
return ftrace_modify_code(ip, old, new);
} else if (core_kernel_text(ip))
@@ -700,7 +714,7 @@
__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
- unsigned int op;
+ struct ppc_inst op;
unsigned long ip = rec->ip;
unsigned long entry, ptr, tramp;
struct module *mod = rec->arch.mod;
@@ -712,14 +726,14 @@
}
/* read where this goes */
- if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+ if (probe_kernel_read_inst(&op, (void *)ip)) {
pr_err("Fetching opcode failed.\n");
return -EFAULT;
}
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -748,7 +762,7 @@
/* The new target may be within range */
if (test_24bit_addr(ip, addr)) {
/* within range */
- if (patch_branch((unsigned int *)ip, addr, BRANCH_SET_LINK)) {
+ if (patch_branch((struct ppc_inst *)ip, addr, BRANCH_SET_LINK)) {
pr_err("REL24 out of range!\n");
return -EINVAL;
}
@@ -776,12 +790,12 @@
}
/* Ensure branch is within 24 bits */
- if (!create_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) {
+ if (create_branch(&op, (struct ppc_inst *)ip, tramp, BRANCH_SET_LINK)) {
pr_err("Branch out of range\n");
return -EINVAL;
}
- if (patch_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) {
+ if (patch_branch((struct ppc_inst *)ip, tramp, BRANCH_SET_LINK)) {
pr_err("REL24 out of range!\n");
return -EINVAL;
}
@@ -794,7 +808,7 @@
unsigned long addr)
{
unsigned long ip = rec->ip;
- unsigned int old, new;
+ struct ppc_inst old, new;
/*
* If the calling address is more that 24 bits away,
@@ -834,10 +848,10 @@
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
- unsigned int old, new;
+ struct ppc_inst old, new;
int ret;
- old = *(unsigned int *)&ftrace_call;
+ old = ppc_inst_read((struct ppc_inst *)&ftrace_call);
new = ftrace_call_replace(ip, (unsigned long)func, 1);
ret = ftrace_modify_code(ip, old, new);
@@ -845,7 +859,7 @@
/* Also update the regs callback function */
if (!ret) {
ip = (unsigned long)(&ftrace_regs_call);
- old = *(unsigned int *)&ftrace_regs_call;
+ old = ppc_inst_read((struct ppc_inst *)&ftrace_regs_call);
new = ftrace_call_replace(ip, (unsigned long)func, 1);
ret = ftrace_modify_code(ip, old, new);
}
@@ -919,7 +933,7 @@
unsigned long ip = (unsigned long)(&ftrace_graph_call);
unsigned long addr = (unsigned long)(&ftrace_graph_caller);
unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- unsigned int old, new;
+ struct ppc_inst old, new;
old = ftrace_call_replace(ip, stub, 0);
new = ftrace_call_replace(ip, addr, 0);
@@ -932,7 +946,7 @@
unsigned long ip = (unsigned long)(&ftrace_graph_call);
unsigned long addr = (unsigned long)(&ftrace_graph_caller);
unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- unsigned int old, new;
+ struct ppc_inst old, new;
old = ftrace_call_replace(ip, addr, 0);
new = ftrace_call_replace(ip, stub, 0);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index ecfa460..069d451 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -39,7 +39,6 @@
#include <linux/kmsg_dump.h>
#include <asm/emulated_ops.h>
-#include <asm/pgtable.h>
#include <linux/uaccess.h>
#include <asm/debugfs.h>
#include <asm/io.h>
@@ -441,15 +440,12 @@
void system_reset_exception(struct pt_regs *regs)
{
unsigned long hsrr0, hsrr1;
- bool nested = in_nmi();
bool saved_hsrrs = false;
+ u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
- /*
- * Avoid crashes in case of nested NMI exceptions. Recoverability
- * is determined by RI and in_nmi
- */
- if (!nested)
- nmi_enter();
+ this_cpu_set_ftrace_enabled(0);
+
+ nmi_enter();
/*
* System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -524,8 +520,9 @@
mtspr(SPRN_HSRR1, hsrr1);
}
- if (!nested)
- nmi_exit();
+ nmi_exit();
+
+ this_cpu_set_ftrace_enabled(ftrace_enabled);
/* What should we do here? We could issue a shutdown or hard reset. */
}
@@ -535,9 +532,6 @@
* Check if the NIP corresponds to the address of a sync
* instruction for which there is an entry in the exception
* table.
- * Note that the 601 only takes a machine check on TEA
- * (transfer error ack) signal assertion, and does not
- * set any of the top 16 bits of SRR1.
* -- paulus.
