summaryrefslogtreecommitdiff
path: root/arch/powerpc/perf
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-05 22:39:30 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-05 22:39:30 +0300
commit7ae77150d94d3b535c7b85e6b3647113095e79bf (patch)
tree90fe894e7efd92898e813d88acfd4611d79be969 /arch/powerpc/perf
parent084623e468d535d98f883cc2ccf2c4fdf2108556 (diff)
parent1395375c592770fe5158a592944aaeed67fa94ff (diff)
downloadlinux-7ae77150d94d3b535c7b85e6b3647113095e79bf.tar.xz
Merge tag 'powerpc-5.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: - Support for userspace to send requests directly to the on-chip GZIP accelerator on Power9. - Rework of our lockless page table walking (__find_linux_pte()) to make it safe against parallel page table manipulations without relying on an IPI for serialisation. - A series of fixes & enhancements to make our machine check handling more robust. - Lots of plumbing to add support for "prefixed" (64-bit) instructions on Power10. - Support for using huge pages for the linear mapping on 8xx (32-bit). - Remove obsolete Xilinx PPC405/PPC440 support, and an associated sound driver. - Removal of some obsolete 40x platforms and associated cruft. - Initial support for booting on Power10. - Lots of other small features, cleanups & fixes. Thanks to: Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan, Andrey Abramov, Aneesh Kumar K.V, Balamuruhan S, Bharata B Rao, Bulent Abali, Cédric Le Goater, Chen Zhou, Christian Zigotzky, Christophe JAILLET, Christophe Leroy, Dmitry Torokhov, Emmanuel Nicolet, Erhard F., Gautham R. Shenoy, Geoff Levand, George Spelvin, Greg Kurz, Gustavo A. R. Silva, Gustavo Walbon, Haren Myneni, Hari Bathini, Joel Stanley, Jordan Niethe, Kajol Jain, Kees Cook, Leonardo Bras, Madhavan Srinivasan., Mahesh Salgaonkar, Markus Elfring, Michael Neuling, Michal Simek, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pingfan Liu, Qian Cai, Ram Pai, Raphael Moreira Zinsly, Ravi Bangoria, Sam Bobroff, Sandipan Das, Segher Boessenkool, Stephen Rothwell, Sukadev Bhattiprolu, Tyrel Datwyler, Wolfram Sang, Xiongfeng Wang. * tag 'powerpc-5.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (299 commits) powerpc/pseries: Make vio and ibmebus initcalls pseries specific cxl: Remove dead Kconfig options powerpc: Add POWER10 architected mode powerpc/dt_cpu_ftrs: Add MMA feature powerpc/dt_cpu_ftrs: Enable Prefixed Instructions powerpc/dt_cpu_ftrs: Advertise support for ISA v3.1 if selected powerpc: Add support for ISA v3.1 powerpc: Add new HWCAP bits powerpc/64s: Don't set FSCR bits in INIT_THREAD powerpc/64s: Save FSCR to init_task.thread.fscr after feature init powerpc/64s: Don't let DT CPU features set FSCR_DSCR powerpc/64s: Don't init FSCR_DSCR in __init_FSCR() powerpc/32s: Fix another build failure with CONFIG_PPC_KUAP_DEBUG powerpc/module_64: Use special stub for _mcount() with -mprofile-kernel powerpc/module_64: Simplify check for -mprofile-kernel ftrace relocations powerpc/module_64: Consolidate ftrace code powerpc/32: Disable KASAN with pages bigger than 16k powerpc/uaccess: Don't set KUEP by default on book3s/32 powerpc/uaccess: Don't set KUAP by default on book3s/32 powerpc/8xx: Reduce time spent in allow_user_access() and friends ...
