Changes representative of linux-3.10.0-1062.12.1.el7.tar.xz

Makefile

@@ -5,7 +5,7 @@ EXTRAVERSION =
 NAME = Unicycling Gorilla
 RHEL_MAJOR = 7
 RHEL_MINOR = 7
-RHEL_RELEASE = 1062.9.1
+RHEL_RELEASE = 1062.12.1
 
 #
 # DRM backport version

arch/powerpc/platforms/pseries/lpar.c

@@ -64,6 +64,22 @@ EXPORT_SYMBOL(plpar_hcall);
 EXPORT_SYMBOL(plpar_hcall9);
 EXPORT_SYMBOL(plpar_hcall_norets);
 
+/*
+ * H_BLOCK_REMOVE supported block size for this page size in segment who's base
+ * page size is that page size.
+ *
+ * The first index is the segment base page size, the second one is the actual
+ * page size.
+ */
+static int hblkrm_size[MMU_PAGE_COUNT][MMU_PAGE_COUNT];
+
+/*
+ * Due to the involved complexity, and that the current hypervisor is only
+ * returning this value or 0, we are limiting the support of the H_BLOCK_REMOVE
+ * buffer size to 8 size block.
+ */
+#define HBLKRM_SUPPORTED_BLOCK_SIZE 8
+
 extern void pSeries_find_serial_port(void);
 
 void vpa_init(int cpu)
@@ -433,6 +449,17 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 #define HBLKR_CTRL_ERRNOTFOUND	0x8800000000000000UL
 #define HBLKR_CTRL_ERRBUSY	0xa000000000000000UL
 
+/*
+ * Returned true if we are supporting this block size for the specified segment
+ * base page size and actual page size.
+ *
+ * Currently, we only support 8 size block.
+ */
+static inline bool is_supported_hlbkrm(int bpsize, int psize)
+{
+	return (hblkrm_size[bpsize][psize] == HBLKRM_SUPPORTED_BLOCK_SIZE);
+}
+
 /**
  * H_BLOCK_REMOVE caller.
  * @idx should point to the latest @param entry set with a PTEX.
@@ -591,7 +618,8 @@ static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
 	if (lock_tlbie)
 		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
-	if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+	/* Assuming THP size is 16M */
+	if (is_supported_hlbkrm(psize, MMU_PAGE_16M))
 		hugepage_block_invalidate(slot, vpn, count, psize, ssize);
 	else
 		hugepage_bulk_invalidate(slot, vpn, count, psize, ssize);
@@ -747,6 +775,140 @@ static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch,
 		(void)call_block_remove(pix, param, true);
 }
 
+/*
+ * TLB Block Invalidate Characteristics
+ *
+ * These characteristics define the size of the block the hcall H_BLOCK_REMOVE
+ * is able to process for each couple segment base page size, actual page size.
+ *
+ * The ibm,get-system-parameter properties is returning a buffer with the
+ * following layout:
+ *
+ * [ 2 bytes size of the RTAS buffer (excluding these 2 bytes) ]
+ * -----------------
+ * TLB Block Invalidate Specifiers:
+ * [ 1 byte LOG base 2 of the TLB invalidate block size being specified ]
+ * [ 1 byte Number of page sizes (N) that are supported for the specified
+ *          TLB invalidate block size ]
+ * [ 1 byte Encoded segment base page size and actual page size
+ *          MSB=0 means 4k segment base page size and actual page size
+ *          MSB=1 the penc value in mmu_psize_def ]
+ * ...
+ * -----------------
+ * Next TLB Block Invalidate Specifiers...
+ * -----------------
+ * [ 0 ]
+ */
+static inline void set_hblkrm_bloc_size(int bpsize, int psize,
+					unsigned int block_size)
+{
+	if (block_size > hblkrm_size[bpsize][psize])
+		hblkrm_size[bpsize][psize] = block_size;
+}
+
+/*
+ * Decode the Encoded segment base page size and actual page size.
+ * PAPR specifies:
+ *   - bit 7 is the L bit
+ *   - bits 0-5 are the penc value
+ * If the L bit is 0, this means 4K segment base page size and actual page size
+ * otherwise the penc value should be read.
+ */
+#define HBLKRM_L_MASK		0x80
+#define HBLKRM_PENC_MASK	0x3f
+static inline void __init check_lp_set_hblkrm(unsigned int lp,
+					      unsigned int block_size)
+{
+	unsigned int bpsize, psize;
+
+	/* First, check the L bit, if not set, this means 4K */
+	if ((lp & HBLKRM_L_MASK) == 0) {
+		set_hblkrm_bloc_size(MMU_PAGE_4K, MMU_PAGE_4K, block_size);
+		return;
+	}
+
+	lp &= HBLKRM_PENC_MASK;
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) {
+		struct mmu_psize_def *def = &mmu_psize_defs[bpsize];
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+			if (def->penc[psize] == lp) {
+				set_hblkrm_bloc_size(bpsize, psize, block_size);
+				return;
+			}
+		}
+	}
+}
+
+#define SPLPAR_TLB_BIC_TOKEN		50
+
+/*
+ * The size of the TLB Block Invalidate Characteristics is variable. But at the
+ * maximum it will be the number of possible page sizes *2 + 10 bytes.
+ * Currently MMU_PAGE_COUNT is 16, which means 42 bytes. Use a cache line size
+ * (128 bytes) for the buffer to get plenty of space.
+ */
+#define SPLPAR_TLB_BIC_MAXLENGTH	128
+
+void __init pseries_lpar_read_hblkrm_characteristics(void)
+{
+	unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH];
+	int call_status, len, idx, bpsize;
+
+	if (!firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+		return;
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_TLB_BIC_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH);
+	local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0';
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		pr_warn("%s %s Error calling get-system-parameter (0x%x)\n",
+			__FILE__, __func__, call_status);
+		return;
+	}
+
+	/*
+	 * The first two (2) bytes of the data in the buffer are the length of
+	 * the returned data, not counting these first two (2) bytes.
+	 */
+	len = be16_to_cpu(*((u16 *)local_buffer)) + 2;
+	if (len > SPLPAR_TLB_BIC_MAXLENGTH) {
+		pr_warn("%s too large returned buffer %d", __func__, len);
+		return;
+	}
+
+	idx = 2;
+	while (idx < len) {
+		u8 block_shift = local_buffer[idx++];
+		u32 block_size;
+		unsigned int npsize;
+
+		if (!block_shift)
+			break;
+
+		block_size = 1 << block_shift;
+
+		for (npsize = local_buffer[idx++];
+		     npsize > 0 && idx < len; npsize--)
+			check_lp_set_hblkrm((unsigned int) local_buffer[idx++],
+					    block_size);
+	}
+
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
+		for (idx = 0; idx < MMU_PAGE_COUNT; idx++)
+			if (hblkrm_size[bpsize][idx])
+				pr_info("H_BLOCK_REMOVE supports base psize:%d psize:%d block size:%d",
+					bpsize, idx, hblkrm_size[bpsize][idx]);
+}
+
 /*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
@@ -766,7 +928,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 	if (lock_tlbie)
 		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
-	if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) {
+	if (is_supported_hlbkrm(batch->psize, batch->psize)) {
 		do_block_remove(number, batch, param);
 		goto out;
 	}

