* [PATCH v6 29/39] powerpc/64: context tracking move to interrupt wrappers
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
This moves exception_enter/exit calls to wrapper functions for
synchronous interrupts. More interrupt handlers are covered by
this than previously.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 9 ++++
arch/powerpc/kernel/traps.c | 74 ++++++---------------------
arch/powerpc/mm/book3s64/hash_utils.c | 3 --
arch/powerpc/mm/fault.c | 9 +---
4 files changed, 27 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 488bdd5bd922..e65ce3e2b071 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,10 +7,16 @@
#include <asm/ftrace.h>
struct interrupt_state {
+#ifdef CONFIG_PPC64
+ enum ctx_state ctx_state;
+#endif
};
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ state->ctx_state = exception_enter();
+#endif
}
/*
@@ -29,6 +35,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ exception_exit(state->ctx_state);
+#endif
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 076e5ff75cf7..d3892f402b0e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1087,41 +1087,28 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_iabr_match(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(RunModeException)
@@ -1131,8 +1118,6 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
- enum ctx_state prev_state = exception_enter();
-
clear_single_step(regs);
clear_br_trace(regs);
@@ -1141,14 +1126,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
if (notify_die(DIE_SSTEP, "single_step", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_sstep(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(single_step_exception);
@@ -1476,7 +1458,6 @@ static inline int emulate_math(struct pt_regs *regs) { return -1; }
DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
- enum ctx_state prev_state = exception_enter();
unsigned int reason = get_reason(regs);
/* We can now get here via a FP Unavailable exception if the core
@@ -1485,22 +1466,22 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (reason & REASON_FP) {
/* IEEE FP exception */
parse_fpe(regs);
- goto bail;
+ return;
}
if (reason & REASON_TRAP) {
unsigned long bugaddr;
/* Debugger is first in line to stop recursive faults in
* rcu_lock, notify_die, or atomic_notifier_call_chain */
if (debugger_bpt(regs))
- goto bail;
+ return;
if (kprobe_handler(regs))
- goto bail;
+ return;
/* trap exception */
if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
== NOTIFY_STOP)
- goto bail;
+ return;
bugaddr = regs->nip;
/*
@@ -1512,10 +1493,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (!(regs->msr & MSR_PR) && /* not user-mode */
report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
regs->nip += 4;
- goto bail;
+ return;
}
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
- goto bail;
+ return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (reason & REASON_TM) {
@@ -1536,7 +1517,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
*/
if (user_mode(regs)) {
_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
- goto bail;
+ return;
} else {
printk(KERN_EMERG "Unexpected TM Bad Thing exception "
"at %lx (msr 0x%lx) tm_scratch=%llx\n",
@@ -1567,7 +1548,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
* pattern to occurrences etc. -dgibson 31/Mar/2003
*/
if (!emulate_math(regs))
- goto bail;
+ return;
/* Try to emulate it if we should. */
if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1575,10 +1556,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
case 0:
regs->nip += 4;
emulate_single_step(regs);
- goto bail;
+ return;
case -EFAULT:
_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
- goto bail;
+ return;
}
}
@@ -1587,9 +1568,6 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
else
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(program_check_exception);
@@ -1606,14 +1584,12 @@ NOKPROBE_SYMBOL(emulation_assist_interrupt);
DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
- enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
unsigned long reason;
interrupt_cond_local_irq_enable(regs);
reason = get_reason(regs);
-
if (reason & REASON_BOUNDARY) {
sig = SIGBUS;
code = BUS_ADRALN;
@@ -1621,7 +1597,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
}
if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
- goto bail;
+ return;
/* we don't implement logging of alignment exceptions */
if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -1631,7 +1607,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
/* skip over emulated instruction */
regs->nip += inst_length(reason);
emulate_single_step(regs);
- goto bail;
+ return;
}
/* Operand address was bad */
@@ -1647,9 +1623,6 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
_exception(sig, regs, code, regs->dar);
else
bad_page_fault(regs, sig);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(StackOverflow)
@@ -1663,41 +1636,28 @@ DEFINE_INTERRUPT_HANDLER(StackOverflow)
DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
- enum ctx_state prev_state = exception_enter();
-
die("Kernel stack overflow", regs, SIGSEGV);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (user_mode(regs)) {
/* A user program has executed an altivec instruction,
but this kernel doesn't support altivec. */
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- goto bail;
+ return;
}
printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index b7b78aeea3eb..176f05ad3065 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1513,7 +1513,6 @@ EXPORT_SYMBOL_GPL(hash_page);
DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
{
- enum ctx_state prev_state = exception_enter();
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1562,8 +1561,6 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
err = 0;
}
- exception_exit(prev_state);
-
return err;
}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 620ff623b2c6..24dcaea2b512 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -564,14 +564,7 @@ NOKPROBE_SYMBOL(__do_page_fault);
DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
{
- enum ctx_state prev_state = exception_enter();
- long err;
-
- err = __do_page_fault(regs);
-
- exception_exit(prev_state);
-
- return err;
+ return __do_page_fault(regs);
}
NOKPROBE_SYMBOL(do_page_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 30/39] powerpc/64: add context tracking to asynchronous interrupts
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
Previously context tracking was not done for asynchronous interrupts,
(those that run in interrupt context), and if those would cause a
reschedule when they exit, then scheduling functions (schedule_user,
preempt_schedule_irq) call exception_enter/exit to fix this up and
exit user context.
This is a hack we would like to get away from, so do context tracking
for asynchronous interrupts too.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e65ce3e2b071..f7f64c3c514d 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -42,10 +42,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_enter_prepare(regs, state);
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_exit_prepare(regs, state);
}
struct interrupt_nmi_state {
--
2.23.0
^ permalink raw reply related
* [PATCH v6 31/39] powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
Move irq_enter/irq_exit into asynchronous interrupt handler wrappers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
arch/powerpc/kernel/dbell.c | 3 +--
arch/powerpc/kernel/irq.c | 4 ----
arch/powerpc/kernel/tau_6xx.c | 3 ---
arch/powerpc/kernel/time.c | 4 ++--
arch/powerpc/kernel/traps.c | 10 +++-------
6 files changed, 8 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index f7f64c3c514d..5a1395499508 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -43,10 +43,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
interrupt_enter_prepare(regs, state);
+ irq_enter();
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ irq_exit();
interrupt_exit_prepare(regs, state);
}
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 6a7ecfca5c3b..5545c9cd17c1 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -23,7 +23,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
trace_doorbell_entry(regs);
ppc_msgsync();
@@ -36,7 +35,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
smp_ipi_demux_relaxed(); /* already performed the barrier */
trace_doorbell_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
}
#else /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2055d204d08e..681abb7c0507 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -641,8 +641,6 @@ void __do_irq(struct pt_regs *regs)
{
unsigned int irq;
- irq_enter();
-
trace_irq_entry(regs);
/*
@@ -662,8 +660,6 @@ void __do_irq(struct pt_regs *regs)
generic_handle_irq(irq);
trace_irq_exit(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 46b2e5de4ef5..d864f07bab74 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -104,12 +104,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
{
int cpu = smp_processor_id();
- irq_enter();
tau[cpu].interrupts++;
TAUupdate(cpu);
-
- irq_exit();
}
#endif /* CONFIG_TAU_INT */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 435a251247ed..2177defb7884 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -610,7 +610,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
#endif
old_regs = set_irq_regs(regs);
- irq_enter();
+
trace_timer_interrupt_entry(regs);
if (test_irq_work_pending()) {
@@ -635,7 +635,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
}
trace_timer_interrupt_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
}
EXPORT_SYMBOL(timer_interrupt);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index d3892f402b0e..f37583d57442 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -801,7 +801,9 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
* do_exit() checks for in_interrupt() and panics in that case, so
* exit the irq/nmi before calling die.
*/
- if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ irq_exit();
+ else
nmi_exit();
die(str, regs, err);
}
@@ -1061,7 +1063,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
struct pt_regs *old_regs;
old_regs = set_irq_regs(regs);
- irq_enter();
#ifdef CONFIG_VSX
/* Real mode flagged P9 special emu is needed */
@@ -1081,7 +1082,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
if (ppc_md.handle_hmi_exception)
ppc_md.handle_hmi_exception(regs);
- irq_exit();
set_irq_regs(old_regs);
}
@@ -1899,13 +1899,9 @@ DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
- irq_enter();
-
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
--
2.23.0
^ permalink raw reply related
* [PATCH v6 32/39] powerpc/64s: move context tracking exit to interrupt exit path
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
The interrupt handler wrapper functions are not the ideal place to
maintain context tracking because after they return, the low level exit
code must then determine if there are interrupts to replay, or if the
task should be preempted, etc. Those paths (e.g., schedule_user) include
their own exception_enter/exit pairs to fix this up but it's a bit hacky
(see schedule_user() comments).
Ideally context tracking will go to user mode only when there are no
more interrupts or context switches or other exit processing work to
handle.
64e can not do this because it does not use the C interrupt exit code.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 34 +++++++++++++++++++++++++---
arch/powerpc/kernel/syscall_64.c | 9 ++++++++
2 files changed, 40 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5a1395499508..1c966e47b36f 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,16 +7,30 @@
#include <asm/ftrace.h>
struct interrupt_state {
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
enum ctx_state ctx_state;
#endif
};
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
state->ctx_state = exception_enter();
#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (user_mode(regs)) {
+ CT_WARN_ON(ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+ } else {
+ /*
+ * CT_WARN_ON comes here via program_check_exception,
+ * so avoid recursion.
+ */
+ if (TRAP(regs) != 0x700)
+ CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+ }
+#endif
}
/*
@@ -35,9 +49,23 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
exception_exit(state->ctx_state);
#endif
+
+ /*
+ * Book3S exits to user via interrupt_exit_user_prepare(), which does
+ * context tracking, which is a cleaner way to handle PREEMPT=y
+ * and avoid context entry/exit in e.g., preempt_schedule_irq()),
+ * which is likely to be where the core code wants to end up.
+ *
+ * The above comment explains why we can't do the
+ *
+ * if (user_mode(regs))
+ * user_exit_irqoff();
+ *
+ * sequence here.
+ */
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index d7d256a7a41f..42f0ad4b2fbb 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -305,6 +305,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
BUG_ON(!(regs->msr & MSR_PR));
BUG_ON(!FULL_REGS(regs));
BUG_ON(regs->softe != IRQS_ENABLED);
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
@@ -347,7 +348,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
}
}
+ user_enter_irqoff();
if (unlikely(!prep_irq_for_enabled_exit(true))) {
+ user_exit_irqoff();
local_irq_enable();
local_irq_disable();
goto again;
@@ -392,6 +395,12 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
unrecoverable_exception(regs);
BUG_ON(regs->msr & MSR_PR);
BUG_ON(!FULL_REGS(regs));
+ /*
+ * CT_WARN_ON comes here via program_check_exception,
+ * so avoid recursion.