Diffstat (limited to 'arch/powerpc/perf')
-rw-r--r--arch/powerpc/perf/8xx-pmu.c19
-rw-r--r--arch/powerpc/perf/callchain_64.c46
-rw-r--r--arch/powerpc/perf/core-book3s.c4
-rw-r--r--arch/powerpc/perf/hv-24x7.c96
4 files changed, 107 insertions, 58 deletions
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 1ad03c55c88c..e53c3c161257 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -15,6 +15,7 @@
#include <asm/firmware.h>
#include <asm/ptrace.h>
#include <asm/code-patching.h>
+#include <asm/inst.h>
#define PERF_8xx_ID_CPU_CYCLES 1
#define PERF_8xx_ID_HW_INSTRUCTIONS 2
@@ -99,9 +100,6 @@ static int mpc8xx_pmu_add(struct perf_event *event, int flags)
unsigned long target = patch_site_addr(&patch__itlbmiss_perf);
patch_branch_site(&patch__itlbmiss_exit_1, target, 0);
-#ifndef CONFIG_PIN_TLB_TEXT
- patch_branch_site(&patch__itlbmiss_exit_2, target, 0);
-#endif
}
val = itlb_miss_counter;
break;
@@ -110,8 +108,6 @@ static int mpc8xx_pmu_add(struct perf_event *event, int flags)
unsigned long target = patch_site_addr(&patch__dtlbmiss_perf);
patch_branch_site(&patch__dtlbmiss_exit_1, target, 0);
- patch_branch_site(&patch__dtlbmiss_exit_2, target, 0);
- patch_branch_site(&patch__dtlbmiss_exit_3, target, 0);
}
val = dtlb_miss_counter;
break;
@@ -170,24 +166,19 @@ static void mpc8xx_pmu_del(struct perf_event *event, int flags)
case PERF_8xx_ID_ITLB_LOAD_MISS:
if (atomic_dec_return(&itlb_miss_ref) == 0) {
/* mfspr r10, SPRN_SPRG_SCRATCH0 */
- unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
- __PPC_SPR(SPRN_SPRG_SCRATCH0);
+ struct ppc_inst insn = ppc_inst(PPC_INST_MFSPR | __PPC_RS(R10) |
+ __PPC_SPR(SPRN_SPRG_SCRATCH0));
patch_instruction_site(&patch__itlbmiss_exit_1, insn);
-#ifndef CONFIG_PIN_TLB_TEXT
- patch_instruction_site(&patch__itlbmiss_exit_2, insn);
-#endif
}
break;
case PERF_8xx_ID_DTLB_LOAD_MISS:
if (atomic_dec_return(&dtlb_miss_ref) == 0) {
/* mfspr r10, SPRN_DAR */
- unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
- __PPC_SPR(SPRN_DAR);
+ struct ppc_inst insn = ppc_inst(PPC_INST_MFSPR | __PPC_RS(R10) |
+ __PPC_SPR(SPRN_DAR));
patch_instruction_site(&patch__dtlbmiss_exit_1, insn);
- patch_instruction_site(&patch__dtlbmiss_exit_2, insn);
- patch_instruction_site(&patch__dtlbmiss_exit_3, insn);
}
break;
}
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index df1ffd8b20f2..b63086b663ef 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -26,43 +26,25 @@
*/
int read_user_stack_slow(void __user *ptr, void *buf, int nb)
{
- int ret = -EFAULT;
- pgd_t *pgdir;
- pte_t *ptep, pte;
- unsigned int shift;
+
unsigned long addr = (unsigned long) ptr;
unsigned long offset;
- unsigned long pfn, flags;
+ struct page *page;
+ int nrpages;
void *kaddr;
- pgdir = current->mm->pgd;
- if (!pgdir)
- return -EFAULT;
+ nrpages = __get_user_pages_fast(addr, 1, 1, &page);
+ if (nrpages == 1) {
+ kaddr = page_address(page);
+
+ /* align address to page boundary */
+ offset = addr & ~PAGE_MASK;
- local_irq_save(flags);
- ptep = find_current_mm_pte(pgdir, addr, NULL, &shift);
- if (!ptep)
- goto err_out;
- if (!shift)
- shift = PAGE_SHIFT;
-
- /* align address to page boundary */
- offset = addr & ((1UL << shift) - 1);
-
- pte = READ_ONCE(*ptep);
- if (!pte_present(pte) || !pte_user(pte))
- goto err_out;
- pfn = pte_pfn(pte);
- if (!page_is_ram(pfn))
- goto err_out;
-
- /* no highmem to worry about here */
- kaddr = pfn_to_kaddr(pfn);
- memcpy(buf, kaddr + offset, nb);
- ret = 0;
-err_out:
- local_irq_restore(flags);
- return ret;
+ memcpy(buf, kaddr + offset, nb);
+ put_page(page);
+ return 0;
+ }
+ return -EFAULT;
}
static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3dcfecf858f3..13b9dd5e4a76 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -421,14 +421,14 @@ static __u64 power_pmu_bhrb_to(u64 addr)
if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
return 0;
- return branch_target(&instr);
+ return branch_target((struct ppc_inst *)&instr);
}
/* Userspace: need copy instruction here then translate it */
if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr)))
return 0;
- target = branch_target(&instr);
+ target = branch_target((struct ppc_inst *)&instr);
if ((!target) || (instr & BRANCH_ABSOLUTE))
return target;
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 573e0b309c0c..db213eb7cb02 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -20,6 +20,7 @@
#include <asm/io.h>
#include <linux/byteorder/generic.h>
+#include <asm/rtas.h>
#include "hv-24x7.h"
#include "hv-24x7-catalog.h"
#include "hv-common.h"
@@ -57,6 +58,65 @@ static bool is_physical_domain(unsigned domain)
}
}
+/*
+ * The Processor Module Information system parameter allows transferring
+ * of certain processor module information from the platform to the OS.