*/
static inline int check_io_access(struct pt_regs *regs)
@@ -586,6 +580,8 @@
#define REASON_ILLEGAL (ESR_PIL | ESR_PUO)
#define REASON_PRIVILEGED ESR_PPR
#define REASON_TRAP ESR_PTR
+#define REASON_PREFIXED 0
+#define REASON_BOUNDARY 0
/* single-step stuff */
#define single_stepping(regs) (current->thread.debug.dbcr0 & DBCR0_IC)
@@ -600,12 +596,16 @@
#define REASON_ILLEGAL SRR1_PROGILL
#define REASON_PRIVILEGED SRR1_PROGPRIV
#define REASON_TRAP SRR1_PROGTRAP
+#define REASON_PREFIXED SRR1_PREFIXED
+#define REASON_BOUNDARY SRR1_BOUNDARY
#define single_stepping(regs) ((regs)->msr & MSR_SE)
#define clear_single_step(regs) ((regs)->msr &= ~MSR_SE)
#define clear_br_trace(regs) ((regs)->msr &= ~MSR_BE)
#endif
+#define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4)
+
#if defined(CONFIG_E500)
int machine_check_e500mc(struct pt_regs *regs)
{
@@ -796,7 +796,6 @@
case 0x80000:
pr_cont("Machine check signal\n");
break;
- case 0: /* for 601 */
case 0x40000:
case 0x140000: /* 7450 MSS error and TEA */
pr_cont("Transfer error ack signal\n");
@@ -826,9 +825,20 @@
void machine_check_exception(struct pt_regs *regs)
{
int recover = 0;
- bool nested = in_nmi();
- if (!nested)
- nmi_enter();
+
+ /*
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled).
+ *
+ * This is silly. The BOOK3S_64 should just call a different function
+ * rather than expecting semantics to magically change. Something
+ * like 'non_nmi_machine_check_exception()', perhaps?
+ */
+ const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64);
+
+ if (nmi) nmi_enter();
__this_cpu_inc(irq_stat.mce_exceptions);
@@ -854,8 +864,7 @@
if (check_io_access(regs))
goto bail;
- if (!nested)
- nmi_exit();
+ if (nmi) nmi_exit();
die("Machine check", regs, SIGBUS);
@@ -866,8 +875,7 @@
return;
bail:
- if (!nested)
- nmi_exit();
+ if (nmi) nmi_exit();
}
void SMIException(struct pt_regs *regs)
@@ -1596,11 +1604,20 @@
{
enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
+ unsigned long reason;
/* We restore the interrupt state now */
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
+ reason = get_reason(regs);
+
+ if (reason & REASON_BOUNDARY) {
+ sig = SIGBUS;
+ code = BUS_ADRALN;
+ goto bad;
+ }
+
if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
goto bail;
@@ -1609,7 +1626,8 @@
fixed = fix_alignment(regs);
if (fixed == 1) {
- regs->nip += 4; /* skip over emulated instruction */
+ /* skip over emulated instruction */
+ regs->nip += inst_length(reason);
emulate_single_step(regs);
goto bail;
}
@@ -1622,6 +1640,7 @@
sig = SIGBUS;
code = BUS_ADRALN;
}
+bad:
if (user_mode(regs))
_exception(sig, regs, code, regs->dar);
else
@@ -1640,6 +1659,15 @@
panic("kernel stack overflow");
}
+void stack_overflow_exception(struct pt_regs *regs)
+{
+ enum ctx_state prev_state = exception_enter();
+
+ die("Kernel stack overflow", regs, SIGSEGV);
+
+ exception_exit(prev_state);
+}
+
void kernel_fp_unavailable_exception(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
@@ -1714,6 +1742,7 @@
[FSCR_TAR_LG] = "TAR",
[FSCR_MSGP_LG] = "MSGP",
[FSCR_SCV_LG] = "SCV",
+ [FSCR_PREFIX_LG] = "PREFIX",
};
char *facility = "unknown";
u64 value;
@@ -1893,11 +1922,40 @@
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-void performance_monitor_exception(struct pt_regs *regs)
+static void performance_monitor_exception_nmi(struct pt_regs *regs)
{
+ nmi_enter();
+
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
+
+ nmi_exit();
+}
+
+static void performance_monitor_exception_async(struct pt_regs *regs)
+{
+ irq_enter();
+
+ __this_cpu_inc(irq_stat.pmu_irqs);
+
+ perf_irq(regs);
+
+ irq_exit();
+}
+
+void performance_monitor_exception(struct pt_regs *regs)
+{
+ /*
+ * On 64-bit, if perf interrupts hit in a local_irq_disable
+ * (soft-masked) region, we consider them as NMIs. This is required to
+ * prevent hash faults on user addresses when reading callchains (and
+ * looks better from an irq tracing perspective).
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && unlikely(arch_irq_disabled_regs(regs)))
+ performance_monitor_exception_nmi(regs);
+ else
+ performance_monitor_exception_async(regs);
}
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -2030,14 +2088,6 @@
NOKPROBE_SYMBOL(DebugException);
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-#if !defined(CONFIG_TAU_INT)
-void TAUException(struct pt_regs *regs)
-{
- printk("TAU trap at PC: %lx, MSR: %lx, vector=%lx %s\n",
- regs->nip, regs->msr, regs->trap, print_tainted());
-}
-#endif /* CONFIG_INT_TAU */
-
#ifdef CONFIG_ALTIVEC
void altivec_assist_exception(struct pt_regs *regs)
{
@@ -2272,35 +2322,20 @@
static int __init ppc_warn_emulated_init(void)
{
- struct dentry *dir, *d;
+ struct dentry *dir;
unsigned int i;
struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
- if (!powerpc_debugfs_root)
- return -ENODEV;
-
dir = debugfs_create_dir("emulated_instructions",
powerpc_debugfs_root);
- if (!dir)
- return -ENOMEM;
- d = debugfs_create_u32("do_warn", 0644, dir,
- &ppc_warn_emulated);
- if (!d)
- goto fail;
+ debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
- for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) {
- d = debugfs_create_u32(entries[i].name, 0644, dir,
- (u32 *)&entries[i].val.counter);
- if (!d)
- goto fail;
- }
+ for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++)
+ debugfs_create_u32(entries[i].name, 0644, dir,
+ (u32 *)&entries[i].val.counter);
return 0;
-
-fail:
- debugfs_remove_recursive(dir);
- return -ENOMEM;
}
device_initcall(ppc_warn_emulated_init);
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index a384e7c..01595e8 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -120,13 +120,15 @@
#define UDBG_BUFSIZE 256
void udbg_printf(const char *fmt, ...)