+ */
+ if (TRAP(regs) != 0x700)
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
amr = kuap_get_and_check_amr();
--
2.23.0
^ permalink raw reply related
* [PATCH v6 33/39] powerpc/64s: reconcile interrupts in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 15 +++++++++++----
arch/powerpc/kernel/exceptions-64s.S | 26 --------------------------
2 files changed, 11 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 1c966e47b36f..e96d215f518a 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -14,11 +14,14 @@ struct interrupt_state {
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC_BOOK3E_64
- state->ctx_state = exception_enter();
-#endif
-
+ /*
+ * Book3E reconciles irq soft mask in asm
+ */
#ifdef CONFIG_PPC_BOOK3S_64
+ if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
+ trace_hardirqs_off();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
@@ -31,6 +34,10 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
}
#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ state->ctx_state = exception_enter();
+#endif
}
/*
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index fe33197ea8fb..39630b3f78b0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -139,7 +139,6 @@ 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) \
@@ -203,9 +202,6 @@ do_define_int n
.ifndef ISTACK
ISTACK=1
.endif
- .ifndef IRECONCILE
- IRECONCILE=1
- .endif
.ifndef IKUAP
IKUAP=1
.endif
@@ -653,10 +649,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.if ISTACK
ACCOUNT_STOLEN_TIME
.endif
-
- .if IRECONCILE
- RECONCILE_IRQ_STATE(r10, r11)
- .endif
.endm
/*
@@ -935,7 +927,6 @@ INT_DEFINE_BEGIN(system_reset)
*/
ISET_RI=0
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
INT_DEFINE_END(system_reset)
@@ -1123,7 +1114,6 @@ INT_DEFINE_BEGIN(machine_check_early)
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)
@@ -1483,7 +1473,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(data_access_slb)
IVEC=0x380
IAREA=PACA_EXSLB
- IRECONCILE=0
IDAR=1
IKVM_SKIP=1
IKVM_REAL=1
@@ -1510,7 +1499,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1568,7 +1556,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(instruction_access_slb)
IVEC=0x480
IAREA=PACA_EXSLB
- IRECONCILE=0
IISIDE=1
IDAR=1
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -1597,7 +1584,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1757,7 +1743,6 @@ EXC_COMMON_BEGIN(program_check_common)
*/
INT_DEFINE_BEGIN(fp_unavailable)
IVEC=0x800
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -1772,7 +1757,6 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
EXC_COMMON_BEGIN(fp_unavailable_common)
GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
0: trap
@@ -1791,7 +1775,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
b interrupt_return
@@ -1856,7 +1839,6 @@ INT_DEFINE_BEGIN(hdecrementer)
IVEC=0x980
IHSRR=1
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
IKVM_VIRT=1
INT_DEFINE_END(hdecrementer)
@@ -2230,7 +2212,6 @@ INT_DEFINE_BEGIN(hmi_exception_early)
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)
@@ -2404,7 +2385,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
*/
INT_DEFINE_BEGIN(altivec_unavailable)
IVEC=0xf20
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2434,7 +2414,6 @@ BEGIN_FTR_SECTION
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
b interrupt_return
@@ -2442,7 +2421,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b interrupt_return
@@ -2458,7 +2436,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
*/
INT_DEFINE_BEGIN(vsx_unavailable)
IVEC=0xf40
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2487,7 +2464,6 @@ BEGIN_FTR_SECTION
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
b interrupt_return
@@ -2495,7 +2471,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
b interrupt_return
@@ -2830,7 +2805,6 @@ EXC_VIRT_NONE(0x5800, 0x100)
INT_DEFINE_BEGIN(soft_nmi)
IVEC=0x900
ISTACK=0
- IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
INT_DEFINE_END(soft_nmi)
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v6 34/39] powerpc/64: move account_stolen_time into its own function
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
This will be used by interrupt entry as well.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/cputime.h | 14 ++++++++++++++
arch/powerpc/kernel/syscall_64.c | 10 +---------
2 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index ed75d1c318e3..504f7fe6711a 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -87,6 +87,17 @@ static notrace inline void account_cpu_user_exit(void)
acct->starttime_user = tb;
}
+static notrace inline void account_stolen_time(void)
+{
+#ifdef CONFIG_PPC_SPLPAR
+ if (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
+}
#endif /* __KERNEL__ */
#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
@@ -96,5 +107,8 @@ static inline void account_cpu_user_entry(void)
static inline void account_cpu_user_exit(void)
{
}
+static notrace inline void account_stolen_time(void)
+{
+}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 42f0ad4b2fbb..32f72965da26 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -69,15 +69,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
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
+ account_stolen_time();
/*
* This is not required for the syscall exit path, but makes the
--
2.23.0
^ permalink raw reply related
* [PATCH v6 35/39] powerpc/64: entry cpu time accounting in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new interrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 6 ++++++
arch/powerpc/include/asm/ppc_asm.h | 24 ------------------------
arch/powerpc/kernel/exceptions-64e.S | 1 -
arch/powerpc/kernel/exceptions-64s.S | 5 -----
4 files changed, 6 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e96d215f518a..ca8e08b18a16 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -4,6 +4,7 @@
#include <linux/context_tracking.h>
#include <linux/hardirq.h>
+#include <asm/cputime.h>
#include <asm/ftrace.h>
struct interrupt_state {
@@ -25,6 +26,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
+
+ account_cpu_user_entry();
+ account_stolen_time();
} else {
/*
* CT_WARN_ON comes here via program_check_exception,
@@ -37,6 +41,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
#ifdef CONFIG_PPC_BOOK3E_64
state->ctx_state = exception_enter();
+ if (user_mode(regs))
+ account_cpu_user_entry();
#endif
}
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cc1bca571332..3dceb64fc9af 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -25,7 +25,6 @@
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)
#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
-#define ACCOUNT_STOLEN_TIME
#else
#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb) \
MFTB(ra); /* get timebase */ \
@@ -44,29 +43,6 @@
PPC_LL ra, ACCOUNT_SYSTEM_TIME(ptr); \
add ra,ra,rb; /* add on to system time */ \
PPC_STL ra, ACCOUNT_SYSTEM_TIME(ptr)
-
-#ifdef CONFIG_PPC_SPLPAR
-#define ACCOUNT_STOLEN_TIME \
-BEGIN_FW_FTR_SECTION; \
- beq 33f; \
- /* from user - 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 cr1,r11,r10; \
- beq+ cr1,33f; \
- bl accumulate_stolen_time; \
- ld r12,_MSR(r1); \
- andi. r10,r12,MSR_PR; /* Restore cr0 (coming from user) */ \
-33: \
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-
-#else /* CONFIG_PPC_SPLPAR */
-#define ACCOUNT_STOLEN_TIME
-
-#endif /* CONFIG_PPC_SPLPAR */
-
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
/*
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 003999c7836c..e8eb9992a270 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -398,7 +398,6 @@ exc_##n##_common: \
std r10,_NIP(r1); /* save SRR0 to stackframe */ \
std r11,_MSR(r1); /* save SRR1 to stackframe */ \
beq 2f; /* if from kernel mode */ \
- ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */ \
2: ld r3,excf+EX_R10(r13); /* get back r10 */ \
ld r4,excf+EX_R11(r13); /* get back r11 */ \
mfspr r5,scratch; /* get back r13 */ \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 39630b3f78b0..94b89ea123f3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -577,7 +577,6 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
kuap_save_amr_and_lock r9, r10, cr1, cr0
.endif
beq 101f /* if from kernel mode */
- ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
BEGIN_FTR_SECTION
ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
std r9,_PPR(r1)
@@ -645,10 +644,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r11,exception_marker@toc(r2)
std r10,RESULT(r1) /* clear regs->result */
std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
-
- .if ISTACK
- ACCOUNT_STOLEN_TIME
- .endif
.endm
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v6 36/39] powerpc: move NMI entry/exit code into wrapper
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
This moves the common NMI entry and exit code into the interrupt handler
wrappers.
This changes the behaviour of soft-NMI (watchdog) and HMI interrupts, and
also MCE interrupts on 64e, by adding missing parts of the NMI entry to
them.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 24 +++++++++++++++++++
arch/powerpc/kernel/mce.c | 11 ---------
arch/powerpc/kernel/traps.c | 35 +++++-----------------------
arch/powerpc/kernel/watchdog.c | 10 ++++----
4 files changed, 34 insertions(+), 46 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index ca8e08b18a16..879a0b2705d6 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -94,14 +94,38 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
}
struct interrupt_nmi_state {
+#ifdef CONFIG_PPC64
+ u8 ftrace_enabled;
+#endif
};
static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
+#ifdef CONFIG_PPC64
+ state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+ this_cpu_set_ftrace_enabled(0);
+#endif
+
+ /*
+ * Do not use nmi_enter() for pseries hash guest taking a real-mode
+ * NMI because not everything it touches is within the RMA limit.
+ */
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+ !firmware_has_feature(FW_FEATURE_LPAR) ||
+ radix_enabled() || (mfmsr() & MSR_DR))
+ nmi_enter();
}
static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+ !firmware_has_feature(FW_FEATURE_LPAR) ||
+ radix_enabled() || (mfmsr() & MSR_DR))
+ nmi_exit();
+
+#ifdef CONFIG_PPC64
+ this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+#endif
}
/**
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 54269947113d..51456217ec40 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -592,12 +592,6 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
{
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);
@@ -607,11 +601,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
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;
}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f37583d57442..9e5574756689 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -435,11 +435,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
{
unsigned long hsrr0, hsrr1;
bool saved_hsrrs = false;
- u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
- this_cpu_set_ftrace_enabled(0);
-
- nmi_enter();
/*
* System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -514,10 +509,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
mtspr(SPRN_HSRR1, hsrr1);
}
- nmi_exit();
-
- this_cpu_set_ftrace_enabled(ftrace_enabled);
-
/* What should we do here? We could issue a shutdown or hard reset. */
return 0;
@@ -809,6 +800,12 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
}
NOKPROBE_SYMBOL(die_mce);
+/*
+ * 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).
