Merge tag 'powerpc-4.14-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "A fix for a bad bug (written by me) in our livepatch handler. Removal
  of an over-zealous lockdep_assert_cpus_held() in our topology code. A
  fix to the recently added emulation of cntlz[wd]. And three small
  fixes to the recently added IMC PMU driver.

  Thanks to: Anju T Sudhakar, Balbir Singh, Kamalesh Babulal, Naveen N.
  Rao, Sandipan Das, Santosh Sivaraj, Thiago Jung Bauermann"

* tag 'powerpc-4.14-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/perf: Fix IMC initialization crash
  powerpc/perf: Add ___GFP_NOWARN flag to alloc_pages_node()
  powerpc/perf: Fix for core/nest imc call trace on cpuhotplug
  powerpc: Don't call lockdep_assert_cpus_held() from arch_update_cpu_topology()
  powerpc/lib/sstep: Fix count leading zeros instructions
  powerpc/livepatch: Fix livepatch stack access

4 files changed, 53 insertions, 38 deletions

diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index c98e90b4ea7b..b4e2b7165f79 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub)
          *  - we have no stack frame and can not allocate one
          *  - LR points back to the original caller (in A)
          *  - CTR holds the new NIP in C
-         *  - r0 & r12 are free
-         *
-         * r0 can't be used as the base register for a DS-form load or store, so
-         * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+         *  - r0, r11 & r12 are free
          */
 livepatch_handler:
         CURRENT_THREAD_INFO(r12, r1)
 
-        /* Save stack pointer into r0 */
-        mr      r0, r1
-
         /* Allocate 3 x 8 bytes */
-        ld      r1, TI_livepatch_sp(r12)
-        addi    r1, r1, 24
-        std     r1, TI_livepatch_sp(r12)
+        ld      r11, TI_livepatch_sp(r12)
+        addi    r11, r11, 24
+        std     r11, TI_livepatch_sp(r12)
 
         /* Save toc & real LR on livepatch stack */
-        std     r2,  -24(r1)
+        std     r2,  -24(r11)
         mflr    r12
-        std     r12, -16(r1)
+        std     r12, -16(r11)
 
         /* Store stack end marker */
         lis     r12, STACK_END_MAGIC@h
         ori     r12, r12, STACK_END_MAGIC@l
-        std     r12, -8(r1)
-
-        /* Restore real stack pointer */
-        mr      r1, r0
+        std     r12, -8(r11)
 
         /* Put ctr in r12 for global entry and branch there */
         mfctr   r12
@@ -216,36 +207,30 @@ livepatch_handler:
 
         /*
          * Now we are returning from the patched function to the original
-         * caller A. We are free to use r0 and r12, and we can use r2 until we
+         * caller A. We are free to use r11, r12 and we can use r2 until we
          * restore it.
          */
 
         CURRENT_THREAD_INFO(r12, r1)
 
-        /* Save stack pointer into r0 */
-        mr      r0, r1
-
-        ld      r1, TI_livepatch_sp(r12)
+        ld      r11, TI_livepatch_sp(r12)
 
         /* Check stack marker hasn't been trashed */
         lis     r2,  STACK_END_MAGIC@h
         ori     r2,  r2, STACK_END_MAGIC@l
-        ld      r12, -8(r1)
+        ld      r12, -8(r11)
 1:      tdne    r12, r2
         EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
 
         /* Restore LR & toc from livepatch stack */
-        ld      r12, -16(r1)
+        ld      r12, -16(r11)
         mtlr    r12
-        ld      r2,  -24(r1)
+        ld      r2,  -24(r11)
 
         /* Pop livepatch stack frame */
-        CURRENT_THREAD_INFO(r12, r0)
-        subi    r1, r1, 24
-        std     r1, TI_livepatch_sp(r12)
-
-        /* Restore real stack pointer */
-        mr      r1, r0
+        CURRENT_THREAD_INFO(r12, r1)
+        subi    r11, r11, 24
+        std     r11, TI_livepatch_sp(r12)
 
         /* Return to original caller of live patched function */
         blr
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5e8418c28bd8..f208f560aecd 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
  * Logical instructions
  */
                 case 26:        /* cntlzw */
-                        op->val = __builtin_clz((unsigned int) regs->gpr[rd]);
+                        val = (unsigned int) regs->gpr[rd];
+                        op->val = ( val ? __builtin_clz(val) : 32 );
                         goto logical_done;
 #ifdef __powerpc64__
                 case 58:        /* cntlzd */
-                        op->val = __builtin_clzl(regs->gpr[rd]);
+                        val = regs->gpr[rd];
+                        op->val = ( val ? __builtin_clzl(val) : 64 );
                         goto logical_done;
 #endif
                 case 28:        /* and */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b95c584ce19d..a51df9ef529d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1438,7 +1438,6 @@ out:
 
 int arch_update_cpu_topology(void)
 {
-        lockdep_assert_cpus_held();
         return numa_update_cpu_topology(true);
 }
 
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ccac86f3463..88126245881b 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event)
 
         /* Take the mutex lock for this node and then decrement the reference count */
         mutex_lock(&ref->lock);
+        if (ref->refc == 0) {
+                /*
+                 * The scenario where this is true is, when perf session is
+                 * started, followed by offlining of all cpus in a given node.
+                 *
+                 * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline()
+                 * function set the ref->count to zero, if the cpu which is
+                 * about to offline is the last cpu in a given node and make
+                 * an OPAL call to disable the engine in that node.
+                 *
+                 */
+                mutex_unlock(&ref->lock);
+                return;
+        }
         ref->refc--;
         if (ref->refc == 0) {
                 rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
@@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size)
 
         /* We need only vbase for core counters */
         mem_info->vbase = page_address(alloc_pages_node(phys_id,
-                                          GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
-                                          get_order(size)));
+                                          GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+                                          __GFP_NOWARN, get_order(size)));
         if (!mem_info->vbase)
                 return -ENOMEM;
 
@@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event)
                 return;
 
         mutex_lock(&ref->lock);
+        if (ref->refc == 0) {
+                /*
+                 * The scenario where this is true is, when perf session is
+                 * started, followed by offlining of all cpus in a given core.
+                 *
+                 * In the cpuhotplug offline path, ppc_core_imc_cpu_offline()
+                 * function set the ref->count to zero, if the cpu which is
+                 * about to offline is the last