{
- char buf[UDBG_BUFSIZE];
- va_list args;
+ if (udbg_putc) {
+ char buf[UDBG_BUFSIZE];
+ va_list args;
- va_start(args, fmt);
- vsnprintf(buf, UDBG_BUFSIZE, fmt, args);
- udbg_puts(buf);
- va_end(args);
+ va_start(args, fmt);
+ vsnprintf(buf, UDBG_BUFSIZE, fmt, args);
+ udbg_puts(buf);
+ va_end(args);
+ }
}
void __init udbg_progress(char *s, unsigned short hex)
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index 1cfef0e..d200e7d 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -14,6 +14,7 @@
#include <linux/kdebug.h>
#include <asm/sstep.h>
+#include <asm/inst.h>
#define UPROBE_TRAP_NR UINT_MAX
@@ -111,7 +112,7 @@
* support doesn't exist and have to fix-up the next instruction
* to be executed.
*/
- regs->nip = utask->vaddr + MAX_UINSN_BYTES;
+ regs->nip = (unsigned long)ppc_inst_next((void *)utask->vaddr, &auprobe->insn);
user_disable_single_step(current);
return 0;
@@ -173,7 +174,7 @@
* emulate_step() returns 1 if the insn was successfully emulated.
* For all other cases, we need to single-step in hardware.
*/
- ret = emulate_step(regs, auprobe->insn);
+ ret = emulate_step(regs, ppc_inst_read(&auprobe->insn));
if (ret > 0)
return true;
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index efb1ba4..495ffc9 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -18,7 +18,6 @@
#include <linux/security.h>
#include <linux/memblock.h>
-#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -171,7 +170,7 @@
* and end up putting it elsewhere.
* Add enough to the size so that the result can be aligned.
*/
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
vdso_base = get_unmapped_area(NULL, vdso_base,
(vdso_pages << PAGE_SHIFT) +
@@ -211,11 +210,11 @@
goto fail_mmapsem;
}
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
return 0;
fail_mmapsem:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
return rc;
}
@@ -391,12 +390,7 @@
symname);
return 0;
}
-#ifdef VDS64_HAS_DESCRIPTORS
- return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) -
- VDSO64_LBASE;
-#else
return sym->st_value - VDSO64_LBASE;
-#endif
}
static int __init vdso_do_func_patch64(struct lib32_elfinfo *v32,
@@ -481,7 +475,7 @@
*/
#ifdef CONFIG_PPC64
- vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64");
+ vdso64_rt_sigtramp = find_function64(v64, "__kernel_start_sigtramp_rt64");
#endif
vdso32_sigtramp = find_function32(v32, "__kernel_sigtramp32");
vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32");
@@ -656,7 +650,8 @@
if (sys_call_table[i] != sys_ni_syscall)
vdso_data->syscall_map_64[i >> 5] |=
0x80000000UL >> (i & 0x1f);
- if (compat_sys_call_table[i] != sys_ni_syscall)
+ if (IS_ENABLED(CONFIG_COMPAT) &&
+ compat_sys_call_table[i] != sys_ni_syscall)
vdso_data->syscall_map_32[i >> 5] |=
0x80000000UL >> (i & 0x1f);
#else /* CONFIG_PPC64 */
@@ -728,11 +723,6 @@
*/
vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT;
DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages);
-#else
- vdso_data->dcache_block_size = L1_CACHE_BYTES;
- vdso_data->dcache_log_block_size = L1_CACHE_SHIFT;
- vdso_data->icache_block_size = L1_CACHE_BYTES;
- vdso_data->icache_log_block_size = L1_CACHE_SHIFT;
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/vdso32/.gitignore b/arch/powerpc/kernel/vdso32/.gitignore
index fea5809..824b863 100644
--- a/arch/powerpc/kernel/vdso32/.gitignore
+++ b/arch/powerpc/kernel/vdso32/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
vdso32.lds
vdso32.so.dbg
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 06f54d9..73eada6 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,9 +2,7 @@
# List of files in the vdso, has to be asm only for now
-obj-vdso32-$(CONFIG_PPC64) = getcpu.o
-obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \
- $(obj-vdso32-y)
+obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
# Build rules
@@ -31,7 +29,7 @@
asflags-y := -D__VDSO32__ -s
obj-y += vdso32_wrapper.o
-extra-y += vdso32.lds
+targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -Upowerpc
# Force dependency (incbin is bad)
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 7f882e7..3440ddf 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -8,7 +8,9 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
+#include <asm/cache.h>
.text
@@ -22,42 +24,62 @@
*/