+ */
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
#else
@@ -817,20 +814,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
{
int recover = 0;
- /*
- * 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);
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -862,8 +845,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
if (!(regs->msr & MSR_RI))
die_mce("Unrecoverable Machine check", regs, SIGBUS);
- if (nmi) nmi_exit();
-
#ifdef CONFIG_PPC_BOOK3S_64
return;
#else
@@ -1885,14 +1866,10 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
#ifdef CONFIG_PPC64
DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
{
- nmi_enter();
-
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
- nmi_exit();
-
return 0;
}
#endif
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 824b9376ac35..dc39534836a3 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -254,11 +254,12 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
int cpu = raw_smp_processor_id();
u64 tb;
+ /* should only arrive from kernel, with irqs disabled */
+ WARN_ON_ONCE(!arch_irq_disabled_regs(regs));
+
if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
return 0;
- nmi_enter();
-
__this_cpu_inc(irq_stat.soft_nmi_irqs);
tb = get_tb();
@@ -266,7 +267,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
wd_smp_lock(&flags);
if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
wd_smp_unlock(&flags);
- goto out;
+ return 0;
}
set_cpu_stuck(cpu, tb);
@@ -290,9 +291,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
if (wd_panic_timeout_tb < 0x7fffffff)
mtspr(SPRN_DEC, wd_panic_timeout_tb);
-out:
- nmi_exit();
-
return 0;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v6 37/39] powerpc/64s: move NMI soft-mask handling to C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
Saving and restoring soft-mask state can now be done in C using the
interrupt handler wrapper functions.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 26 ++++++++++++
arch/powerpc/kernel/exceptions-64s.S | 60 ----------------------------
2 files changed, 26 insertions(+), 60 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 879a0b2705d6..5f4e304a98d9 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -95,6 +95,10 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
struct interrupt_nmi_state {
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+ u8 irq_soft_mask;
+ u8 irq_happened;
+#endif
u8 ftrace_enabled;
#endif
};
@@ -102,6 +106,21 @@ struct interrupt_nmi_state {
static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+ state->irq_soft_mask = local_paca->irq_soft_mask;
+ state->irq_happened = local_paca->irq_happened;
+
+ /*
+ * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
+ * the right thing, and set IRQ_HARD_DIS. We do not want to reconcile
+ * because that goes through irq tracing which we don't want in NMI.
+ */
+ local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /* Don't do any per-CPU operations until interrupt state is fixed */
+ state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+#endif
state->ftrace_enabled = this_cpu_get_ftrace_enabled();
this_cpu_set_ftrace_enabled(0);
#endif
@@ -125,6 +144,13 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
#ifdef CONFIG_PPC64
this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Check we didn't change the pending interrupt mask. */
+ WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
+ local_paca->irq_happened = state->irq_happened;
+ local_paca->irq_soft_mask = state->irq_soft_mask;
+#endif
#endif
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 94b89ea123f3..2fca2bad6b02 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1008,20 +1008,6 @@ EXC_COMMON_BEGIN(system_reset_common)
ld r1,PACA_NMI_EMERG_SP(r13)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY system_reset
- /*
- * 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 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,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
addi r3,r1,STACK_FRAME_OVERHEAD
bl system_reset_exception
@@ -1037,14 +1023,6 @@ EXC_COMMON_BEGIN(system_reset_common)
subi r10,r10,1
sth r10,PACA_IN_NMI(r13)
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
kuap_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
@@ -1190,30 +1168,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
li r10,MSR_RI
mtmsrd r10,1
- /*
- * 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
@@ -2818,17 +2777,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
subi r1,r1,INT_FRAME_SIZE
__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
@@ -2836,14 +2784,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
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_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS hsrr=0
RFI_TO_KERNEL
--
2.23.0
^ permalink raw reply related
* [PATCH v6 38/39] powerpc/64s: runlatch interrupt handling in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 7 +++++++
arch/powerpc/kernel/exceptions-64s.S | 18 ------------------
2 files changed, 7 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5f4e304a98d9..5e3b290bf3ae 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -6,6 +6,7 @@
#include <linux/hardirq.h>
#include <asm/cputime.h>
#include <asm/ftrace.h>
+#include <asm/runlatch.h>
struct interrupt_state {
#ifdef CONFIG_PPC_BOOK3E_64
@@ -83,6 +84,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_CTRL) &&
+ !test_thread_local_flags(_TLF_RUNLATCH))
+ __ppc64_runlatch_on();
+#endif
+
interrupt_enter_prepare(regs, state);
irq_enter();
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2fca2bad6b02..27351276c54b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -692,14 +692,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r1,GPR1(r1)
.endm
-#define RUNLATCH_ON \
-BEGIN_FTR_SECTION \
- ld r3, PACA_THREAD_INFO(r13); \
- ld r4,TI_LOCAL_FLAGS(r3); \
- andi. r0,r4,_TLF_RUNLATCH; \
- beql ppc64_runlatch_on_trampoline; \
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-
/*
* When the idle code in power4_idle puts the CPU into NAP mode,
* it has to do so in a loop, and relies on the external interrupt
@@ -1585,7 +1577,6 @@ EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
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
@@ -1771,7 +1762,6 @@ EXC_VIRT_END(decrementer, 0x4900, 0x80)
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl timer_interrupt
b interrupt_return
@@ -1857,7 +1847,6 @@ EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2212,7 +2201,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
@@ -2242,7 +2230,6 @@ EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2276,7 +2263,6 @@ EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
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
@@ -2323,7 +2309,6 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
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
@@ -3057,9 +3042,6 @@ kvmppc_skip_Hinterrupt:
* come here.
*/
-EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline)
- b __ppc64_runlatch_on
-
USE_FIXED_SECTION(virt_trampolines)
/*
* All code below __end_interrupts is treated as soft-masked. If
--
2.23.0
^ permalink raw reply related
* [PATCH v6 39/39] powerpc/64s: power4 nap fixup in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 15 +++++++++
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/include/asm/thread_info.h | 6 ++++
arch/powerpc/kernel/exceptions-64s.S | 45 --------------------------
arch/powerpc/kernel/idle_book3s.S | 4 +++
5 files changed, 26 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5e3b290bf3ae..c48ded0df2bc 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -8,6 +8,16 @@
#include <asm/ftrace.h>
#include <asm/runlatch.h>
+static inline void nap_adjust_return(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_970_NAP
+ if (unlikely(test_thread_local_flags(_TLF_NAPPING))) {
+ clear_thread_local_flags(_TLF_NAPPING);
+ regs->nip = (unsigned long)power4_idle_nap_return;
+ }
+#endif
+}
+
struct interrupt_state {
#ifdef CONFIG_PPC_BOOK3E_64
enum ctx_state ctx_state;
@@ -98,6 +108,9 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
{
irq_exit();
interrupt_exit_prepare(regs, state);
+
+ /* Adjust at exit so the main handler sees the true NIA */
+ nap_adjust_return(regs);
}
struct interrupt_nmi_state {
@@ -149,6 +162,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
radix_enabled() || (mfmsr() & MSR_DR))
nmi_exit();
+ nap_adjust_return(regs);
+
#ifdef CONFIG_PPC64
this_cpu_set_ftrace_enabled(state->ftrace_enabled);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 8acc3590c971..eedc3c775141 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -393,6 +393,7 @@ extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
#ifdef CONFIG_PPC_970_NAP
extern void power4_idle_nap(void);
+void power4_idle_nap_return(void);
#endif
extern unsigned long cpuidle_disable;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 386d576673a1..bf137151100b 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -152,6 +152,12 @@ void arch_setup_new_exec(void);
#ifndef __ASSEMBLY__
+static inline void clear_thread_local_flags(unsigned int flags)
+{
+ struct thread_info *ti = current_thread_info();
+ ti->local_flags &= ~flags;
+}
+
static inline bool test_thread_local_flags(unsigned int flags)
{
struct thread_info *ti = current_thread_info();
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 27351276c54b..5478ffa85603 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -692,25 +692,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r1,GPR1(r1)
.endm
-/*
- * When the idle code in power4_idle puts the CPU into NAP mode,
- * it has to do so in a loop, and relies on the external interrupt
- * and decrementer interrupt entry code to get it out of the loop.
- * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
- * to signal that it is in the loop and needs help to get out.
- */
-#ifdef CONFIG_PPC_970_NAP
-#define FINISH_NAP \
-BEGIN_FTR_SECTION \
- ld r11, PACA_THREAD_INFO(r13); \
- ld r9,TI_LOCAL_FLAGS(r11); \
- andi. r10,r9,_TLF_NAPPING; \
- bnel power4_fixup_nap; \
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
-#else
-#define FINISH_NAP
-#endif
-
/*
* There are a few constraints to be concerned with.
* - Real mode exceptions code/data must be located at their physical location.
@@ -1248,7 +1229,6 @@ EXC_COMMON_BEGIN(machine_check_common)
*/
GEN_COMMON machine_check
- FINISH_NAP
/* Enable MSR_RI when finished with PACA_EXMC */
li r10,MSR_RI
mtmsrd r10,1
@@ -1576,7 +1556,6 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
EXC_COMMON_BEGIN(hardware_interrupt_common)
GEN_COMMON hardware_interrupt
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -1761,7 +1740,6 @@ EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
EXC_VIRT_END(decrementer, 0x4900, 0x80)
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl timer_interrupt
b interrupt_return
@@ -1846,7 +1824,6 @@ EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2200,7 +2177,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
@@ -2229,7 +2205,6 @@ EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2262,7 +2237,6 @@ EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
EXC_COMMON_BEGIN(h_virt_irq_common)
GEN_COMMON h_virt_irq
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -2308,7 +2282,6 @@ EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
b interrupt_return
@@ -3059,24 +3032,6 @@ USE_FIXED_SECTION(virt_trampolines)
__end_interrupts:
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)
- LOAD_REG_ADDR(r10, power4_idle_nap_return)
- std r10,_NIP(r1)
- blr
-
-power4_idle_nap_return:
- blr
-#endif
-
CLOSE_FIXED_SECTION(real_vectors);
CLOSE_FIXED_SECTION(real_trampolines);
CLOSE_FIXED_SECTION(virt_vectors);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 22f249b6f58d..27d2e6a72ec9 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -201,4 +201,8 @@ _GLOBAL(power4_idle_nap)
mtmsrd r7
isync
b 1b
+
+ .globl power4_idle_nap_return
+power4_idle_nap_return:
+ blr
#endif
--
2.23.0
^ permalink raw reply related
* Re: [PATCH v2 0/7] Rid W=1 warnings in Ethernet
From: Jakub Kicinski @ 2021-01-15 16:56 UTC (permalink / raw)
To: Lee Jones
Cc: Paul Durrant, Kurt Kanzenbach, Alexei Starovoitov, linux-kernel,
Peter Cammaert, Paul Mackerras, Sukadev Bhattiprolu, Wei Liu,
Daniel Borkmann, Utz Bacher, John Fastabend, Santiago Leon,
xen-devel, Grygorii Strashko, Thomas Falcon,
Jesper Dangaard Brouer, Jens Osterkamp, Rusty Russell,
Daris A Nevil, Lijun Pan, Ivan Khoronzhuk, Nicolas Pitre,
Geoff Levand, netdev, Gustavo A. R. Silva, Erik Stahlman,
John Allen, Dany Madden, bpf, linuxppc-dev, David S. Miller,
Russell King
In-Reply-To: <20210115133848.GK3975472@dell>
On Fri, 15 Jan 2021 13:38:48 +0000 Lee Jones wrote:
> Okay, so what would you like me to do? Would you like me to re-submit
> the set based only on net-next
Yes, rebase your patches on net-next, recheck everything builds okay
and resubmit. You should always develop against the tree that will
merge your patches. I appreciate for your janitorial work using
linux-next is more expedient, but as you can see it causes trouble,
this is not the first time your patches don't apply to net-next IIRC.
