summaryrefslogtreecommitdiff
path: root/arch/powerpc/perf/core-book3s.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-12-18 00:34:25 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-12-18 00:34:25 +0300
commit8a5be36b9303ae167468d4f5e1b3c090b9981396 (patch)
treeddf1721677782484bab6369a87f13611eafb879a /arch/powerpc/perf/core-book3s.c
parent09c0796adf0c793462fda1d7c8c43324551405c7 (diff)
parentc1bea0a840ac75dca19bc6aa05575a33eb9fd058 (diff)
downloadlinux-8a5be36b9303ae167468d4f5e1b3c090b9981396.tar.xz
Merge tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: - Switch to the generic C VDSO, as well as some cleanups of our VDSO setup/handling code. - Support for KUAP (Kernel User Access Prevention) on systems using the hashed page table MMU, using memory protection keys. - Better handling of PowerVM SMT8 systems where all threads of a core do not share an L2, allowing the scheduler to make better scheduling decisions. - Further improvements to our machine check handling. - Show registers when unwinding interrupt frames during stack traces. - Improvements to our pseries (PowerVM) partition migration code. - Several series from Christophe refactoring and cleaning up various parts of the 32-bit code. - Other smaller features, fixes & cleanups. Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King, Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz, Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour, Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu. * tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits) powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug powerpc: Add config fragment for disabling -Werror powerpc/configs: Add ppc64le_allnoconfig target powerpc/powernv: Rate limit opal-elog read failure message powerpc/pseries/memhotplug: Quieten some DLPAR operations powerpc/ps3: use dma_mapping_error() powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10 powerpc/perf: Fix Threshold Event Counter Multiplier width for P10 powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range() KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp KVM: PPC: fix comparison to bool warning KVM: PPC: Book3S: Assign boolean values to a bool variable powerpc: Inline setup_kup() powerpc/64s: Mark the kuap/kuep functions non __init KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering powerpc/xive: Improve error reporting of OPAL calls powerpc/xive: Simplify xive_do_source_eoi() powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG ...
Diffstat (limited to 'arch/powerpc/perf/core-book3s.c')
-rw-r--r--arch/powerpc/perf/core-book3s.c65
1 files changed, 59 insertions, 6 deletions
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6586f7e71cfb..28206b1fe172 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -95,6 +95,7 @@ static unsigned int freeze_events_kernel = MMCR0_FCS;
#define SPRN_SIER3 0
#define MMCRA_SAMPLE_ENABLE 0
#define MMCRA_BHRB_DISABLE 0
+#define MMCR0_PMCCEXT 0
static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
{
@@ -137,6 +138,9 @@ static void pmao_restore_workaround(bool ebb) { }
bool is_sier_available(void)
{
+ if (!ppmu)
+ return false;
+
if (ppmu->flags & PPMU_HAS_SIER)
return true;
@@ -250,11 +254,32 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
static inline u32 perf_get_misc_flags(struct pt_regs *regs)
{
bool use_siar = regs_use_siar(regs);
+ unsigned long mmcra = regs->dsisr;
+ int marked = mmcra & MMCRA_SAMPLE_ENABLE;
if (!use_siar)
return perf_flags_from_msr(regs);
/*
+ * Check the address in SIAR to identify the
+ * privilege levels since the SIER[MSR_HV, MSR_PR]
+ * bits are not set for marked events in power10
+ * DD1.
+ */
+ if (marked && (ppmu->flags & PPMU_P10_DD1)) {
+ unsigned long siar = mfspr(SPRN_SIAR);
+ if (siar) {
+ if (is_kernel_addr(siar))
+ return PERF_RECORD_MISC_KERNEL;
+ return PERF_RECORD_MISC_USER;
+ } else {
+ if (is_kernel_addr(regs->nip))
+ return PERF_RECORD_MISC_KERNEL;
+ return PERF_RECORD_MISC_USER;
+ }
+ }
+
+ /*
* If we don't have flags in MMCRA, rather than using
* the MSR, we intuit the flags from the address in
* SIAR which should give slightly more reliable
@@ -350,7 +375,14 @@ static inline int siar_valid(struct pt_regs *regs)
int marked = mmcra & MMCRA_SAMPLE_ENABLE;
if (marked) {
- if (ppmu->flags & PPMU_HAS_SIER)
+ /*
+ * SIER[SIAR_VALID] is not set for some
+ * marked events on power10 DD1, so drop
+ * the check for SIER[SIAR_VALID] and return true.
+ */
+ if (ppmu->flags & PPMU_P10_DD1)
+ return 0x1;
+ else if (ppmu->flags & PPMU_HAS_SIER)
return regs->dar & SIER_SIAR_VALID;
if (ppmu->flags & PPMU_SIAR_VALID)
@@ -1242,6 +1274,9 @@ static void power_pmu_disable(struct pmu *pmu)
val |= MMCR0_FC;
val &= ~(MMCR0_EBE | MMCR0_BHRBA | MMCR0_PMCC | MMCR0_PMAO |
MMCR0_FC56);
+ /* Set mmcr0 PMCCEXT for p10 */
+ if (ppmu->flags & PPMU_ARCH_31)
+ val |= MMCR0_PMCCEXT;
/*
* The barrier is to make sure the mtspr has been
@@ -1881,7 +1916,7 @@ static bool is_event_blacklisted(u64 ev)
static int power_pmu_event_init(struct perf_event *event)
{
u64 ev;
- unsigned long flags;
+ unsigned long flags, irq_flags;
struct perf_event *ctrs[MAX_HWEVENTS];
u64 events[MAX_HWEVENTS];
unsigned int cflags[MAX_HWEVENTS];
@@ -1989,7 +2024,9 @@ static int power_pmu_event_init(struct perf_event *event)
if (check_excludes(ctrs, cflags, n, 1))
return -EINVAL;
- cpuhw = &get_cpu_var(cpu_hw_events);
+ local_irq_save(irq_flags);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
+
err = power_check_constraints(cpuhw, events, cflags, n + 1);
if (has_branch_stack(event)) {
@@ -2000,13 +2037,13 @@ static int power_pmu_event_init(struct perf_event *event)
event->attr.branch_sample_type);
if (bhrb_filter == -1) {
- put_cpu_var(cpu_hw_events);
+ local_irq_restore(irq_flags);
return -EOPNOTSUPP;
}
cpuhw->bhrb_filter = bhrb_filter;
}
- put_cpu_var(cpu_hw_events);
+ local_irq_restore(irq_flags);
if (err)
return -EINVAL;
@@ -2125,6 +2162,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
perf_event_update_userpage(event);
/*
+ * Due to hardware limitation, sometimes SIAR could sample a kernel
+ * address even when freeze on supervisor state (kernel) is set in
+ * MMCR2. Check attr.exclude_kernel and address to drop the sample in
+ * these cases.
+ */
+ if (event->attr.exclude_kernel && record)
+ if (is_kernel_addr(mfspr(SPRN_SIAR)))
+ record = 0;
+
+ /*
* Finally record data if requested.
*/
if (record) {
@@ -2180,8 +2227,14 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
bool use_siar = regs_use_siar(regs);
+ unsigned long siar = mfspr(SPRN_SIAR);
- if (use_siar && siar_valid(regs))
+ if (ppmu->flags & PPMU_P10_DD1) {
+ if (siar)
+ return siar;
+ else
+ return regs->nip;
+ } else if (use_siar && siar_valid(regs))
return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
else if (use_siar)
return 0; // no valid instruction pointer