V_FUNCTION_BEGIN(__kernel_sync_dicache)
.cfi_startproc
+#ifdef CONFIG_PPC64
mflr r12
.cfi_register lr,r12
- mr r11,r3
- bl __get_datapage@local
+ get_datapage r10, r0
mtlr r12
- mr r10,r3
+#endif
+#ifdef CONFIG_PPC64
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+#else
+ li r5, L1_CACHE_BYTES - 1
+#endif
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5 /* ensure we get enough */
+#ifdef CONFIG_PPC64
lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
srw. r8,r8,r9 /* compute line count */
+#else
+ srwi. r8, r8, L1_CACHE_SHIFT
+ mr r7, r6
+#endif
crclr cr0*4+so
beqlr /* nothing to do? */
mtctr r8
1: dcbst 0,r6
+#ifdef CONFIG_PPC64
add r6,r6,r7
+#else
+ addi r6, r6, L1_CACHE_BYTES
+#endif
bdnz 1b
sync
/* Now invalidate the instruction cache */
+#ifdef CONFIG_PPC64
lwz r7,CFG_ICACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5
lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
srw. r8,r8,r9 /* compute line count */
crclr cr0*4+so
beqlr /* nothing to do? */
+#endif
mtctr r8
+#ifdef CONFIG_PPC64
2: icbi 0,r6
add r6,r6,r7
+#else
+2: icbi 0, r7
+ addi r7, r7, L1_CACHE_BYTES
+#endif
bdnz 2b
isync
li r3,0
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 6c7401b..1d23e27 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -10,35 +10,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
.text
.global __kernel_datapage_offset;
__kernel_datapage_offset:
.long 0
-V_FUNCTION_BEGIN(__get_datapage)
- .cfi_startproc
- /* We don't want that exposed or overridable as we want other objects
- * to be able to bl directly to here
- */
- .protected __get_datapage
- .hidden __get_datapage
-
- mflr r0
- .cfi_register lr,r0
-
- bcl 20,31,data_page_branch
-data_page_branch:
- mflr r3
- mtlr r0
- addi r3, r3, __kernel_datapage_offset-data_page_branch
- lwz r0,0(r3)
- .cfi_restore lr
- add r3,r0,r3
- blr
- .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
*
@@ -52,11 +30,10 @@
.cfi_startproc
mflr r12
.cfi_register lr,r12
- mr r4,r3
- bl __get_datapage@local
+ mr. r4,r3
+ get_datapage r3, r0
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP32
- cmpli cr0,r4,0
beqlr
li r0,NR_syscalls
stw r0,0(r4)
@@ -70,12 +47,11 @@
*
* returns the timebase frequency in HZ
*/
-#ifndef CONFIG_PPC_BOOK3S_601
V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- bl __get_datapage@local
+ get_datapage r3, r0
lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
lwz r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
@@ -83,4 +59,3 @@
blr
.cfi_endproc
V_FUNCTION_END(__kernel_get_tbfreq)
-#endif
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 63e9145..ff5e214 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -15,6 +15,7 @@
* int __kernel_getcpu(unsigned *cpu, unsigned *node);
*
*/
+#if defined(CONFIG_PPC64)
V_FUNCTION_BEGIN(__kernel_getcpu)
.cfi_startproc
mfspr r5,SPRN_SPRG_VDSO_READ
@@ -24,10 +25,26 @@
rlwinm r7,r5,16,31-15,31-0
beq cr0,1f
stw r6,0(r3)
-1: beq cr1,2f
- stw r7,0(r4)
-2: crclr cr0*4+so
+1: crclr cr0*4+so
li r3,0 /* always success */
+ beqlr cr1
+ stw r7,0(r4)
blr
.cfi_endproc
V_FUNCTION_END(__kernel_getcpu)
+#elif !defined(CONFIG_SMP)
+V_FUNCTION_BEGIN(__kernel_getcpu)
+ .cfi_startproc
+ cmpwi cr0, r3, 0
+ cmpwi cr1, r4, 0
+ li r5, 0
+ beq cr0, 1f
+ stw r5, 0(r3)
+1: li r3, 0 /* always success */
+ crclr cr0*4+so
+ beqlr cr1
+ stw r5, 0(r4)
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
+#endif
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index a967e79..e7f8f9f 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -9,16 +9,15 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
/* Offset for the low 32-bit part of a field of long type */
#ifdef CONFIG_PPC64
#define LOPART 4
-#define TSPEC_TV_SEC TSPC64_TV_SEC+LOPART
#else
#define LOPART 0
-#define TSPEC_TV_SEC TSPC32_TV_SEC
#endif
.text
@@ -33,28 +32,26 @@
mflr r12
.cfi_register lr,r12
- mr r10,r3 /* r10 saves tv */
+ mr. r10,r3 /* r10 saves tv */
mr r11,r4 /* r11 saves tz */
- bl __get_datapage@local /* get data page */
- mr r9, r3 /* datapage ptr in r9 */
- cmplwi r10,0 /* check if tv is NULL */
+ get_datapage r9, r0
beq 3f
- lis r7,1000000@ha /* load up USEC_PER_SEC */
- addi r7,r7,1000000@l /* so we get microseconds in r4 */
+ LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */
bl __do_get_tspec@local /* get sec/usec from tb & kernel */
stw r3,TVAL32_TV_SEC(r10)
stw r4,TVAL32_TV_USEC(r10)
3: cmplwi r11,0 /* check if tz is NULL */
- beq 1f
+ mtlr r12
+ crclr cr0*4+so
+ li r3,0
+ beqlr
+
lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
lwz r5,CFG_TZ_DSTTIME(r9)
stw r4,TZONE_TZ_MINWEST(r11)
stw r5,TZONE_TZ_DSTTIME(r11)
-1: mtlr r12
- crclr cr0*4+so
- li r3,0
blr
.cfi_endproc
V_FUNCTION_END(__kernel_gettimeofday)
@@ -71,17 +68,23 @@
cmpli cr0,r3,CLOCK_REALTIME
cmpli cr1,r3,CLOCK_MONOTONIC
cror cr0*4+eq,cr0*4+eq,cr1*4+eq
- bne cr0,99f
+
+ cmpli cr5,r3,CLOCK_REALTIME_COARSE
+ cmpli cr6,r3,CLOCK_MONOTONIC_COARSE
+ cror cr5*4+eq,cr5*4+eq,cr6*4+eq
+
+ cror cr0*4+eq,cr0*4+eq,cr5*4+eq
+ bne cr0, .Lgettime_fallback
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- bl __get_datapage@local /* get data page */
- mr r9,r3 /* datapage ptr in r9 */
- lis r7,NSEC_PER_SEC@h /* want nanoseconds */
- ori r7,r7,NSEC_PER_SEC@l
-50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
- bne cr1,80f /* not monotonic -> all done */
+ get_datapage r9, r0
+ LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */
+ beq cr5, .Lcoarse_clocks
+.Lprecise_clocks:
+ bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
+ bne cr1, .Lfinish /* not monotonic -> all done */
/*
* CLOCK_MONOTONIC
@@ -105,12 +108,53 @@
add r9,r9,r0
lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
cmpl cr0,r8,r0 /* check if updated */
- bne- 50b
+ bne- .Lprecise_clocks
+ b .Lfinish_monotonic
+
+ /*
+ * For coarse clocks we get data directly from the vdso data page, so
+ * we don't need to call __do_get_tspec, but we still need to do the
+ * counter trick.
+ */
+.Lcoarse_clocks:
+ lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+ andi. r0,r8,1 /* pending update ? loop */
+ bne- .Lcoarse_clocks
+ add r9,r9,r0 /* r0 is already 0 */
+
+ /*
+ * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+ * too
+ */
+ lwz r3,STAMP_XTIME_SEC+LOPART(r9)
+ lwz r4,STAMP_XTIME_NSEC+LOPART(r9)
+ bne cr6,1f
+
+ /* CLOCK_MONOTONIC_COARSE */
+ lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
+ lwz r6,WTOM_CLOCK_NSEC(r9)
+
+ /* check if counter has updated */
+ or r0,r6,r5
+1: or r0,r0,r3
+ or r0,r0,r4
+ xor r0,r0,r0
+ add r3,r3,r0
+ lwz r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
+ cmpl cr0,r0,r8 /* check if updated */
+ bne- .Lcoarse_clocks
+
+ /* Counter has not updated, so continue calculating proper values for
+ * sec and nsec if monotonic coarse, or just return with the proper
+ * values for realtime.
+ */
+ bne cr6, .Lfinish
/* Calculate and store result. Note that this mimics the C code,
* which may cause funny results if nsec goes negative... is that
* possible at all ?
*/
+.Lfinish_monotonic:
add r3,r3,r5
add r4,r4,r6
cmpw cr0,r4,r7
@@ -118,11 +162,12 @@
blt 1f
subf r4,r7,r4
addi r3,r3,1
-1: bge cr1,80f
+1: bge cr1, .Lfinish
addi r3,r3,-1
add r4,r4,r7
-80: stw r3,TSPC32_TV_SEC(r11)
+.Lfinish:
+ stw r3,TSPC32_TV_SEC(r11)
stw r4,TSPC32_TV_NSEC(r11)
mtlr r12
@@ -133,7 +178,7 @@
/*
* syscall fallback
*/
-99:
+.Lgettime_fallback:
li r0,__NR_clock_gettime
.cfi_restore lr
sc
@@ -151,17 +196,20 @@
V_FUNCTION_BEGIN(__kernel_clock_getres)
.cfi_startproc
/* Check for supported clock IDs */
- cmpwi cr0,r3,CLOCK_REALTIME
- cmpwi cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
- bne cr0,99f
+ cmplwi cr0, r3, CLOCK_MAX
+ cmpwi cr1, r3, CLOCK_REALTIME_COARSE
+ cmpwi cr7, r3, CLOCK_MONOTONIC_COARSE
+ bgt cr0, 99f
+ LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
+ beq cr1, 1f
+ beq cr7, 1f
mflr r12
.cfi_register lr,r12
- bl __get_datapage@local /* get data page */
+ get_datapage r3, r0
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
- li r3,0
+1: li r3,0
cmpli cr0,r4,0
crclr cr0*4+so
beqlr
@@ -192,16 +240,15 @@
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- bl __get_datapage@local
- mr r9, r3 /* datapage ptr in r9 */
+ get_datapage r9, r0
- lwz r3,STAMP_XTIME+TSPEC_TV_SEC(r9)
+ lwz r3,STAMP_XTIME_SEC+LOPART(r9)
cmplwi r11,0 /* check if t is NULL */
- beq 2f
- stw r3,0(r11) /* store result at *t */
-2: mtlr r12
+ mtlr r12
crclr cr0*4+so
+ beqlr
+ stw r3,0(r11) /* store result at *t */
blr
.cfi_endproc
V_FUNCTION_END(__kernel_time)
@@ -271,7 +318,7 @@
* as a 32.32 fixed-point number in r3 and r4.