^ permalink raw reply
* Re: [PATCH v6 07/39] powerpc: bad_page_fault get registers from regs
From: Christophe Leroy @ 2021-01-15 17:09 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev
In-Reply-To: <20210115165012.1260253-8-npiggin@gmail.com>
Le 15/01/2021 à 17:49, Nicholas Piggin a écrit :
> Similar to the previous patch this makes interrupt handler function
> types more regular so they can be wrapped with the next patch.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> arch/powerpc/include/asm/bug.h | 5 +++--
> arch/powerpc/kernel/entry_32.S | 3 +--
> arch/powerpc/kernel/exceptions-64e.S | 3 +--
> arch/powerpc/kernel/exceptions-64s.S | 4 +---
> arch/powerpc/kernel/traps.c | 2 +-
> arch/powerpc/mm/book3s64/hash_utils.c | 4 ++--
> arch/powerpc/mm/book3s64/slb.c | 2 +-
> arch/powerpc/mm/fault.c | 13 ++++++++++---
> arch/powerpc/platforms/8xx/machine_check.c | 2 +-
> 9 files changed, 21 insertions(+), 17 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
> index f7827e993196..8f09ddae9305 100644
> --- a/arch/powerpc/include/asm/bug.h
> +++ b/arch/powerpc/include/asm/bug.h
> @@ -112,8 +112,9 @@
>
> struct pt_regs;
> long do_page_fault(struct pt_regs *);
> -extern void bad_page_fault(struct pt_regs *, unsigned long, int);
> -void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig);
> +void bad_page_fault(struct pt_regs *, int);
> +void __bad_page_fault(struct pt_regs *regs, int sig);
> +void do_bad_page_fault_segv(struct pt_regs *regs);
What is that do_bad_page_fault_segv() ? Shouldn't it be in a separate patch ?
> extern void _exception(int, struct pt_regs *, int, unsigned long);
> extern void _exception_pkey(struct pt_regs *, unsigned long, int);
> extern void die(const char *, struct pt_regs *, long);
> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
> index d6ea3f2d6cc0..b102b40c4988 100644
> --- a/arch/powerpc/kernel/entry_32.S
> +++ b/arch/powerpc/kernel/entry_32.S
> @@ -672,9 +672,8 @@ handle_page_fault:
> lwz r0,_TRAP(r1)
> clrrwi r0,r0,1
> stw r0,_TRAP(r1)
> - mr r5,r3
> + mr r4,r3 /* err arg for bad_page_fault */
> addi r3,r1,STACK_FRAME_OVERHEAD
> - lwz r4,_DAR(r1)
> bl __bad_page_fault
> b ret_from_except_full
>
> diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
> index 43e71d86dcbf..52421042a020 100644
> --- a/arch/powerpc/kernel/exceptions-64e.S
> +++ b/arch/powerpc/kernel/exceptions-64e.S
> @@ -1018,9 +1018,8 @@ storage_fault_common:
> bne- 1f
> b ret_from_except_lite
> 1: bl save_nvgprs
> - mr r5,r3
> + mr r4,r3
> addi r3,r1,STACK_FRAME_OVERHEAD
> - ld r4,_DAR(r1)
> bl __bad_page_fault
> b ret_from_except
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 839dcb94eea7..b90d3cde14cf 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -2151,9 +2151,7 @@ EXC_COMMON_BEGIN(h_data_storage_common)
> GEN_COMMON h_data_storage
> addi r3,r1,STACK_FRAME_OVERHEAD
> BEGIN_MMU_FTR_SECTION
> - ld r4,_DAR(r1)
> - li r5,SIGSEGV
> - bl bad_page_fault
> + bl do_bad_page_fault_segv
> MMU_FTR_SECTION_ELSE
> bl unknown_exception
> ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
> diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
> index 3ec7b443fe6b..f3f6af3141ee 100644
> --- a/arch/powerpc/kernel/traps.c
> +++ b/arch/powerpc/kernel/traps.c
> @@ -1612,7 +1612,7 @@ void alignment_exception(struct pt_regs *regs)
> if (user_mode(regs))
> _exception(sig, regs, code, regs->dar);
> else
> - bad_page_fault(regs, regs->dar, sig);
> + bad_page_fault(regs, sig);
>
> bail:
> exception_exit(prev_state);
> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
> index 9a499af3eebf..1a270cc37d97 100644
> --- a/arch/powerpc/mm/book3s64/hash_utils.c
> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> @@ -1539,7 +1539,7 @@ long do_hash_fault(struct pt_regs *regs)
> * the access, or panic if there isn't a handler.
> */
> if (unlikely(in_nmi())) {
> - bad_page_fault(regs, ea, SIGSEGV);
> + bad_page_fault(regs, SIGSEGV);
> return 0;
> }
>
> @@ -1578,7 +1578,7 @@ long do_hash_fault(struct pt_regs *regs)
> else
> _exception(SIGBUS, regs, BUS_ADRERR, ea);
> } else {
> - bad_page_fault(regs, ea, SIGBUS);
> + bad_page_fault(regs, SIGBUS);
> }
> err = 0;
>
> diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
> index 985902ce0272..c581548b533f 100644
> --- a/arch/powerpc/mm/book3s64/slb.c
> +++ b/arch/powerpc/mm/book3s64/slb.c
> @@ -874,7 +874,7 @@ void do_bad_slb_fault(struct pt_regs *regs)
> if (user_mode(regs))
> _exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
> else
> - bad_page_fault(regs, regs->dar, SIGSEGV);
> + bad_page_fault(regs, SIGSEGV);
> } else if (err == -EINVAL) {
> unrecoverable_exception(regs);
> } else {
> diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
> index 273ff845eccf..e476d7701413 100644
> --- a/arch/powerpc/mm/fault.c
> +++ b/arch/powerpc/mm/fault.c
> @@ -566,7 +566,7 @@ NOKPROBE_SYMBOL(do_page_fault);
> * It is called from the DSI and ISI handlers in head.S and from some
> * of the procedures in traps.c.
> */
> -void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
> +void __bad_page_fault(struct pt_regs *regs, int sig)
> {
> int is_write = page_fault_is_write(regs->dsisr);
>
> @@ -604,7 +604,7 @@ void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
> die("Kernel access of bad area", regs, sig);
> }
>
> -void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
> +void bad_page_fault(struct pt_regs *regs, int sig)
> {
> const struct exception_table_entry *entry;
>
> @@ -613,5 +613,12 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
> if (entry)
> instruction_pointer_set(regs, extable_fixup(entry));
> else
> - __bad_page_fault(regs, address, sig);
> + __bad_page_fault(regs, sig);
> }
> +
> +#ifdef CONFIG_PPC_BOOK3S_64
> +void do_bad_page_fault_segv(struct pt_regs *regs)
> +{
> + bad_page_fault(regs, SIGSEGV);
> +}
> +#endif
> diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c
> index 88dedf38eccd..656365975895 100644
> --- a/arch/powerpc/platforms/8xx/machine_check.c
> +++ b/arch/powerpc/platforms/8xx/machine_check.c
> @@ -26,7 +26,7 @@ int machine_check_8xx(struct pt_regs *regs)
> * to deal with that than having a wart in the mcheck handler.
> * -- BenH
> */
> - bad_page_fault(regs, regs->dar, SIGBUS);
> + bad_page_fault(regs, SIGBUS);
> return 1;
> #else
> return 0;
>
^ permalink raw reply
* Re: [PATCH v6 17/39] powerpc/fsl_booke/32: CacheLockingException remove args
From: Christophe Leroy @ 2021-01-15 17:14 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev
In-Reply-To: <20210115165012.1260253-18-npiggin@gmail.com>
Le 15/01/2021 à 17:49, Nicholas Piggin a écrit :
> Like other interrupt handler conversions, switch to getting registers
> from the pt_regs argument.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> arch/powerpc/kernel/head_fsl_booke.S | 6 +++---
> arch/powerpc/kernel/traps.c | 5 +++--
> 2 files changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
> index fdd4d274c245..0d4d9a6fcca1 100644
> --- a/arch/powerpc/kernel/head_fsl_booke.S
> +++ b/arch/powerpc/kernel/head_fsl_booke.S
> @@ -364,12 +364,12 @@ interrupt_base:
> /* Data Storage Interrupt */
> START_EXCEPTION(DataStorage)
> NORMAL_EXCEPTION_PROLOG(DATA_STORAGE)
> - mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
> + mfspr r5,SPRN_ESR /* Grab the ESR, save it3 */
> stw r5,_ESR(r11)
> - mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
> + mfspr r4,SPRN_DEAR /* Grab the DEAR, save it */
> + stw r4, _DEAR(r11)
> 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
Why isn't the above done in patch 5 ?
> diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
> index 639bcafbad5e..1af52a4bce1f 100644
> --- a/arch/powerpc/kernel/traps.c
> +++ b/arch/powerpc/kernel/traps.c
> @@ -2105,9 +2105,10 @@ void altivec_assist_exception(struct pt_regs *regs)
> #endif /* CONFIG_ALTIVEC */
>
> #ifdef CONFIG_FSL_BOOKE
> -void CacheLockingException(struct pt_regs *regs, unsigned long address,
> - unsigned long error_code)
> +void CacheLockingException(struct pt_regs *regs)
> {
> + unsigned long error_code = regs->dsisr;
> +
> /* We treat cache locking instructions from the user
> * as priv ops, in the future we could try to do
> * something smarter
>
^ permalink raw reply
* [PATCH v15 00/10] Carry forward IMA measurement log on kexec on ARM64
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
On kexec file load Integrity Measurement Architecture (IMA) subsystem
may verify the IMA signature of the kernel and initramfs, and measure
it. The command line parameters passed to the kernel in the kexec call
may also be measured by IMA. A remote attestation service can verify
a TPM quote based on the TPM event log, the IMA measurement list, and
the TPM PCR data. This can be achieved only if the IMA measurement log
is carried over from the current kernel to the next kernel across
the kexec call.
powerpc already supports carrying forward the IMA measurement log on
kexec. This patch set adds support for carrying forward the IMA
measurement log on kexec on ARM64.