arch/powerpc/platforms/pseries/pseries.h

@@ -95,5 +95,6 @@ unsigned long pseries_memory_block_size(void);
 int dlpar_workqueue_init(void);
 
 void pseries_setup_rfi_flush(void);
+void pseries_lpar_read_hblkrm_characteristics(void);
 
 #endif /* _PSERIES_PSERIES_H */

arch/powerpc/platforms/pseries/setup.c

@@ -631,6 +631,7 @@ static void __init pSeries_setup_arch(void)
 
 	pseries_setup_rfi_flush();
 	setup_stf_barrier();
+	pseries_lpar_read_hblkrm_characteristics();
 
 	/* By default, only probe PCI (can be overriden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);

arch/x86/include/asm/atomic.h

@@ -48,7 +48,7 @@ static __always_inline void atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -62,7 +62,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -93,7 +93,7 @@ static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
 static __always_inline void atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 
 /**
@@ -105,7 +105,7 @@ static __always_inline void atomic_inc(atomic_t *v)
 static __always_inline void atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 
 /**

arch/x86/include/asm/atomic64_64.h

@@ -44,7 +44,7 @@ static __always_inline void atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -58,7 +58,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -90,7 +90,7 @@ static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 
 /**
@@ -103,7 +103,7 @@ static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 
 /**

arch/x86/include/asm/barrier.h

@@ -115,8 +115,8 @@ do {									\
 #endif
 
 /* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic()	barrier()
-#define smp_mb__after_atomic()	barrier()
+#define smp_mb__before_atomic()	do { } while (0)
+#define smp_mb__after_atomic()	do { } while (0)
 
 /*
  * Stop RDTSC speculation. This is needed when you need to use RDTSC

arch/x86/include/asm/cpuidle_haltpoll.h

@@ -2,7 +2,7 @@
 #ifndef _ARCH_HALTPOLL_H
 #define _ARCH_HALTPOLL_H
 
-void arch_haltpoll_enable(void);
-void arch_haltpoll_disable(void);
+void arch_haltpoll_enable(unsigned int cpu);
+void arch_haltpoll_disable(unsigned int cpu);
 
 #endif

arch/x86/kernel/kvm.c

@@ -939,32 +939,26 @@ static void kvm_enable_host_haltpoll(void *i)
 	wrmsrl(MSR_KVM_POLL_CONTROL, 1);
 }
 
-void arch_haltpoll_enable(void)
+void arch_haltpoll_enable(unsigned int cpu)
 {
 	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
-		printk(KERN_ERR "kvm: host does not support poll control\n");
-		printk(KERN_ERR "kvm: host upgrade recommended\n");
+		pr_err_once("kvm: host does not support poll control\n");
+		pr_err_once("kvm: host upgrade recommended\n");
 		return;
 	}
 
-	preempt_disable();
 	/* Enable guest halt poll disables host halt poll */
-	kvm_disable_host_haltpoll(NULL);
-	smp_call_function(kvm_disable_host_haltpoll, NULL, 1);
-	preempt_enable();
+	smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(arch_haltpoll_enable);
 
-void arch_haltpoll_disable(void)
+void arch_haltpoll_disable(unsigned int cpu)
 {
 	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
 		return;
 
-	preempt_disable();
 	/* Enable guest halt poll disables host halt poll */
-	kvm_enable_host_haltpoll(NULL);
-	smp_call_function(kvm_enable_host_haltpoll, NULL, 1);
-	preempt_enable();
+	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
 #endif