* Load & add the xtime stamp.
*/
- lwz r5,STAMP_XTIME+TSPEC_TV_SEC(r9)
+ lwz r5,STAMP_XTIME_SEC+LOPART(r9)
lwz r6,STAMP_SEC_FRAC(r9)
addc r4,r4,r6
adde r3,r3,r5
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 00c025b..7eadac7 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -144,18 +144,16 @@
__kernel_datapage_offset;
__kernel_get_syscall_map;
-#ifndef CONFIG_PPC_BOOK3S_601
__kernel_gettimeofday;
__kernel_clock_gettime;
__kernel_clock_getres;
__kernel_time;
__kernel_get_tbfreq;
-#endif
__kernel_sync_dicache;
__kernel_sync_dicache_p5;
__kernel_sigtramp32;
__kernel_sigtramp_rt32;
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
__kernel_getcpu;
#endif
diff --git a/arch/powerpc/kernel/vdso64/.gitignore b/arch/powerpc/kernel/vdso64/.gitignore
index 77a0b42..84151a7 100644
--- a/arch/powerpc/kernel/vdso64/.gitignore
+++ b/arch/powerpc/kernel/vdso64/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
vdso64.lds
vdso64.so.dbg
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 32ebb35..dfd34f6 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -17,7 +17,7 @@
asflags-y := -D__VDSO64__ -s
obj-y += vdso64_wrapper.o
-extra-y += vdso64.lds
+targets += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
# Force dependency (incbin is bad)
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index 526f5ba..cab1432 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -8,6 +8,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
.text
@@ -24,14 +25,12 @@
.cfi_startproc
mflr r12
.cfi_register lr,r12
- mr r11,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r10, r0
mtlr r12
- mr r10,r3
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5 /* ensure we get enough */
lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
@@ -48,7 +47,7 @@
lwz r7,CFG_ICACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5
lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index dc84f5a..067247d 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -10,35 +10,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
.text
.global __kernel_datapage_offset;
__kernel_datapage_offset:
.long 0
-V_FUNCTION_BEGIN(__get_datapage)
- .cfi_startproc
- /* We don't want that exposed or overridable as we want other objects
- * to be able to bl directly to here
- */
- .protected __get_datapage
- .hidden __get_datapage
-
- mflr r0
- .cfi_register lr,r0
-
- bcl 20,31,data_page_branch
-data_page_branch:
- mflr r3
- mtlr r0
- addi r3, r3, __kernel_datapage_offset-data_page_branch
- lwz r0,0(r3)
- .cfi_restore lr
- add r3,r0,r3
- blr
- .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
*
@@ -53,7 +31,7 @@
mflr r12
.cfi_register lr,r12
mr r4,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP64
cmpldi cr0,r4,0
@@ -75,7 +53,7 @@
.cfi_startproc
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
ld r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
crclr cr0*4+so
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 81757f0..20f8be4 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -9,6 +9,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
@@ -26,7 +27,7 @@
mr r11,r3 /* r11 holds tv */
mr r10,r4 /* r10 holds tz */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
cmpldi r11,0 /* check if tv is NULL */
beq 2f
lis r7,1000000@ha /* load up USEC_PER_SEC */
@@ -71,7 +72,7 @@
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
ori r7,r7,NSEC_PER_SEC@l
beq cr5,70f
@@ -116,8 +117,8 @@
* CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
* too
*/
- ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
- ld r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+ ld r4,STAMP_XTIME_SEC(r3)
+ ld r5,STAMP_XTIME_NSEC(r3)
bne cr6,75f
/* CLOCK_MONOTONIC_COARSE */
@@ -188,7 +189,7 @@
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
li r3,0
@@ -221,9 +222,9 @@
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
- ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+ ld r4,STAMP_XTIME_SEC(r3)
cmpldi r11,0 /* check if t is NULL */
beq 2f
@@ -268,7 +269,7 @@
mulhdu r6,r6,r5 /* in units of 2^-32 seconds */
/* Add stamp since epoch */
- ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+ ld r4,STAMP_XTIME_SEC(r3)
lwz r5,STAMP_SEC_FRAC(r3)
or r0,r4,r5
or r0,r0,r6
diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S
index a8cc040..2d40675 100644
--- a/arch/powerpc/kernel/vdso64/sigtramp.S
+++ b/arch/powerpc/kernel/vdso64/sigtramp.S
@@ -6,6 +6,7 @@
* Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
* Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
*/
+#include <asm/cache.h> /* IFETCH_ALIGN_BYTES */
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/unistd.h>
@@ -14,21 +15,26 @@
.text
-/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from
- the return address to get an address in the middle of the presumed
- call instruction. Since we don't have a call here, we artificially
- extend the range covered by the unwind info by padding before the
- real start. */
- nop
+/*
+ * __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together
+ * are one function split in two parts. The kernel jumps to the former
+ * and the signal handler indirectly (by blr) returns to the latter.