This patch set moves the platform independent code defined for powerpc
such that it can be reused for other platforms as well. A chosen node
"linux,ima-kexec-buffer" is added to the DTB for ARM64 to hold
the address and the size of the memory reserved to carry
the IMA measurement log.
This patch set has been tested for ARM64 platform using QEMU.
I would like help from the community for testing this change on powerpc.
Thanks.
This patch set is based on
commit 207cdd565dfc ("ima: Don't modify file descriptor mode on the fly")
in https://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git
"next-integrity" branch.
Changelog:
v15
- Included Rob's patches in the patch set, and rebased
the changes to "next-integrity" branch.
- Allocate memory for DTB, on arm64, using kmalloc() instead of
vmalloc() to keep it consistent with powerpc implementation.
- Call of_kexec_setup_new_fdt() from setup_new_fdt_ppc64() and
remove setup_new_fdt() in the same patch to keep it bisect safe.
v14
- Select CONFIG_HAVE_IMA_KEXEC for CONFIG_KEXEC_FILE, for powerpc
and arm64, if CONFIG_IMA is enabled.
- Use IS_ENABLED() macro instead of "#ifdef" in remove_ima_buffer(),
ima_get_kexec_buffer(), and ima_free_kexec_buffer().
- Call of_kexec_setup_new_fdt() from setup_new_fdt_ppc64() and
remove setup_new_fdt() in "arch/powerpc/kexec/file_load.c".
v13
- Moved the arch independent functions to drivers/of/kexec.c
and then refactored the code.
- Moved arch_ima_add_kexec_buffer() to
security/integrity/ima/ima_kexec.c
v12
- Use fdt_appendprop_addrrange() in setup_ima_buffer()
to setup the IMA measurement list property in
the device tree.
- Moved architecture independent functions from
"arch/powerpc/kexec/ima.c" to "drivers/of/kexec."
- Deleted "arch/powerpc/kexec/ima.c" and
"arch/powerpc/include/asm/ima.h".
v11
- Rebased the changes on the kexec code refactoring done by
Rob Herring in his "dt/kexec" branch
- Removed "extern" keyword in function declarations
- Removed unnecessary header files included in C files
- Updated patch descriptions per Thiago's comments
v10
- Moved delete_fdt_mem_rsv(), remove_ima_buffer(),
get_ima_kexec_buffer, and get_root_addr_size_cells()
to drivers/of/kexec.c
- Moved arch_ima_add_kexec_buffer() to
security/integrity/ima/ima_kexec.c
- Conditionally define IMA buffer fields in struct kimage_arch
v9
- Moved delete_fdt_mem_rsv() to drivers/of/kexec_fdt.c
- Defined a new function get_ima_kexec_buffer() in
drivers/of/ima_kexec.c to replace do_get_kexec_buffer()
- Changed remove_ima_kexec_buffer() to the original function name
remove_ima_buffer()
- Moved remove_ima_buffer() to drivers/of/ima_kexec.c
- Moved ima_get_kexec_buffer() and ima_free_kexec_buffer()
to security/integrity/ima/ima_kexec.c
v8:
- Moved remove_ima_kexec_buffer(), do_get_kexec_buffer(), and
delete_fdt_mem_rsv() to drivers/of/fdt.c
- Moved ima_dump_measurement_list() and ima_add_kexec_buffer()
back to security/integrity/ima/ima_kexec.c
v7:
- Renamed remove_ima_buffer() to remove_ima_kexec_buffer() and moved
this function definition to kernel.
- Moved delete_fdt_mem_rsv() definition to kernel
- Moved ima_dump_measurement_list() and ima_add_kexec_buffer() to
a new file namely ima_kexec_fdt.c in IMA
v6:
- Remove any existing FDT_PROP_IMA_KEXEC_BUFFER property in the device
tree and also its corresponding memory reservation in the currently
running kernel.
- Moved the function remove_ima_buffer() defined for powerpc to IMA
and renamed the function to ima_remove_kexec_buffer(). Also, moved
delete_fdt_mem_rsv() from powerpc to IMA.
v5:
- Merged get_addr_size_cells() and do_get_kexec_buffer() into a single
function when moving the arch independent code from powerpc to IMA
- Reverted the change to use FDT functions in powerpc code and added
back the original code in get_addr_size_cells() and
do_get_kexec_buffer() for powerpc.
- Added fdt_add_mem_rsv() for ARM64 to reserve the memory for
the IMA log buffer during kexec.
- Fixed the warning reported by kernel test bot for ARM64
arch_ima_add_kexec_buffer() - moved this function to a new file
namely arch/arm64/kernel/ima_kexec.c
v4:
- Submitting the patch series on behalf of the original author
Prakhar Srivastava <prsriva@linux.microsoft.com>
- Moved FDT_PROP_IMA_KEXEC_BUFFER ("linux,ima-kexec-buffer") to
libfdt.h so that it can be shared by multiple platforms.
v3:
Breakup patches further into separate patches.
- Refactoring non architecture specific code out of powerpc
- Update powerpc related code to use fdt functions
- Update IMA buffer read related code to use of functions
- Add support to store the memory information of the IMA
measurement logs to be carried forward.
- Update the property strings to align with documented nodes
https://github.com/devicetree-org/dt-schema/pull/46
v2:
Break patches into separate patches.
- Powerpc related Refactoring
- Updating the docuemntation for chosen node
- Updating arm64 to support IMA buffer pass
v1:
Refactoring carrying over IMA measuremnet logs over Kexec. This patch
moves the non-architecture specific code out of powerpc and adds to
security/ima.(Suggested by Thiago)
Add Documentation regarding the ima-kexec-buffer node in the chosen
node documentation
v0:
Add a layer of abstraction to use the memory reserved by device tree
for ima buffer pass.
Add support for ima buffer pass using reserved memory for arm64 kexec.
Update the arch sepcific code path in kexec file load to store the
ima buffer in the reserved memory. The same reserved memory is read
on kexec or cold boot.
Lakshmi Ramasubramanian (6):
ima: Move arch_ima_add_kexec_buffer() to ima
powerpc: Move arch independent ima kexec functions to
drivers/of/kexec.c
kexec: Use fdt_appendprop_addrrange() to add ima buffer to FDT
powerpc: Delete unused function delete_fdt_mem_rsv()
arm64: Call kmalloc() to allocate DTB buffer
arm64: Add IMA log information in kimage used for kexec
Rob Herring (4):
powerpc: Rename kexec elfcorehdr_addr to elf_headers_mem
of: Add a common kexec FDT setup function
arm64: Use common of_kexec_setup_new_fdt()
powerpc: Use common of_kexec_setup_new_fdt()
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/kexec.h | 5 +
arch/arm64/kernel/machine_kexec_file.c | 135 +-------
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/ima.h | 30 --
arch/powerpc/include/asm/kexec.h | 6 +-
arch/powerpc/kexec/Makefile | 7 -
arch/powerpc/kexec/file_load.c | 184 +----------
arch/powerpc/kexec/file_load_64.c | 8 +-
arch/powerpc/kexec/ima.c | 219 -------------
drivers/of/Makefile | 1 +
drivers/of/kexec.c | 429 +++++++++++++++++++++++++
include/linux/of.h | 7 +
security/integrity/ima/ima.h | 4 -
security/integrity/ima/ima_kexec.c | 22 ++
15 files changed, 484 insertions(+), 576 deletions(-)
delete mode 100644 arch/powerpc/include/asm/ima.h
delete mode 100644 arch/powerpc/kexec/ima.c
create mode 100644 drivers/of/kexec.c
--
2.30.0
^ permalink raw reply
* [PATCH v15 02/10] of: Add a common kexec FDT setup function
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
From: Rob Herring <robh@kernel.org>
Both arm64 and powerpc do essentially the same FDT /chosen setup for
kexec. The differences are either omissions that arm64 should have
or additional properties that will be ignored. The setup code can be
combined and shared by both powerpc and arm64.
The differences relative to the arm64 version:
- If /chosen doesn't exist, it will be created (should never happen).
- Any old dtb and initrd reserved memory will be released.
- The new initrd and elfcorehdr are marked reserved.
- "linux,booted-from-kexec" is set.
The differences relative to the powerpc version:
- "kaslr-seed" and "rng-seed" may be set.
- "linux,elfcorehdr" is set.
- Any existing "linux,usable-memory-range" is removed.
Combine the code for setting up the /chosen node in the FDT and updating
the memory reservation for kexec, for powerpc and arm64, in
of_kexec_setup_new_fdt() and move it to "drivers/of/kexec.c".
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
drivers/of/Makefile | 1 +
drivers/of/kexec.c | 236 ++++++++++++++++++++++++++++++++++++++++++++
include/linux/of.h | 5 +
3 files changed, 242 insertions(+)
create mode 100644 drivers/of/kexec.c
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 6e1e5212f058..8ce11955afde 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -13,5 +13,6 @@ obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
obj-$(CONFIG_OF_RESOLVE) += resolver.o
obj-$(CONFIG_OF_OVERLAY) += overlay.o
obj-$(CONFIG_OF_NUMA) += of_numa.o
+obj-$(CONFIG_KEXEC_FILE) += kexec.o
obj-$(CONFIG_OF_UNITTEST) += unittest-data/
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
new file mode 100644
index 000000000000..4afd3cc1c04a
--- /dev/null
+++ b/drivers/of/kexec.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Arm Limited
+ *
+ * Based on arch/arm64/kernel/machine_kexec_file.c:
+ * Copyright (C) 2018 Linaro Limited
+ *
+ * And arch/powerpc/kexec/file_load.c:
+ * Copyright (C) 2016 IBM Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/libfdt.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/random.h>
+#include <linux/types.h>
+
+/* relevant device tree properties */
+#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr"
+#define FDT_PROP_MEM_RANGE "linux,usable-memory-range"
+#define FDT_PROP_INITRD_START "linux,initrd-start"
+#define FDT_PROP_INITRD_END "linux,initrd-end"
+#define FDT_PROP_BOOTARGS "bootargs"
+#define FDT_PROP_KASLR_SEED "kaslr-seed"
+#define FDT_PROP_RNG_SEED "rng-seed"
+#define RNG_SEED_SIZE 128
+
+/**
+ * fdt_find_and_del_mem_rsv - delete memory reservation with given address and size
+ *
+ * @fdt: Flattened device tree for the current kernel.
+ * @start: Starting address of the reserved memory.
+ * @size: Size of the reserved memory.