+ * Refer PAPR+ document to get parameter token value as '43'.
+ */
+
+#define PROCESSOR_MODULE_INFO 43
+
+static u32 phys_sockets; /* Physical sockets */
+static u32 phys_chipspersocket; /* Physical chips per socket*/
+static u32 phys_coresperchip; /* Physical cores per chip */
+
+/*
+ * read_24x7_sys_info()
+ * Retrieve the number of sockets and chips per socket and cores per
+ * chip details through the get-system-parameter rtas call.
+ */
+void read_24x7_sys_info(void)
+{
+ int call_status, len, ntypes;
+
+ spin_lock(&rtas_data_buf_lock);
+
+ /*
+ * Making system parameter: chips and sockets and cores per chip
+ * default to 1.
+ */
+ phys_sockets = 1;
+ phys_chipspersocket = 1;
+ phys_coresperchip = 1;
+
+ call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+ NULL,
+ PROCESSOR_MODULE_INFO,
+ __pa(rtas_data_buf),
+ RTAS_DATA_BUF_SIZE);
+
+ if (call_status != 0) {
+ pr_err("Error calling get-system-parameter %d\n",
+ call_status);
+ } else {
+ len = be16_to_cpup((__be16 *)&rtas_data_buf[0]);
+ if (len < 8)
+ goto out;
+
+ ntypes = be16_to_cpup((__be16 *)&rtas_data_buf[2]);
+
+ if (!ntypes)
+ goto out;
+
+ phys_sockets = be16_to_cpup((__be16 *)&rtas_data_buf[4]);
+ phys_chipspersocket = be16_to_cpup((__be16 *)&rtas_data_buf[6]);
+ phys_coresperchip = be16_to_cpup((__be16 *)&rtas_data_buf[8]);
+ }
+
+out:
+ spin_unlock(&rtas_data_buf_lock);
+}
+
/* Domains for which more than one result element are returned for each event. */
static bool domain_needs_aggregation(unsigned int domain)
{
@@ -386,6 +446,24 @@ static ssize_t device_show_string(struct device *dev,
return sprintf(buf, "%s\n", (char *)d->var);
}
+static ssize_t sockets_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", phys_sockets);
+}
+
+static ssize_t chipspersocket_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", phys_chipspersocket);
+}
+
+static ssize_t coresperchip_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", phys_coresperchip);
+}
+
static struct attribute *device_str_attr_create_(char *name, char *str)
{
struct dev_ext_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
@@ -1032,6 +1110,9 @@ PAGE_0_ATTR(catalog_len, "%lld\n",
(unsigned long long)be32_to_cpu(page_0->length) * 4096);
static BIN_ATTR_RO(catalog, 0/* real length varies */);
static DEVICE_ATTR_RO(domains);
+static DEVICE_ATTR_RO(sockets);
+static DEVICE_ATTR_RO(chipspersocket);
+static DEVICE_ATTR_RO(coresperchip);
static struct bin_attribute *if_bin_attrs[] = {
&bin_attr_catalog,
@@ -1042,6 +1123,9 @@ static struct attribute *if_attrs[] = {
&dev_attr_catalog_len.attr,
&dev_attr_catalog_version.attr,
&dev_attr_domains.attr,
+ &dev_attr_sockets.attr,
+ &dev_attr_chipspersocket.attr,
+ &dev_attr_coresperchip.attr,
NULL,
};
@@ -1400,16 +1484,6 @@ static void h_24x7_event_read(struct perf_event *event)
h24x7hw = &get_cpu_var(hv_24x7_hw);
h24x7hw->events[i] = event;
put_cpu_var(h24x7hw);
- /*
- * Clear the event count so we can compute the _change_
- * in the 24x7 raw counter value at the end of the txn.
- *
- * Note that we could alternatively read the 24x7 value
- * now and save its value in event->hw.prev_count. But
- * that would require issuing a hcall, which would then
- * defeat the purpose of using the txn interface.
- */
- local64_set(&event->count, 0);
}
put_cpu_var(hv_24x7_reqb);
@@ -1615,6 +1689,8 @@ static int hv_24x7_init(void)
if (r)
return r;
+ read_24x7_sys_info();
+
return 0;
}