+ * __kernel_sigtramp_rt64 needs to point to the return address so
+ * glibc can correctly identify the trampoline stack frame.
+ */
.balign 8
+ .balign IFETCH_ALIGN_BYTES
+V_FUNCTION_BEGIN(__kernel_start_sigtramp_rt64)
+.Lsigrt_start:
+ bctrl /* call the handler */
+V_FUNCTION_END(__kernel_start_sigtramp_rt64)
V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
-.Lsigrt_start = . - 4
addi r1, r1, __SIGNAL_FRAMESIZE
li r0,__NR_rt_sigreturn
sc
.Lsigrt_end:
V_FUNCTION_END(__kernel_sigtramp_rt64)
-/* The ".balign 8" above and the following zeros mimic the old stack
+/* The .balign 8 above and the following zeros mimic the old stack
trampoline layout. The last magic value is the ucontext pointer,
chosen in such a way that older libgcc unwind code returns a zero
for a sigcontext pointer. */
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 256fb97..bd120f5 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -150,6 +150,7 @@
__kernel_get_tbfreq;
__kernel_sync_dicache;
__kernel_sync_dicache_p5;
+ __kernel_start_sigtramp_rt64;
__kernel_sigtramp_rt64;
__kernel_getcpu;
__kernel_time;
diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
index 4acd3fb..ae63256 100644
--- a/arch/powerpc/kernel/vecemu.c
+++ b/arch/powerpc/kernel/vecemu.c
@@ -10,6 +10,7 @@
#include <asm/processor.h>
#include <asm/switch_to.h>
#include <linux/uaccess.h>
+#include <asm/inst.h>
/* Functions in vector.S */
extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
@@ -260,21 +261,24 @@
int emulate_altivec(struct pt_regs *regs)
{
- unsigned int instr, i;
+ struct ppc_inst instr;
+ unsigned int i, word;
unsigned int va, vb, vc, vd;
vector128 *vrs;
- if (get_user(instr, (unsigned int __user *) regs->nip))
+ if (get_user_instr(instr, (void __user *)regs->nip))
return -EFAULT;
- if ((instr >> 26) != 4)
+
+ word = ppc_inst_val(instr);
+ if (ppc_inst_primary_opcode(instr) != 4)
return -EINVAL; /* not an altivec instruction */
- vd = (instr >> 21) & 0x1f;
- va = (instr >> 16) & 0x1f;
- vb = (instr >> 11) & 0x1f;
- vc = (instr >> 6) & 0x1f;
+ vd = (word >> 21) & 0x1f;
+ va = (word >> 16) & 0x1f;
+ vb = (word >> 11) & 0x1f;
+ vc = (word >> 6) & 0x1f;
vrs = current->thread.vr_state.vr;
- switch (instr & 0x3f) {
+ switch (word & 0x3f) {
case 10:
switch (vc) {
case 0: /* vaddfp */
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 8eb867d..801dc28 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -67,15 +67,16 @@
#ifdef CONFIG_PPC32
mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
oris r9,r9,MSR_VEC@h
+#ifdef CONFIG_VMAP_STACK
+ tovirt(r5, r5)
+#endif
#else
ld r4,PACACURRENT(r13)
addi r5,r4,THREAD /* Get THREAD */
oris r12,r12,MSR_VEC@h
std r12,_MSR(r1)
#endif
- /* Don't care if r4 overflows, this is desired behaviour */
- lbz r4,THREAD_LOAD_VEC(r5)
- addi r4,r4,1
+ li r4,1
stb r4,THREAD_LOAD_VEC(r5)
addi r6,r5,THREAD_VRSTATE
li r4,1
@@ -86,6 +87,7 @@
REST_32VRS(0,r4,r6)
/* restore registers and return */
blr
+_ASM_NOKPROBE_SYMBOL(load_up_altivec)
/*
* save_altivec(tsk)
@@ -131,7 +133,7 @@
/* enable use of VSX after return */
oris r12,r12,MSR_VSX@h
std r12,_MSR(r1)
- b fast_exception_return
+ b fast_interrupt_return
#endif /* CONFIG_VSX */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 3ea360c..4a1f494 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -6,6 +6,8 @@
#endif
#define BSS_FIRST_SECTIONS *(.bss.prominit)
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN 0
#include <asm/page.h>
#include <asm-generic/vmlinux.lds.h>
@@ -13,27 +15,12 @@
#include <asm/thread_info.h>
#define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT)
-#define ETEXT_ALIGN_SIZE (1 << CONFIG_ETEXT_SHIFT)
ENTRY(_stext)
PHDRS {
- kernel PT_LOAD FLAGS(7); /* RWX */
- notes PT_NOTE FLAGS(0);
- dummy PT_NOTE FLAGS(0);
-
- /* binutils < 2.18 has a bug that makes it misbehave when taking an
- ELF file with all segments at load address 0 as input. This
- happens when running "strip" on vmlinux, because of the AT() magic
- in this linker script. People using GCC >= 4.2 won't run into
- this problem, because the "build-id" support will put some data
- into the "notes" segment (at a non-zero load address).
-
- To work around this, we force some data into both the "dummy"
- segment and the kernel segment, so the dummy segment will get a
- non-zero load address. It's not enough to always create the
- "notes" segment, since if nothing gets assigned to it, its load
- address will be zero. */
+ text PT_LOAD FLAGS(7); /* RWX */
+ note PT_NOTE FLAGS(0);
}
#ifdef CONFIG_PPC64
@@ -77,7 +64,7 @@
#else /* !CONFIG_PPC64 */
HEAD_TEXT
#endif
- } :kernel
+ } :text
__head_end = .;
@@ -127,9 +114,9 @@
__got2_end = .;
#endif /* CONFIG_PPC32 */
- } :kernel
+ } :text
- . = ALIGN(ETEXT_ALIGN_SIZE);
+ . = ALIGN(PAGE_SIZE);
_etext = .;
PROVIDE32 (etext = .);
@@ -159,6 +146,13 @@
}
. = ALIGN(8);
+ __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) {
+ __start___scv_entry_flush_fixup = .;
+ *(__scv_entry_flush_fixup)
+ __stop___scv_entry_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
__start___stf_exit_barrier_fixup = .;
*(__stf_exit_barrier_fixup)
@@ -190,17 +184,6 @@
__stop__btb_flush_fixup = .;
}
#endif
- EXCEPTION_TABLE(0)
-
- NOTES :kernel :notes
-
- /* The dummy segment contents for the bug workaround mentioned above
- near PHDRS. */
- .dummy : AT(ADDR(.dummy) - LOAD_OFFSET) {
- LONG(0)
- LONG(0)
- LONG(0)
- } :kernel :dummy
/*
* Init sections discarded at runtime
@@ -221,7 +204,7 @@
#ifdef CONFIG_PPC64
*(.tramp.ftrace.init);
#endif
- } :kernel
+ } :text
/* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
@@ -285,6 +268,7 @@
*(.dynamic)
}
.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
+ .gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) }
.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
{
@@ -352,7 +336,7 @@
#endif
/* The initial task and kernel stack */
- INIT_TASK_DATA_SECTION(THREAD_SIZE)
+ INIT_TASK_DATA_SECTION(THREAD_ALIGN)
.data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) {
PAGE_ALIGNED_DATA(PAGE_SIZE)
@@ -388,8 +372,8 @@
PROVIDE32 (end = .);
STABS_DEBUG
-
DWARF_DEBUG
+ ELF_DETAILS
DISCARDS
/DISCARD/ : {
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index af3c15a..75b2a6c 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -132,6 +132,10 @@
{
cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask);
cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask);
+ /*
+ * See wd_smp_clear_cpu_pending()
+ */
+ smp_mb();
if (cpumask_empty(&wd_smp_cpus_pending)) {
wd_smp_last_reset_tb = tb;
cpumask_andnot(&wd_smp_cpus_pending,
@@ -217,13 +221,44 @@
cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck);
wd_smp_unlock(&flags);
+ } else {
+ /*
+ * The last CPU to clear pending should have reset the
+ * watchdog so we generally should not find it empty
+ * here if our CPU was clear. However it could happen
+ * due to a rare race with another CPU taking the
+ * last CPU out of the mask concurrently.
+ *
+ * We can't add a warning for it. But just in case
+ * there is a problem with the watchdog that is causing
+ * the mask to not be reset, try to kick it along here.
+ */
+ if (unlikely(cpumask_empty(&wd_smp_cpus_pending)))
+ goto none_pending;
}
return;
}
+
cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+
+ /*
+ * Order the store to clear pending with the load(s) to check all
+ * words in the pending mask to check they are all empty. This orders
+ * with the same barrier on another CPU. This prevents two CPUs
+ * clearing the last 2 pending bits, but neither seeing the other's
+ * store when checking if the mask is empty, and missing an empty
+ * mask, which ends with a false positive.
+ */
+ smp_mb();
if (cpumask_empty(&wd_smp_cpus_pending)) {
unsigned long flags;
+none_pending:
+ /*
+ * Double check under lock because more than one CPU could see
+ * a clear mask with the lockless check after clearing their
+ * pending bits.
+ */
wd_smp_lock(&flags);
if (cpumask_empty(&wd_smp_cpus_pending)) {
wd_smp_last_reset_tb = tb;
@@ -314,8 +349,12 @@
{
unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
int cpu = smp_processor_id();
- u64 tb = get_tb();
+ u64 tb;
+ if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+ return;
+
+ tb = get_tb();
if (tb - per_cpu(wd_timer_tb, cpu) >= ticks) {
per_cpu(wd_timer_tb, cpu) = tb;
wd_smp_clear_cpu_pending(cpu, tb);