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+static int fdt_find_and_del_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++) {
+ u64 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;
+}
+
+/*
+ * of_kexec_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 of_kexec_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 = fdt_find_and_del_mem_rsv(fdt, __pa(initial_boot_params),
+ fdt_totalsize(initial_boot_params));
+ if (ret == -EINVAL)
+ 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) {
+ ret = chosen_node;
+ goto out;
+ }
+
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_KEXEC_ELFHDR);
+ if (ret && ret != -FDT_ERR_NOTFOUND)
+ goto out;
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_MEM_RANGE);
+ if (ret && ret != -FDT_ERR_NOTFOUND)
+ goto out;
+
+ /* Did we boot using an initrd? */
+ prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL);
+ if (prop) {
+ u64 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)
+ 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 = fdt_find_and_del_mem_rsv(fdt, tmp_start, tmp_size);
+ if (ret == -ENOENT)
+ ret = fdt_find_and_del_mem_rsv(fdt, tmp_start,
+ round_up(tmp_size, PAGE_SIZE));
+ if (ret == -EINVAL)
+ return ret;
+ }
+
+ /* add initrd-* */
+ if (initrd_load_addr) {
+ ret = fdt_setprop_u64(fdt, chosen_node, FDT_PROP_INITRD_START,
+ initrd_load_addr);
+ if (ret)
+ goto out;
+
+ ret = fdt_setprop_u64(fdt, chosen_node, FDT_PROP_INITRD_END,
+ initrd_load_addr + initrd_len);
+ if (ret)
+ goto out;
+
+ ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len);
+ if (ret)
+ goto out;
+
+ } else {
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_INITRD_START);
+ if (ret && (ret != -FDT_ERR_NOTFOUND))
+ goto out;
+
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_INITRD_END);
+ if (ret && (ret != -FDT_ERR_NOTFOUND))
+ goto out;
+ }
+
+ if (image->type == KEXEC_TYPE_CRASH) {
+ /* add linux,elfcorehdr */
+ ret = fdt_appendprop_addrrange(fdt, 0, chosen_node,
+ FDT_PROP_KEXEC_ELFHDR,
+ image->arch.elf_headers_mem,
+ image->arch.elf_headers_sz);
+ if (ret)
+ goto out;
+
+ /*
+ * Avoid elfcorehdr from being stomped on in kdump kernel by
+ * setting up memory reserve map.
+ */
+ ret = fdt_add_mem_rsv(fdt, image->arch.elf_headers_mem,
+ image->arch.elf_headers_sz);
+ if (ret)
+ goto out;
+
+ /* add linux,usable-memory-range */
+ ret = fdt_appendprop_addrrange(fdt, 0, chosen_node,
+ FDT_PROP_MEM_RANGE,
+ crashk_res.start,
+ crashk_res.end - crashk_res.start + 1);
+ if (ret)
+ goto out;
+ }
+
+ /* add bootargs */
+ if (cmdline) {
+ ret = fdt_setprop_string(fdt, chosen_node, FDT_PROP_BOOTARGS, cmdline);
+ if (ret)
+ goto out;
+ } else {
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_BOOTARGS);
+ if (ret && (ret != -FDT_ERR_NOTFOUND))
+ goto out;
+ }
+
+ /* add kaslr-seed */
+ ret = fdt_delprop(fdt, chosen_node, FDT_PROP_KASLR_SEED);
+ if (ret == -FDT_ERR_NOTFOUND)
+ ret = 0;
+ else if (ret)
+ goto out;
+
+ if (rng_is_initialized()) {
+ u64 seed = get_random_u64();
+
+ ret = fdt_setprop_u64(fdt, chosen_node, FDT_PROP_KASLR_SEED, seed);
+ if (ret)
+ goto out;
+ } else {
+ pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+ FDT_PROP_KASLR_SEED);
+ }
+
+ /* add rng-seed */
+ if (rng_is_initialized()) {
+ void *rng_seed;
+
+ ret = fdt_setprop_placeholder(fdt, chosen_node, FDT_PROP_RNG_SEED,
+ RNG_SEED_SIZE, &rng_seed);
+ if (ret)
+ goto out;
+ get_random_bytes(rng_seed, RNG_SEED_SIZE);
+ } else {
+ pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+ FDT_PROP_RNG_SEED);
+ }
+
+ ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
+
+out:
+ if (ret)
+ return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
+
+ return 0;
+}
diff --git a/include/linux/of.h b/include/linux/of.h
index 5d51891cbf1a..3375f5295875 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -558,6 +558,11 @@ int of_map_id(struct device_node *np, u32 id,
const char *map_name, const char *map_mask_name,
struct device_node **target, u32 *id_out);
+struct kimage;
+int of_kexec_setup_new_fdt(const struct kimage *image, void *fdt,
+ unsigned long initrd_load_addr, unsigned long initrd_len,
+ const char *cmdline);
+
#else /* CONFIG_OF */
static inline void of_core_init(void)
--
2.30.0
^ permalink raw reply related
* [PATCH v15 01/10] powerpc: Rename kexec elfcorehdr_addr to elf_headers_mem
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
From: Rob Herring <robh@kernel.org>
The architecture specific field, elfcorehdr_addr in struct kimage_arch,
that holds the address of the buffer in memory for ELF core header for
powerpc has a different name than the one used for arm64. This makes
it hard to have a common code for setting up the device tree for
kexec system call.
Rename elfcorehdr_addr to elf_headers_mem to align with arm64 name so
common code can use it.
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
arch/powerpc/include/asm/kexec.h | 2 +-
arch/powerpc/kexec/file_load.c | 4 ++--
arch/powerpc/kexec/file_load_64.c | 4 ++--
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 55d6ede30c19..dbf09d2f36d0 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -108,7 +108,7 @@ struct kimage_arch {
unsigned long backup_start;
void *backup_buf;
- unsigned long elfcorehdr_addr;
+ unsigned long elf_headers_mem;
unsigned long elf_headers_sz;
void *elf_headers;
diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c
index 9a232bc36c8f..e452b11df631 100644
--- a/arch/powerpc/kexec/file_load.c
+++ b/arch/powerpc/kexec/file_load.c
@@ -45,7 +45,7 @@ char *setup_kdump_cmdline(struct kimage *image, char *cmdline,
return NULL;
elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ",
- image->arch.elfcorehdr_addr);
+ image->arch.elf_headers_mem);
if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) {
pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n");
@@ -263,7 +263,7 @@ int setup_new_fdt(const struct kimage *image, void *fdt,
* Avoid elfcorehdr from being stomped on in kdump kernel by
* setting up memory reserve map.
*/
- ret = fdt_add_mem_rsv(fdt, image->arch.elfcorehdr_addr,
+ ret = fdt_add_mem_rsv(fdt, image->arch.elf_headers_mem,
image->arch.elf_headers_sz);
if (ret) {
pr_err("Error reserving elfcorehdr memory: %s\n",
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index c69bcf9b547a..a05c19b3cc60 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -815,7 +815,7 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
goto out;
}
- image->arch.elfcorehdr_addr = kbuf->mem;
+ image->arch.elf_headers_mem = kbuf->mem;
image->arch.elf_headers_sz = headers_sz;
image->arch.elf_headers = headers;
out:
@@ -851,7 +851,7 @@ int load_crashdump_segments_ppc64(struct kimage *image,
return ret;
}
pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
- image->arch.elfcorehdr_addr, kbuf->bufsz, kbuf->memsz);
+ image->arch.elf_headers_mem, kbuf->bufsz, kbuf->memsz);
return 0;
}
--
2.30.0
^ permalink raw reply related
* [PATCH v15 03/10] arm64: Use common of_kexec_setup_new_fdt()
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
From: Rob Herring <robh@kernel.org>
The code for setting up the /chosen node in the device tree
and updating the memory reservation for the next kernel has been
moved to of_kexec_setup_new_fdt() defined in "drivers/of/kexec.c".
Use the common of_kexec_setup_new_fdt() to setup the device tree
and update the memory reservation for kexec for arm64.
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Acked-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/machine_kexec_file.c | 123 +------------------------
1 file changed, 3 insertions(+), 120 deletions(-)
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 5b0e67b93cdc..7de9c47dee7c 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -15,23 +15,12 @@
#include <linux/kexec.h>
#include <linux/libfdt.h>
#include <linux/memblock.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
-#include <linux/random.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
-#include <asm/byteorder.h>
-
-/* relevant device tree properties */
-#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr"
-#define FDT_PROP_MEM_RANGE "linux,usable-memory-range"
-#define FDT_PROP_INITRD_START "linux,initrd-start"
-#define FDT_PROP_INITRD_END "linux,initrd-end"
-#define FDT_PROP_BOOTARGS "bootargs"
-#define FDT_PROP_KASLR_SEED "kaslr-seed"
-#define FDT_PROP_RNG_SEED "rng-seed"
-#define RNG_SEED_SIZE 128
const struct kexec_file_ops * const kexec_file_loaders[] = {
&kexec_image_ops,
@@ -50,112 +39,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
return kexec_image_post_load_cleanup_default(image);
}
-static int setup_dtb(struct kimage *image,
- unsigned long initrd_load_addr, unsigned long initrd_len,
- char *cmdline, void *dtb)
-{
- int off, ret;
-
- ret = fdt_path_offset(dtb, "/chosen");
- if (ret < 0)
- goto out;
-
- off = ret;
-
- ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR);
- if (ret && ret != -FDT_ERR_NOTFOUND)
- goto out;
- ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE);
- if (ret && ret != -FDT_ERR_NOTFOUND)
- goto out;
-
- if (image->type == KEXEC_TYPE_CRASH) {
- /* add linux,elfcorehdr */
- ret = fdt_appendprop_addrrange(dtb, 0, off,
- FDT_PROP_KEXEC_ELFHDR,
- image->arch.elf_headers_mem,
- image->arch.elf_headers_sz);
- if (ret)
- return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL);
-
- /* add linux,usable-memory-range */
- ret = fdt_appendprop_addrrange(dtb, 0, off,
- FDT_PROP_MEM_RANGE,
- crashk_res.start,
- crashk_res.end - crashk_res.start + 1);
- if (ret)
- return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL);
- }
-
- /* add bootargs */
- if (cmdline) {
- ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline);
- if (ret)
- goto out;
- } else {
- ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS);
- if (ret && (ret != -FDT_ERR_NOTFOUND))
- goto out;
- }
-
- /* add initrd-* */
- if (initrd_load_addr) {
- ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START,
- initrd_load_addr);
- if (ret)
- goto out;
-
- ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END,
- initrd_load_addr + initrd_len);
- if (ret)
- goto out;
- } else {
- ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START);
- if (ret && (ret != -FDT_ERR_NOTFOUND))
- goto out;
-
- ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END);
- if (ret && (ret != -FDT_ERR_NOTFOUND))
- goto out;
- }
-
- /* add kaslr-seed */
- ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED);
- if (ret == -FDT_ERR_NOTFOUND)
- ret = 0;
- else if (ret)
- goto out;
-
- if (rng_is_initialized()) {
- u64 seed = get_random_u64();
- ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed);
- if (ret)
- goto out;
- } else {
- pr_notice("RNG is not initialised: omitting \"%s\" property\n",
- FDT_PROP_KASLR_SEED);
- }
-
- /* add rng-seed */
- if (rng_is_initialized()) {
- void *rng_seed;
- ret = fdt_setprop_placeholder(dtb, off, FDT_PROP_RNG_SEED,
- RNG_SEED_SIZE, &rng_seed);
- if (ret)
- goto out;
- get_random_bytes(rng_seed, RNG_SEED_SIZE);
- } else {
- pr_notice("RNG is not initialised: omitting \"%s\" property\n",
- FDT_PROP_RNG_SEED);
- }
-
-out:
- if (ret)
- return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
-
- return 0;
-}
-
/*
* More space needed so that we can add initrd, bootargs, kaslr-seed,
* rng-seed, userable-memory-range and elfcorehdr.
@@ -185,8 +68,8 @@ static int create_dtb(struct kimage *image,
if (ret)
return -EINVAL;
- ret = setup_dtb(image, initrd_load_addr, initrd_len,
- cmdline, buf);
+ ret = of_kexec_setup_new_fdt(image, buf, initrd_load_addr,
+ initrd_len, cmdline);
if (ret) {
vfree(buf);
if (ret == -ENOMEM) {
--
2.30.0
^ permalink raw reply related
* [PATCH v15 04/10] powerpc: Use common of_kexec_setup_new_fdt()
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
From: Rob Herring <robh@kernel.org>
The code for setting up the /chosen node in the device tree
and updating the memory reservation for the next kernel has been
moved to of_kexec_setup_new_fdt() defined in "drivers/of/kexec.c".
Use the common of_kexec_setup_new_fdt() to setup the device tree
and update the memory reservation for kexec for powerpc.
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
arch/powerpc/kexec/file_load.c | 125 ++-------------------------------
1 file changed, 6 insertions(+), 119 deletions(-)
diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c
index e452b11df631..956bcb2d1ec2 100644
--- a/arch/powerpc/kexec/file_load.c
+++ b/arch/powerpc/kexec/file_load.c
@@ -16,6 +16,7 @@
#include <linux/slab.h>
#include <linux/kexec.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <asm/setup.h>
@@ -156,132 +157,18 @@ 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;
- }
- }
+ int ret;
- if (image->type == KEXEC_TYPE_CRASH) {
- /*
- * Avoid elfcorehdr from being stomped on in kdump kernel by
- * setting up memory reserve map.
- */
- ret = fdt_add_mem_rsv(fdt, image->arch.elf_headers_mem,
- image->arch.elf_headers_sz);
- if (ret) {
- pr_err("Error reserving elfcorehdr memory: %s\n",
- fdt_strerror(ret));
- goto err;
- }
- }
+ ret = of_kexec_setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
+ if (ret)
+ goto err;
- ret = setup_ima_buffer(image, fdt, chosen_node);
+ ret = setup_ima_buffer(image, fdt, fdt_path_offset(fdt, "/chosen"));
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:
--
2.30.0
^ permalink raw reply related
* [PATCH v15 09/10] arm64: Call kmalloc() to allocate DTB buffer
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
create_dtb() function allocates kernel virtual memory for
the device tree blob (DTB). This is not consistent with other
architectures, such as powerpc, which calls kmalloc() for allocating
memory for the DTB.
Call kmalloc() to allocate memory for the DTB, and kfree() to free
the allocated memory.
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
arch/arm64/kernel/machine_kexec_file.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 7de9c47dee7c..51c40143d6fa 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -29,7 +29,7 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
int arch_kimage_file_post_load_cleanup(struct kimage *image)
{
- vfree(image->arch.dtb);
+ kfree(image->arch.dtb);
image->arch.dtb = NULL;
vfree(image->arch.elf_headers);
@@ -59,19 +59,21 @@ static int create_dtb(struct kimage *image,
+ cmdline_len + DTB_EXTRA_SPACE;
for (;;) {
- buf = vmalloc(buf_size);
+ buf = kmalloc(buf_size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
/* duplicate a device tree blob */
ret = fdt_open_into(initial_boot_params, buf, buf_size);
- if (ret)
+ if (ret) {
+ kfree(buf);
return -EINVAL;
+ }
ret = of_kexec_setup_new_fdt(image, buf, initrd_load_addr,
initrd_len, cmdline);
if (ret) {
- vfree(buf);
+ kfree(buf);
if (ret == -ENOMEM) {
/* unlikely, but just in case */
buf_size += DTB_EXTRA_SPACE;
@@ -217,6 +219,6 @@ int load_other_segments(struct kimage *image,
return 0;
out_err:
- vfree(dtb);
+ kfree(dtb);
return ret;
}
--
2.30.0
^ permalink raw reply related
* [PATCH v15 07/10] kexec: Use fdt_appendprop_addrrange() to add ima buffer to FDT
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
fdt_appendprop_addrrange() function adds a property, with the given name,
to the device tree at the given node offset, and also sets the address
and size of the property. This function should be used to add
"linux,ima-kexec-buffer" property to the device tree and set the address
and size of the IMA measurement buffer, instead of using custom function.
Use fdt_appendprop_addrrange() to add "linux,ima-kexec-buffer" property
to the device tree. This property holds the address and size of
the IMA measurement buffer that needs to be passed from the current
kernel to the next kernel across kexec system call.
Remove custom code that is used in setup_ima_buffer() to add
"linux,ima-kexec-buffer" property to the device tree.
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
---
drivers/of/kexec.c | 57 ++++------------------------------------------
1 file changed, 5 insertions(+), 52 deletions(-)
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
index 450fa6128001..49183da2fc34 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -210,36 +210,6 @@ int ima_free_kexec_buffer(void)
}
#ifdef CONFIG_IMA_KEXEC
-/**
- * write_number - Convert number to big-endian format
- *
- * @p: Buffer to write the number to
- * @value: Number to convert
- * @cells: Number of cells
- *
- * Return: 0 on success, or negative errno on error.
- */
-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.
@@ -251,32 +221,15 @@ static int write_number(void *p, u64 value, int cells)
static int setup_ima_buffer(const struct kimage *image, void *fdt,
int chosen_node)
{
- int ret, addr_cells, size_cells, entry_size;
- u8 value[16];
+ int ret;
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);
+ ret = fdt_appendprop_addrrange(fdt, 0, chosen_node,
+ "linux,ima-kexec-buffer",
+ image->arch.ima_buffer_addr,
+ image->arch.ima_buffer_size);
if (ret < 0)
return -EINVAL;
--
2.30.0
^ permalink raw reply related
* [PATCH v15 08/10] powerpc: Delete unused function delete_fdt_mem_rsv()
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
delete_fdt_mem_rsv() defined in "arch/powerpc/kexec/file_load.c"
has been renamed to fdt_find_and_del_mem_rsv(), and moved to
"drivers/of/kexec.c".
Remove delete_fdt_mem_rsv() in "arch/powerpc/kexec/file_load.c".
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
arch/powerpc/include/asm/kexec.h | 1 -
arch/powerpc/kexec/file_load.c | 32 --------------------------------
2 files changed, 33 deletions(-)
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 11679fc2cadc..b8c270e08481 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -123,7 +123,6 @@ char *setup_kdump_cmdline(struct kimage *image, char *cmdline,
int setup_purgatory(struct kimage *image, const void *slave_code,
const void *fdt, unsigned long kernel_load_addr,
unsigned long fdt_load_addr);
-int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size);
#ifdef CONFIG_PPC64
struct kexec_buf;
diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c
index 5dd3a9c45a2d..036c8fb48fc3 100644
--- a/arch/powerpc/kexec/file_load.c
+++ b/arch/powerpc/kexec/file_load.c
@@ -108,35 +108,3 @@ int setup_purgatory(struct kimage *image, const void *slave_code,
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;
-}
--
2.30.0
^ permalink raw reply related
* [PATCH v15 10/10] arm64: Add IMA log information in kimage used for kexec
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
Address and size of the buffer containing the IMA measurement log need
to be passed from the current kernel to the next kernel on kexec.
Add address and size fields to "struct kimage_arch" for ARM64 platform
to hold the address and size of the IMA measurement log buffer.
Update CONFIG_KEXEC_FILE to select CONFIG_HAVE_IMA_KEXEC, if CONFIG_IMA
is enabled, to indicate that the IMA measurement log information is
present in the device tree for ARM64.
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
---
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/kexec.h | 5 +++++
2 files changed, 6 insertions(+)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1d466addb078..ea7f7fe3dccd 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1094,6 +1094,7 @@ config KEXEC
config KEXEC_FILE
bool "kexec file based system call"
select KEXEC_CORE
+ select HAVE_IMA_KEXEC if IMA
help
This is new version of kexec system call. This system call is
file based and takes file descriptors as system call argument
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index d24b527e8c00..2bd19ccb6c43 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -100,6 +100,11 @@ struct kimage_arch {
void *elf_headers;
unsigned long elf_headers_mem;
unsigned long elf_headers_sz;
+
+#ifdef CONFIG_IMA_KEXEC
+ phys_addr_t ima_buffer_addr;
+ size_t ima_buffer_size;
+#endif
};
extern const struct kexec_file_ops kexec_image_ops;
--
2.30.0
^ permalink raw reply related
* [PATCH v15 06/10] powerpc: Move arch independent ima kexec functions to drivers/of/kexec.c
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
The functions defined in "arch/powerpc/kexec/ima.c" handle setting up
and freeing the resources required to carry over the IMA measurement
list from the current kernel to the next kernel across kexec system call.
These functions do not have architecture specific code, but are
currently limited to powerpc.
Move setup_ima_buffer() call into of_kexec_setup_new_fdt() defined in
"drivers/of/kexec.c". Call of_kexec_setup_new_fdt() from
setup_new_fdt_ppc64() and remove setup_new_fdt() in
"arch/powerpc/kexec/file_load.c".
Move the remaining architecture independent functions from
"arch/powerpc/kexec/ima.c" to "drivers/of/kexec.c".
Delete "arch/powerpc/kexec/ima.c" and "arch/powerpc/include/asm/ima.h".
Remove references to the deleted files in powerpc and in ima.
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
---
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/ima.h | 27 ----
arch/powerpc/include/asm/kexec.h | 3 -
arch/powerpc/kexec/Makefile | 7 -
arch/powerpc/kexec/file_load.c | 35 -----
arch/powerpc/kexec/file_load_64.c | 4 +-
arch/powerpc/kexec/ima.c | 202 ------------------------
drivers/of/kexec.c | 240 +++++++++++++++++++++++++++++
include/linux/of.h | 2 +
security/integrity/ima/ima.h | 4 -
security/integrity/ima/ima_kexec.c | 1 +
11 files changed, 247 insertions(+), 280 deletions(-)
delete mode 100644 arch/powerpc/include/asm/ima.h
delete mode 100644 arch/powerpc/kexec/ima.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e9f13fe08492..4ddd17215ecf 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -548,7 +548,7 @@ config KEXEC
config KEXEC_FILE
bool "kexec file based system call"
select KEXEC_CORE
- select HAVE_IMA_KEXEC
+ select HAVE_IMA_KEXEC if IMA
select BUILD_BIN2C
select KEXEC_ELF
depends on PPC64
diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h
deleted file mode 100644
index 51f64fd06c19..000000000000
--- a/arch/powerpc/include/asm/ima.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_IMA_H
-#define _ASM_POWERPC_IMA_H
-
-struct kimage;
-
-int ima_get_kexec_buffer(void **addr, size_t *size);
-int ima_free_kexec_buffer(void);
-
-#ifdef CONFIG_IMA
-void remove_ima_buffer(void *fdt, int chosen_node);
-#else
-static inline void remove_ima_buffer(void *fdt, int chosen_node) {}
-#endif
-
-#ifdef CONFIG_IMA_KEXEC
-int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node);
-#else
-static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
- int chosen_node)
-{
- remove_ima_buffer(fdt, chosen_node);
- return 0;
-}
-#endif /* CONFIG_IMA_KEXEC */
-
-#endif /* _ASM_POWERPC_IMA_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index dbf09d2f36d0..11679fc2cadc 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -123,9 +123,6 @@ char *setup_kdump_cmdline(struct kimage *image, char *cmdline,
int setup_purgatory(struct kimage *image, const void *slave_code,
const void *fdt, unsigned long kernel_load_addr,
unsigned long fdt_load_addr);
-int setup_new_fdt(const struct kimage *image, void *fdt,
- unsigned long initrd_load_addr, unsigned long initrd_len,
- const char *cmdline);
int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size);
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 4aff6846c772..b6c52608cb49 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -9,13 +9,6 @@ obj-$(CONFIG_PPC32) += relocate_32.o
obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o
-ifdef CONFIG_HAVE_IMA_KEXEC
-ifdef CONFIG_IMA
-obj-y += ima.o
-endif
-endif
-
-
# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_core_$(BITS).o := n
KCOV_INSTRUMENT_core_$(BITS).o := n
diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c
index 956bcb2d1ec2..5dd3a9c45a2d 100644
--- a/arch/powerpc/kexec/file_load.c
+++ b/arch/powerpc/kexec/file_load.c
@@ -20,7 +20,6 @@
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <asm/setup.h>
-#include <asm/ima.h>
#define SLAVE_CODE_SIZE 256 /* First 0x100 bytes */
@@ -141,37 +140,3 @@ int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
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;
-
- ret = of_kexec_setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
- if (ret)
- goto err;
-
- ret = setup_ima_buffer(image, fdt, fdt_path_offset(fdt, "/chosen"));
- if (ret) {
- pr_err("Error setting up the new device tree.\n");
- return ret;
- }
-
- return 0;
-
-err:
- pr_err("Error setting up the new device tree.\n");
- return -EINVAL;
-}
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index a05c19b3cc60..3cab318aa3b9 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -17,6 +17,7 @@
#include <linux/kexec.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
+#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/memblock.h>
#include <linux/slab.h>
@@ -944,7 +945,8 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
struct crash_mem *umem = NULL, *rmem = NULL;
int i, nr_ranges, ret;
- ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
+ ret = of_kexec_setup_new_fdt(image, fdt, initrd_load_addr, initrd_len,
+ cmdline);
if (ret)
goto out;
diff --git a/arch/powerpc/kexec/ima.c b/arch/powerpc/kexec/ima.c
deleted file mode 100644
index 7378d59c0c1e..000000000000
--- a/arch/powerpc/kexec/ima.c
+++ /dev/null
@@ -1,202 +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
-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/drivers/of/kexec.c b/drivers/of/kexec.c
index 4afd3cc1c04a..450fa6128001 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/kexec.h>
+#include <linux/memblock.h>
#include <linux/libfdt.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
@@ -63,6 +64,240 @@ static int fdt_find_and_del_mem_rsv(void *fdt, unsigned long start, unsigned lon
return -ENOENT;
}
+/**
+ * get_addr_size_cells - Get address and size of root node
+ *
+ * @addr_cells: Return address of the root node
+ * @size_cells: Return size of the root node
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+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;
+}
+
+/**
+ * do_get_kexec_buffer - Get address and size of device tree property
+ *
+ * @prop: Device tree property
+ * @len: Size of @prop
+ * @addr: Return address of the node
+ * @size: Return size of the node
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+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;
+}
+
+/**
+ * remove_ima_buffer - remove the IMA buffer property and reservation from @fdt
+ *
+ * @fdt: Flattened Device Tree to update
+ * @chosen_node: Offset to the chosen node in the device tree
+ *
+ * The IMA measurement buffer is of no use to a subsequent kernel, so we always
+ * remove it from the device tree.
+ */
+static void remove_ima_buffer(void *fdt, int chosen_node)
+{
+ int ret, len;
+ unsigned long addr;
+ size_t size;
+ const void *prop;
+
+ if (!IS_ENABLED(CONFIG_HAVE_IMA_KEXEC))
+ return;
+
+ 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 = fdt_find_and_del_mem_rsv(fdt, addr, size);
+ if (!ret)
+ pr_debug("Removed old IMA buffer reservation.\n");
+}
+
+/**
+ * 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;
+
+ if (!IS_ENABLED(CONFIG_HAVE_IMA_KEXEC))
+ return -ENOTSUPP;
+
+ 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;
+
+ if (!IS_ENABLED(CONFIG_HAVE_IMA_KEXEC))
+ return -ENOTSUPP;
+
+ 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);
+
+}
+
+#ifdef CONFIG_IMA_KEXEC
+/**
+ * write_number - Convert number to big-endian format
+ *
+ * @p: Buffer to write the number to
+ * @value: Number to convert
+ * @cells: Number of cells
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+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.
+ */
+static int setup_ima_buffer(const struct kimage *image, void *fdt,
+ int chosen_node)
+{
+ int ret, addr_cells, size_cells, entry_size;
+ u8 value[16];
+
+ 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;
+}
+#else /* CONFIG_IMA_KEXEC */
+static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
+ int chosen_node)
+{
+ return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
+
/*
* of_kexec_setup_new_fdt - modify /chosen and memory reservation for the next kernel
*
@@ -227,6 +462,11 @@ int of_kexec_setup_new_fdt(const struct kimage *image, void *fdt,
}
ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
+ if (ret)
+ goto out;
+
+ remove_ima_buffer(fdt, chosen_node);
+ ret = setup_ima_buffer(image, fdt, fdt_path_offset(fdt, "/chosen"));
out:
if (ret)
diff --git a/include/linux/of.h b/include/linux/of.h
index 3375f5295875..48eb2d05c0ec 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -562,6 +562,8 @@ struct kimage;
int of_kexec_setup_new_fdt(const struct kimage *image, void *fdt,
unsigned long initrd_load_addr, unsigned long initrd_len,
const char *cmdline);
+int ima_get_kexec_buffer(void **addr, size_t *size);
+int ima_free_kexec_buffer(void);
#else /* CONFIG_OF */
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 8e8b1e3cb847..cc0906cd3cd6 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -24,10 +24,6 @@
#include "../integrity.h"
-#ifdef CONFIG_HAVE_IMA_KEXEC
-#include <asm/ima.h>
-#endif
-
enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8, TPM_PCR10 = 10 };
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
index 95513c97ce8f..c62bbb586d2e 100644
--- a/security/integrity/ima/ima_kexec.c
+++ b/security/integrity/ima/ima_kexec.c
@@ -10,6 +10,7 @@
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/kexec.h>
+#include <linux/of.h>
#include "ima.h"
#ifdef CONFIG_IMA_KEXEC
--
2.30.0
^ permalink raw reply related
* [PATCH v15 05/10] ima: Move arch_ima_add_kexec_buffer() to ima
From: Lakshmi Ramasubramanian @ 2021-01-15 17:30 UTC (permalink / raw)
To: zohar, bauerman, robh, takahiro.akashi, gregkh, will,
catalin.marinas, mpe
Cc: mark.rutland, bhsharma, tao.li, paulus, vincenzo.frascino,
frowand.list, sashal, masahiroy, jmorris, linux-arm-kernel, serge,
devicetree, pasha.tatashin, prsriva, hsinyi, allison,
christophe.leroy, mbrugger, balajib, dmitry.kasatkin,
linux-kernel, james.morse, linux-integrity, linuxppc-dev
In-Reply-To: <20210115173017.30617-1-nramas@linux.microsoft.com>
arch_ima_add_kexec_buffer() defined in "arch/powerpc/kexec/ima.c"
sets up the address and size of the IMA measurement list in
the architecture specific fields in kimage struct. This function does not
have architecture specific code, but is currently limited to powerpc.
Move arch_ima_add_kexec_buffer() to ima.
Co-developed-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
Signed-off-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
---
arch/powerpc/include/asm/ima.h | 3 ---
arch/powerpc/kexec/ima.c | 17 -----------------
security/integrity/ima/ima_kexec.c | 21 +++++++++++++++++++++
3 files changed, 21 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h
index ead488cf3981..51f64fd06c19 100644
--- a/arch/powerpc/include/asm/ima.h
+++ b/arch/powerpc/include/asm/ima.h
@@ -14,9 +14,6 @@ static inline void remove_ima_buffer(void *fdt, int chosen_node) {}
#endif
#ifdef CONFIG_IMA_KEXEC
-int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
- size_t size);
-
int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node);
#else
static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
diff --git a/arch/powerpc/kexec/ima.c b/arch/powerpc/kexec/ima.c
index 720e50e490b6..7378d59c0c1e 100644
--- a/arch/powerpc/kexec/ima.c
+++ b/arch/powerpc/kexec/ima.c
@@ -128,23 +128,6 @@ void remove_ima_buffer(void *fdt, int chosen_node)
}
#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) {
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
index 121de3e04af2..95513c97ce8f 100644
--- a/security/integrity/ima/ima_kexec.c
+++ b/security/integrity/ima/ima_kexec.c
@@ -71,6 +71,27 @@ static int ima_dump_measurement_list(unsigned long *buffer_size, void **buffer,
return ret;
}
+/**
+ * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA buffer
+ *
+ * @image: kimage struct to set IMA buffer data
+ * @load_addr: Starting address where IMA buffer is loaded at
+ * @size: Number of bytes in 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.
+ */
+static 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;
+}
+
/*
* Called during kexec_file_load so that IMA can add a segment to the kexec
* image for the measurement list for the next kernel.
--
2.30.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox