33 files changed, 307 insertions, 275 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 1344816c4c06..75e3db96dec5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3761,9 +3761,11 @@ F:	include/uapi/linux/gigaset_dev.h
 
 GPIO SUBSYSTEM
 M:      Linus Walleij <linus.walleij@linaro.org>
-S:      Maintained
+M:      Alexandre Courbot <gnurou@gmail.com>
 L:      linux-gpio@vger.kernel.org
-F:      Documentation/gpio.txt
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
+S:      Maintained
+F:      Documentation/gpio/
 F:      drivers/gpio/
 F:      include/linux/gpio*
 F:      include/asm-generic/gpio.h
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 033c06be1d84..7bdcf340016c 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -720,13 +720,13 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val);
+int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
 int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
                        uint32_t addr, uint32_t data, uint32_t sz);
 int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
-                      uint32_t addr, uint32_t *data, uint32_t sz);
+                      uint32_t addr, __be32 *data, uint32_t sz);
 int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
 int64_t opal_manage_flash(uint8_t op);
 int64_t opal_update_flash(uint64_t blk_list);
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 779a78c26435..11c1d069d920 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -124,15 +124,15 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 {
         unsigned long addr;
-        const u32 *basep, *sizep;
+        const __be32 *basep, *sizep;
         unsigned int rtas_start = 0, rtas_end = 0;
 
         basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
         sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 
         if (basep && sizep) {
-                rtas_start = *basep;
-                rtas_end = *basep + *sizep;
+                rtas_start = be32_to_cpup(basep);
+                rtas_end = rtas_start + be32_to_cpup(sizep);
         }
 
         for (addr = begin; addr < end; addr += PAGE_SIZE) {
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 75fb40498b41..2e3d2bf536c5 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1555,7 +1555,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
                         flush_fp_to_thread(child);
                         if (fpidx < (PT_FPSCR - PT_FPR0))
-                                memcpy(&tmp, &child->thread.fp_state.fpr,
+                                memcpy(&tmp, &child->thread.TS_FPR(fpidx),
                                        sizeof(long));
                         else
                                 tmp = child->thread.fp_state.fpscr;
@@ -1588,7 +1588,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
                         flush_fp_to_thread(child);
                         if (fpidx < (PT_FPSCR - PT_FPR0))
-                                memcpy(&child->thread.fp_state.fpr, &data,
+                                memcpy(&child->thread.TS_FPR(fpidx), &data,
                                        sizeof(long));
                         else
                                 child->thread.fp_state.fpscr = data;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index febc80445d25..bc76cc6b419c 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -479,7 +479,7 @@ void __init smp_setup_cpu_maps(void)
         if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) &&
             (dn = of_find_node_by_path("/rtas"))) {
                 int num_addr_cell, num_size_cell, maxcpus;
-                const unsigned int *ireg;
+                const __be32 *ireg;
 
                 num_addr_cell = of_n_addr_cells(dn);
                 num_size_cell = of_n_size_cells(dn);
@@ -489,7 +489,7 @@ void __init smp_setup_cpu_maps(void)
                 if (!ireg)
                         goto out;
 
-                maxcpus = ireg[num_addr_cell + num_size_cell];
+                maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
 
                 /* Double maxcpus for processors which have SMT capability */
                 if (cpu_has_feature(CPU_FTR_SMT))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a3b64f3bf9a2..c1cf4a1522d9 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -580,7 +580,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 int cpu_to_core_id(int cpu)
 {
         struct device_node *np;
-        const int *reg;
+        const __be32 *reg;
         int id = -1;
 
         np = of_get_cpu_node(cpu, NULL);
@@ -591,7 +591,7 @@ int cpu_to_core_id(int cpu)
         if (!reg)
                 goto out;
 
-        id = *reg;
+        id = be32_to_cpup(reg);
 out:
         of_node_put(np);
         return id;
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index e7e59e4f9892..79d83cad3d67 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -24,25 +24,25 @@ static int opal_lpc_chip_id = -1;
 static u8 opal_lpc_inb(unsigned long port)
 {
         int64_t rc;
-        uint32_t data;
+        __be32 data;
 
         if (opal_lpc_chip_id < 0 || port > 0xffff)
                 return 0xff;
         rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
-        return rc ? 0xff : data;
+        return rc ? 0xff : be32_to_cpu(data);
 }
 
 static __le16 __opal_lpc_inw(unsigned long port)
 {
         int64_t rc;
-        uint32_t data;
+        __be32 data;
 
         if (opal_lpc_chip_id < 0 || port > 0xfffe)
                 return 0xffff;
         if (port & 1)
                 return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
         rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
-        return rc ? 0xffff : data;
+        return rc ? 0xffff : be32_to_cpu(data);
 }
 static u16 opal_lpc_inw(unsigned long port)
 {
@@ -52,7 +52,7 @@ static u16 opal_lpc_inw(unsigned long port)
 static __le32 __opal_lpc_inl(unsigned long port)
 {
         int64_t rc;
-        uint32_t data;
+        __be32 data;
 
         if (opal_lpc_chip_id < 0 || port > 0xfffc)
                 return 0xffffffff;
@@ -62,7 +62,7 @@ static __le32 __opal_lpc_inl(unsigned long port)
                        (__le32)opal_lpc_inb(port + 2) <<  8 |
                                opal_lpc_inb(port + 3);
         rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
-        return rc ? 0xffffffff : data;
+        return rc ? 0xffffffff : be32_to_cpu(data);
 }
 
 static u32 opal_lpc_inl(unsigned long port)
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4d99a8fd55ac..4fbf276ac99e 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -96,9 +96,11 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
 {
         struct opal_scom_map *m = map;
         int64_t rc;
+        __be64 v;
 
         reg = opal_scom_unmangle(reg);
-        rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value));
+        rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+        *value = be64_to_cpu(v);
         return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e738007eae64..c9fecf09b8fa 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -157,7 +157,7 @@ static void parse_ppp_data(struct seq_file *m)
 {
         struct hvcall_ppp_data ppp_data;
         struct device_node *root;
-        const int *perf_level;
+        const __be32 *perf_level;
         int rc;
 
         rc = h_get_ppp(&ppp_data);
@@ -201,7 +201,7 @@ static void parse_ppp_data(struct seq_file *m)
                 perf_level = of_get_property(root,
                                 "ibm,partition-performance-parameters-level",
                                              NULL);
-                if (perf_level && (*perf_level >= 1)) {
+                if (perf_level && (be32_to_cpup(perf_level) >= 1)) {
                         seq_printf(m,
                             "physical_procs_allocated_to_virtualization=%d\n",
                                    ppp_data.phys_platform_procs);
@@ -435,7 +435,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
         int partition_potential_processors;
         int partition_active_processors;
         struct device_node *rtas_node;
-        const int *lrdrp = NULL;
+        const __be32 *lrdrp = NULL;
 
         rtas_node = of_find_node_by_path("/rtas");
         if (rtas_node)
@@ -444,7 +444,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
         if (lrdrp == NULL) {
                 partition_potential_processors = vdso_data->processorCount;
         } else {
-                partition_potential_processors = *(lrdrp + 4);
+                partition_potential_processors = be32_to_cpup(lrdrp + 4);
         }
         of_node_put(rtas_node);
 
@@ -654,7 +654,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
         const char *model = "";
         const char *system_id = "";
         const char *tmp;
-        const unsigned int *lp_index_ptr;
+        const __be32 *lp_index_ptr;
         unsigned int lp_index = 0;
 
         seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
@@ -670,7 +670,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
                 lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
                                         NULL);
                 if (lp_index_ptr)
-                        lp_index = *lp_index_ptr;
+                        lp_index = be32_to_cpup(lp_index_ptr);
                 of_node_put(rootdn);
         }
         seq_printf(m, "serial_number=%s\n", system_id);
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 6d2f0abce6fa..0c882e83c4ce 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -130,7 +130,8 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 {
         struct device_node *dn;
         struct pci_dn *pdn;
-        const u32 *req_msi;
+        const __be32 *p;
+        u32 req_msi;
 
         pdn = pci_get_pdn(pdev);
         if (!pdn)
@@ -138,19 +139,20 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 
         dn = pdn->node;
 
-        req_msi = of_get_property(dn, prop_name, NULL);
-        if (!req_msi) {
+        p = of_get_property(dn, prop_name, NULL);
+        if (!p) {
                 pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name);
                 return -ENOENT;
         }
 
-        if (*req_msi < nvec) {
+        req_msi = be32_to_cpup(p);
+        if (req_msi < nvec) {
                 pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec);
 
-                if (*req_msi == 0) /* Be paranoid */
+                if (req_msi == 0) /* Be paranoid */
                         return -ENOSPC;
 
-                return *req_msi;
+                return req_msi;
         }
 
         return 0;
@@ -171,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec)
 static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 {
         struct device_node *dn;
-        const u32 *p;
+        const __be32 *p;
 
         dn = of_node_get(pci_device_to_OF_node(dev));
         while (dn) {
@@ -179,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
                 if (p) {
                         pr_debug("rtas_msi: found prop on dn %s\n",
                                 dn->full_name);
-                        *total = *p;
+                        *total = be32_to_cpup(p);
                         return dn;
                 }
 
@@ -232,13 +234,13 @@ struct msi_counts {
 static void *count_non_bridge_devices(struct device_node *dn, void *data)
 {
         struct msi_counts *counts = data;
-        const u32 *p;
+        const __be32 *p;
         u32 class;
 
         pr_debug("rtas_msi: counting %s\n", dn->full_name);
 
         p = of_get_property(dn, "class-code", NULL);
-        class = p ? *p : 0;
+        class = p ? be32_to_cpup(p) : 0;
 
         if ((class >> 8) != PCI_CLASS_BRIDGE_PCI)
                 counts->num_devices++;
@@ -249,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data)
 static void *count_spare_msis(struct device_node *dn, void *data)
 {
         struct msi_counts *counts = data;
-        const u32 *p;
+        const __be32 *p;
         int req;
 
         if (dn == counts->requestor)
@@ -260,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data)
                 req = 0;
                 p = of_get_property(dn, "ibm,req#msi", NULL);
                 if (p)
-                        req = *p;
+                        req = be32_to_cpup(p);
 
                 p = of_get_property(dn, "ibm,req#msi-x", NULL);
                 if (p)
-                        req = max(req, (int)*p);
+                        req = max(req, (int)be32_to_cpup(p));
         }
 
         if (req < counts->quota)
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 7bfaf58d4664..d7096f2f7751 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -43,8 +43,8 @@ static char nvram_buf[NVRW_CNT];	/* assume this is in the first 4GB */
 static DEFINE_SPINLOCK(nvram_lock);
 
 struct err_log_info {
-        int error_type;
-        unsigned int seq_num;
+        __be32 error_type;
+        __be32 seq_num;
 };
 
 struct nvram_os_partition {
@@ -79,9 +79,9 @@ static const char *pseries_nvram_os_partitions[] = {
 };
 
 struct oops_log_info {
-        u16 version;
-        u16 report_length;
-        u64 timestamp;
+        __be16 version;
+        __be16 report_length;
+        __be64 timestamp;
 } __attribute__((packed));
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
@@ -291,8 +291,8 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff,
                 length = part->size;
         }
 
-        info.error_type = err_type;
-        info.seq_num = error_log_cnt;
+        info.error_type = cpu_to_be32(err_type);
+        info.seq_num = cpu_to_be32(error_log_cnt);
 
         tmp_index = part->index;
 
@@ -364,8 +364,8 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff,
         }
 
         if (part->os_partition) {
-                *error_log_cnt = info.seq_num;
-                *err_type = info.error_type;
+                *error_log_cnt = be32_to_cpu(info.seq_num);
+                *err_type = be32_to_cpu(info.error_type);
         }
 
         return 0;
@@ -529,9 +529,9 @@ static int zip_oops(size_t text_len)
                 pr_err("nvram: logging uncompressed oops/panic report\n");
                 return -1;
         }
-        oops_hdr->version = OOPS_HDR_VERSION;
-        oops_hdr->report_length = (u16) zipped_len;
-        oops_hdr->timestamp = get_seconds();
+        oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+        oops_hdr->report_length = cpu_to_be16(zipped_len);
+        oops_hdr->timestamp = cpu_to_be64(get_seconds());
         return 0;
 }
 
@@ -574,9 +574,9 @@ static int nvram_pstore_write(enum pstore_type_id type,
                                 clobbering_unread_rtas_event())
                 return -1;
 
-        oops_hdr->version = OOPS_HDR_VERSION;
-        oops_hdr->report_length = (u16) size;
-        oops_hdr->timestamp = get_seconds();
+        oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+        oops_hdr->report_length = cpu_to_be16(size);
+        oops_hdr->timestamp = cpu_to_be64(get_seconds());
 
         if (compressed)
                 err_type = ERR_TYPE_KERNEL_PANIC_GZ;
@@ -670,16 +670,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
                 size_t length, hdr_size;
 
                 oops_hdr = (struct oops_log_info *)buff;
-                if (oops_hdr->version < OOPS_HDR_VERSION) {
+                if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
                         /* Old format oops header had 2-byte record size */
                         hdr_size = sizeof(u16);
-                        length = oops_hdr->version;
+                        length = be16_to_cpu(oops_hdr->version);
                         time->tv_sec = 0;
                         time->tv_nsec = 0;
                 } else {
                         hdr_size = sizeof(*oops_hdr);
-                        length = oops_hdr->report_length;
-                        time->tv_sec = oops_hdr->timestamp;
+                        length = be16_to_cpu(oops_hdr->report_length);
+                        time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
                         time->tv_nsec = 0;
                 }
                 *buf = kmalloc(length, GFP_KERNEL);
@@ -889,13 +889,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
                 kmsg_dump_get_buffer(dumper, false,
                                      oops_data, oops_data_sz, &text_len);
                 err_type = ERR_TYPE_KERNEL_PANIC;
-                oops_hdr->version = OOPS_HDR_VERSION;
-                oops_hdr->report_length = (u16) text_len;
-                oops_hdr->timestamp = get_seconds();
+                oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+                oops_hdr->report_length = cpu_to_be16(text_len);
+                oops_hdr->timestamp = cpu_to_be64(get_seconds());
         }
 
         (void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-                (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+                (int) (sizeof(*oops_hdr) + text_len), err_type,
                 ++oops_count);
 
         spin_unlock_irqrestore(&lock, flags);
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 5f93856cdf47..70670a2d9cf2 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
         struct device_node *dn, *pdn;
         struct pci_bus *bus;
-        const uint32_t *pcie_link_speed_stats;
+        const __be32 *pcie_link_speed_stats;
 
         bus = bridge->bus;
 
@@ -122,7 +122,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
                 return 0;
 
         for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
-                pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn,
+                pcie_link_speed_stats = of_get_property(pdn,
                         "ibm,pcie-link-speed-stats", NULL);
                 if (pcie_link_speed_stats)
                         break;
@@ -135,7 +135,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
                 return 0;
         }
 
-        switch (pcie_link_speed_stats[0]) {
+        switch (be32_to_cpup(pcie_link_speed_stats)) {
         case 0x01:
                 bus->max_bus_speed = PCIE_SPEED_2_5GT;
                 break;
@@ -147,7 +147,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
                 break;
         }
 
-        switch (pcie_link_speed_stats[1]) {
+        switch (be32_to_cpup(pcie_link_speed_stats)) {
         case 0x01:
                 bus->cur_bus_speed = PCIE_SPEED_2_5GT;
                 break;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e903c71f7e69..0952ecd60eca 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
         select HAVE_AOUT if X86_32
         select HAVE_UNSTABLE_SCHED_CLOCK
         select ARCH_SUPPORTS_NUMA_BALANCING
+        select ARCH_SUPPORTS_INT128 if X86_64
         select ARCH_WANTS_PROT_NUMA_PROT_NONE
         select HAVE_IDE
         select HAVE_OPROFILE
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8729723636fd..c8b051933b1b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -8,6 +8,12 @@
 DECLARE_PER_CPU(int, __preempt_count);
 
 /*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
+
+/*
  * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
  * that think a non-zero value indicates we cannot preempt.
  */
@@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
         __this_cpu_add_4(__preempt_count, -val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
         GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fd00bb29425d..c1a861829d81 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -262,11 +262,20 @@ struct cpu_hw_events {
         __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
                           HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
-#define EVENT_CONSTRAINT_END            \
-        EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
 
+/*
+ * Check for end marker with weight == -1
+ */
 #define for_each_event_constraint(e, c) \
-        for ((e) = (c); (e)->weight; (e)++)
+        for ((e) = (c); (e)->weight != -1; (e)++)
 
 /*
  * Extra registers for specific events.
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 5c07a56962db..634c4d6dd45a 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -75,6 +75,7 @@ config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 config CLKSRC_EFM32
         bool "Clocksource for Energy Micro's EFM32 SoCs" if !ARCH_EFM32
         depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST)
+        select CLKSRC_MMIO
         default ARCH_EFM32
         help
           Support to use the timers of EFM32 SoCs as clock source and clock
diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 35639cf4e5a2..b9ddd9e3a2f5 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -35,6 +35,5 @@ void __init clocksource_of_init(void)
 
                 init_func = match->data;
                 init_func(np);
-                of_node_put(np);
         }
 }
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 45ba8aecc729..2a2ea2717f3a 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -108,12 +108,11 @@ static void __init add_clocksource(struct device_node *source_timer)
 
 static u64 read_sched_clock(void)
 {
-        return __raw_readl(sched_io_base);
+        return ~__raw_readl(sched_io_base);
 }
 
 static const struct of_device_id sptimer_ids[] __initconst = {
         { .compatible = "picochip,pc3x2-rtc" },
-        { .compatible = "snps,dw-apb-timer-sp" },
         { /* Sentinel */ },
 };
 
@@ -151,4 +150,6 @@ static void __init dw_apb_timer_init(struct device_node *timer)
         num_called++;
 }
 CLOCKSOURCE_OF_DECLARE(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init);
-CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init);
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 2fb4695a28d8..a4f6119aafd8 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -179,6 +179,9 @@ static void __init sun4i_timer_init(struct device_node *node)
         writel(TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
                timer_base + TIMER_CTL_REG(0));
 
+        /* Make sure timer is stopped before playing with interrupts */
+        sun4i_clkevt_time_stop(0);
+
         ret = setup_irq(irq, &sun4i_timer_irq);
         if (ret)
                 pr_warn("failed to setup irq %d\n", irq);
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index d8e47e502785..4e7f6802e840 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -256,11 +256,6 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
         ticks_per_jiffy = (timer_clk + HZ / 2) / HZ;
 
         /*
-         * Set scale and timer for sched_clock.
-         */
-        sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
-
-        /*
          * Setup free-running clocksource timer (interrupts
          * disabled).
          */
@@ -270,6 +265,11 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
         timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN |
                              TIMER0_DIV(TIMER_DIVIDER_SHIFT));
 
+        /*
+         * Set scale and timer for sched_clock.
+         */
+        sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
+
         clocksource_mmio_init(timer_base + TIMER0_VAL_OFF,
                               "armada_370_xp_clocksource",
                               timer_clk, 300, 32, clocksource_mmio_readl_down);
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index 7b37300973db..2baf0ddf7e02 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -252,7 +252,7 @@ static void msm_gpio_irq_mask(struct irq_data *d)
 
         spin_lock_irqsave(&tlmm_lock, irq_flags);
         writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio));
-        clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+        clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
         __clear_bit(gpio, msm_gpio.enabled_irqs);
         spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }
@@ -264,7 +264,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
 
         spin_lock_irqsave(&tlmm_lock, irq_flags);
         __set_bit(gpio, msm_gpio.enabled_irqs);
-        set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+        set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
         writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio));
         spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index fe088a30567a..8b7e719a68c3 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -169,7 +169,8 @@ static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
         u32 pending;
         unsigned int offset, irqs_handled = 0;
 
-        while ((pending = gpio_rcar_read(p, INTDT))) {
+        while ((pending = gpio_rcar_read(p, INTDT) &
+                          gpio_rcar_read(p, INTMSK))) {
                 offset = __ffs(pending);
                 gpio_rcar_write(p, INTCLR, BIT(offset));
                 generic_handle_irq(irq_find_mapping(p->irq_domain, offset));
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index b97d6a6577b9..f9996899c1f2 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -300,7 +300,7 @@ static int twl_direction_in(struct gpio_chip *chip, unsigned offset)
         if (offset < TWL4030_GPIO_MAX)
                 ret = twl4030_set_gpio_direction(offset, 1);
         else
-                ret = -EINVAL;
+                ret = -EINVAL;  /* LED outputs can't be set as input */
 
         if (!ret)
                 priv->direction &= ~BIT(offset);
@@ -354,11 +354,20 @@ static void twl_set(struct gpio_chip *chip, unsigned offset, int value)
 static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value)
 {
         struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip);
-        int ret = -EINVAL;
+        int ret = 0;
 
         mutex_lock(&priv->mutex);
-        if (offset < TWL4030_GPIO_MAX)
+        if (offset < TWL4030_GPIO_MAX) {
                 ret = twl4030_set_gpio_direction(offset, 0);
+                if (ret) {
+                        mutex_unlock(&priv->mutex);
+                        return ret;
+                }
+        }
+
+        /*
+         *  LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output
+         */
 
         priv->direction |= BIT(offset);
         mutex_unlock(&priv->mutex);
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index 11bd0d970a52..e2142956a8e5 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -254,7 +254,7 @@ struct sh_pfc_soc_info {
 #define PINMUX_GPIO(_pin)                                               \
         [GPIO_##_pin] = {                                               \
                 .pin = (u16)-1,                                         \
-                .name = __stringify(name),                              \
+                .name = __stringify(GPIO_##_pin),                       \
                 .enum_id = _pin##_DATA,                                 \
         }
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e561c059539..ec3ba43b9faa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
         if (err < 0) {
                 SetPageError(page);
                 goto out;
-        } else if (err < PAGE_CACHE_SIZE) {
+        } else {
+                if (err < PAGE_CACHE_SIZE) {
                 /* zero fill remainder of page */
-                zero_user_segment(page, err, PAGE_CACHE_SIZE);
+                        zero_user_segment(page, err, PAGE_CACHE_SIZE);
+                } else {
+                        flush_dcache_page(page);
+                }
         }
         SetPageUptodate(page);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9a8e396aed89..278fd2891288 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -978,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
         struct ceph_mds_reply_inode *ininfo;
         struct ceph_vino vino;
         struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
-        int i = 0;
         int err = 0;
 
         dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1039,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 }
         }
 
+        if (rinfo->head->is_target) {
+                vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+                vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+                in = ceph_get_inode(sb, vino);
+                if (IS_ERR(in)) {
+                        err = PTR_ERR(in);
+                        goto done;
+                }
+                req->r_target_inode = in;
+
+                err = fill_inode(in, &rinfo->targeti, NULL,
+                                session, req->r_request_started,
+                                (le32_to_cpu(rinfo->head->result) == 0) ?
+                                req->r_fmode : -1,
+                                &req->r_caps_reservation);
+                if (err < 0) {
+                        pr_err("fill_inode badness %p %llx.%llx\n",
+                                in, ceph_vinop(in));
+                        goto done;
+                }
+        }
+
         /*
          * ignore null lease/binding on snapdir ENOENT, or else we
          * will have trouble splicing in the virtual snapdir later
@@ -1108,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                              ceph_dentry(req->r_old_dentry)->offset);
 
                         dn = req->r_old_dentry;  /* use old_dentry */
-                        in = dn->d_inode;
                 }
 
                 /* null dentry? */
@@ -1130,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 }
 
                 /* attach proper inode */
-                ininfo = rinfo->targeti.in;
-                vino.ino = le64_to_cpu(ininfo->ino);
-                vino.snap = le64_to_cpu(ininfo->snapid);
-                in = dn->d_inode;
-                if (!in) {
-                        in = ceph_get_inode(sb, vino);
-                        if (IS_ERR(in)) {
-                                pr_err("fill_trace bad get_inode "
-                                       "%llx.%llx\n", vino.ino, vino.snap);
-                                err = PTR_ERR(in);
-                                d_drop(dn);
-                                goto done;
-                        }
+                if (!dn->d_inode) {
+                        ihold(in);
                         dn = splice_dentry(dn, in, &have_lease, true);
                         if (IS_ERR(dn)) {
                                 err = PTR_ERR(dn);
                                 goto done;
                         }
                         req->r_dentry = dn;  /* may have spliced */
-                        ihold(in);
-                } else if (ceph_ino(in) == vino.ino &&
-                           ceph_snap(in) == vino.snap) {
-                        ihold(in);
-                } else {
+                } else if (dn->d_inode && dn->d_inode != in) {
                         dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
-                             dn, in, ceph_ino(in), ceph_snap(in),
-                             vino.ino, vino.snap);
+                             dn, dn->d_inode, ceph_vinop(dn->d_inode),
+                             ceph_vinop(in));
                         have_lease = false;
-                        in = NULL;
                 }
 
                 if (have_lease)
                         update_dentry_lease(dn, rinfo->dlease, session,
                                             req->r_request_started);
                 dout(" final dn %p\n", dn);
-                i++;
-        } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
-                   req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+        } else if (!req->r_aborted &&
+                   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+                    req->r_op == CEPH_MDS_OP_MKSNAP)) {
                 struct dentry *dn = req->r_dentry;
 
                 /* fill out a snapdir LOOKUPSNAP dentry */
@@ -1177,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 ininfo = rinfo->targeti.in;
                 vino.ino = le64_to_cpu(ininfo->ino);
                 vino.snap = le64_to_cpu(ininfo->snapid);
-                in = ceph_get_inode(sb, vino);
-                if (IS_ERR(in)) {
-                        pr_err("fill_inode get_inode badness %llx.%llx\n",
-                               vino.ino, vino.snap);
-                        err = PTR_ERR(in);
-                        d_delete(dn);
-                        goto done;
-                }
                 dout(" linking snapped dir %p to dn %p\n", in, dn);
+                ihold(in);
                 dn = splice_dentry(dn, in, NULL, true);
                 if (IS_ERR(dn)) {
                         err = PTR_ERR(dn);
                         goto done;
                 }
                 req->r_dentry = dn;  /* may have spliced */
-                ihold(in);
-                rinfo->head->is_dentry = 1;  /* fool notrace handlers */
-        }
-
-        if (rinfo->head->is_target) {
-                vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-                vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
-                if (in == NULL || ceph_ino(in) != vino.ino ||
-                    ceph_snap(in) != vino.snap) {
-                        in = ceph_get_inode(sb, vino);
-                        if (IS_ERR(in)) {
-                                err = PTR_ERR(in);
-                                goto done;
-                        }
-                }
-                req->r_target_inode = in;
-
-                err = fill_inode(in,
-                                 &rinfo->targeti, NULL,
-                                 session, req->r_request_started,
-                                 (le32_to_cpu(rinfo->head->result) == 0) ?
-                                 req->r_fmode : -1,
-                                 &req->r_caps_reservation);
-                if (err < 0) {
-                        pr_err("fill_inode badness %p %llx.%llx\n",
-                               in, ceph_vinop(in));
-                        goto done;
-                }
         }
-
 done:
         dout("fill_trace done err=%d\n", err);
         return err;
@@ -1272,7 +1240,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
         struct qstr dname;
         struct dentry *dn;
         struct inode *in;
-        int err = 0, i;
+        int err = 0, ret, i;
         struct inode *snapdir = NULL;
         struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
         struct ceph_dentry_info *di;
@@ -1305,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
                         ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
         }
 
+        /* FIXME: release caps/leases if error occurs */
         for (i = 0; i < rinfo->dir_nr; i++) {
                 struct ceph_vino vino;
 
@@ -1329,9 +1298,10 @@ retry_lookup:
                                 err = -ENOMEM;
                                 goto out;
                         }
-                        err = ceph_init_dentry(dn);
-                        if (err < 0) {
+                        ret = ceph_init_dentry(dn);
+                        if (ret < 0) {
                                 dput(dn);
+                                err = ret;
                                 goto out;
                         }
                 } else if (dn->d_inode &&
@@ -1351,9 +1321,6 @@ retry_lookup:
                         spin_unlock(&parent->d_lock);
                 }
 
-                di = dn->d_fsdata;
-                di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
-
                 /* inode */
                 if (dn->d_inode) {
                         in = dn->d_inode;
@@ -1366,26 +1333,39 @@ retry_lookup:
                                 err = PTR_ERR(in);
                                 goto out;
                         }
-                        dn = splice_dentry(dn, in, NULL, false);
-                        if (IS_ERR(dn))
-                                dn = NULL;
                 }
 
                 if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
                                req->r_request_started, -1,
                                &req->r_caps_reservation) < 0) {
                         pr_err("fill_inode badness on %p\n", in);
+                        if (!dn->d_inode)
+                                iput(in);
+                        d_drop(dn);
                         goto next_item;
                 }
-                if (dn)
-                        update_dentry_lease(dn, rinfo->dir_dlease[i],
-                                            req->r_session,
-                                            req->r_request_started);
+
+                if (!dn->d_inode) {
+                        dn = splice_dentry(dn, in, NULL, false);
+                        if (IS_ERR(dn)) {
+                                err = PTR_ERR(dn);
+                                dn = NULL;
+                                goto next_item;
+                        }
+                }
+
+                di = dn->d_fsdata;
+                di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+                update_dentry_lease(dn, rinfo->dir_dlease[i],
+                                    req->r_session,
+                                    req->r_request_started);
 next_item:
                 if (dn)
                         dput(dn);
         }
-        req->r_did_prepopulate = true;
+        if (err == 0)
+                req->r_did_prepopulate = true;
 
 out:
         if (snapdir) {
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index ddf2b420ac8f..1cd3f5d767a8 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -3,13 +3,11 @@
 
 #include <linux/thread_info.h>
 
-/*
- * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
- * that think a non-zero value indicates we cannot preempt.
- */
+#define PREEMPT_ENABLED (0)
+
 static __always_inline int preempt_count(void)
 {
-        return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
+        return current_thread_info()->preempt_count;
 }
 
 static __always_inline int *preempt_count_ptr(void)
@@ -17,11 +15,6 @@ static __always_inline int *preempt_count_ptr(void)
         return &current_thread_info()->preempt_count;
 }
 
-/*
- * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
- * alternative is loosing a reschedule. Better schedule too often -- also this
- * should be a very rare operation.
- */
 static __always_inline void preempt_count_set(int pc)
 {
         *preempt_count_ptr() = pc;
@@ -41,28 +34,17 @@ static __always_inline void preempt_count_set(int pc)
         task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
 } while (0)
 
-/*
- * We fold the NEED_RESCHED bit into the preempt count such that
- * preempt_enable() can decrement and test for needing to reschedule with a
- * single instruction.
- *
- * We invert the actual bit, so that when the decrement hits 0 we know we both
- * need to resched (the bit is cleared) and can resched (no preempt count).
- */
-
 static __always_inline void set_preempt_need_resched(void)
 {
-        *preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-        *preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-        return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
+        return false;
 }
 
 /*
@@ -81,7 +63,12 @@ static __always_inline void __preempt_count_sub(int val)
 
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-        return !--*preempt_count_ptr();
+        /*
+         * Because of load-store architectures cannot do per-cpu atomic
+         * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+         * lost.
+         */
+        return !--*preempt_count_ptr() && tif_need_resched();
 }
 
 /*
@@ -89,7 +76,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(void)
 {
-        return unlikely(!*preempt_count_ptr());
+        return unlikely(!preempt_count() && tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 69ed5f5e9f6e..c45c089bfdac 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -133,4 +133,34 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
         return ret;
 }
 
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+        return (u64)(((unsigned __int128)a * mul) >> shift);
+}
+#endif /* mul_u64_u32_shr */
+
+#else
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+        u32 ah, al;
+        u64 ret;
+
+        al = a;
+        ah = a >> 32;
+
+        ret = ((u64)al * mul) >> shift;
+        if (ah)
+                ret += ((u64)ah * mul) << (32 - shift);
+
+        return ret;
+}
+#endif /* mul_u64_u32_shr */
+
+#endif
+
 #endif /* _LINUX_MATH64_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 768b037dfacb..53f97eb8dbc7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -440,8 +440,6 @@ struct task_cputime {
                 .sum_exec_runtime = 0,                          \
         }
 
-#define PREEMPT_ENABLED         (PREEMPT_NEED_RESCHED)
-
 #ifdef CONFIG_PREEMPT_COUNT
 #define PREEMPT_DISABLED        (1 + PREEMPT_ENABLED)
 #else
@@ -932,7 +930,8 @@ struct pipe_inode_info;
 struct uts_namespace;
 
 struct load_weight {
-        unsigned long weight, inv_weight;
+        unsigned long weight;
+        u32 inv_weight;
 };
 
 struct sched_avg {
diff --git a/init/Kconfig b/init/Kconfig
index 79383d3aa5dc..4e5d96ab2034 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -809,6 +809,12 @@ config GENERIC_SCHED_CLOCK
 config ARCH_SUPPORTS_NUMA_BALANCING
         bool
 
+#
+# For architectures that know their GCC __int128 support is sound
+#
+config ARCH_SUPPORTS_INT128
+        bool
+
 # For architectures that (ab)use NUMA to represent different memory regions
 # all cpu-local but of different latencies, such as SuperH.
 #
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e85cda20ab2b..19af58f3a261 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5112,6 +5112,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
                  * die on a /0 trap.
                  */
                 sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+                sg->sgp->power_orig = sg->sgp->power;
 
                 /*
                  * Make sure the first group of this domain contains the
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fd773ade1a31..9030da7bcb15 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,59 +178,61 @@ void sched_init_granularity(void)
         update_sysctl();
 }
 
-#if BITS_PER_LONG == 32
-# define WMULT_CONST    (~0UL)
-#else
-# define WMULT_CONST    (1UL << 32)
-#endif
-
+#define WMULT_CONST     (~0U)
 #define WMULT_SHIFT     32
 
-/*
- * Shift right and round:
- */
-#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+static void __update_inv_weight(struct load_weight *lw)
+{
+        unsigned long w;
+
+        if (likely(lw->inv_weight))
+                return;
+
+        w = scale_load_down(lw->weight);
+
+        if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
+                lw->inv_weight = 1;
+        else if (unlikely(!w))
+                lw->inv_weight = WMULT_CONST;
+        else
+                lw->inv_weight = WMULT_CONST / w;
+}
 
 /*
- * delta *= weight / lw
+ * delta_exec * weight / lw.weight
+ *   OR
+ * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
+ *
+ * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
+ * we're guaranteed shift stays positive because inv_weight is guaranteed to
+ * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
+ *
+ * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
+ * weight/lw.weight <= 1, and therefore our shift will also be positive.
  */
-static unsigned long
-calc_delta_mine(unsigned long delta_exec, unsigned long weight,
-                struct load_weight *lw)
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
 {
-        u64 tmp;
+        u64 fact = scale_load_down(weight);
+        int shift = WMULT_SHIFT;
 
-        /*
-         * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
-         * entities since MIN_SHARES = 2. Treat weight as 1 if less than
-         * 2^SCHED_LOAD_RESOLUTION.
-         */
-        if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
-                tmp = (u64)delta_exec * scale_load_down(weight);
-        else
-                tmp = (u64)delta_exec;
+        __update_inv_weight(lw);
 
-        if (!lw->inv_weight) {
-                unsigned long w = scale_load_down(lw->weight);
-
-                if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
-                        lw->inv_weight = 1;
-                else if (unlikely(!w))
-                        lw->inv_weight = WMULT_CONST;
-                else
-                        lw->inv_weight = WMULT_CONST / w;
+        if (unlikely(fact >> 32)) {
+                while (fact >> 32) {
+                        fact >>= 1;
+                        shift--;
+                }
         }
 
-        /*
-         * Check whether we'd overflow the 64-bit multiplication:
-         */
-        if (unlikely(tmp > WMULT_CONST))
-                tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
-                        WMULT_SHIFT/2);
-        else
-                tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+        /* hint to use a 32x32->64 mul */
+        fact = (u64)(u32)fact * lw->inv_weight;
+
+        while (fact >> 32) {
+                fact >>= 1;
+                shift--;
+        }
 
-        return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+        return mul_u64_u32_shr(delta_exec, fact, shift);
 }
 
 
@@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 #endif  /* CONFIG_FAIR_GROUP_SCHED */
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 /*
  * delta /= w
  */
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
 {
         if (unlikely(se->load.weight != NICE_0_LOAD))
-                delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+                delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
 
         return delta;
 }
@@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
                         update_load_add(&lw, se->load.weight);
                         load = &lw;
                 }
-                slice = calc_delta_mine(slice, se->load.weight, load);
+                slice = __calc_delta(slice, se->load.weight, load);
         }
         return slice;
 }
@@ -703,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p)
 #endif
 
 /*
- * Update the current task's runtime statistics. Skip current tasks that
- * are not in our scheduling class.
+ * Update the current task's runtime statistics.
  */
-static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
-              unsigned long delta_exec)
-{
-        unsigned long delta_exec_weighted;
-
-        schedstat_set(curr->statistics.exec_max,
-                      max((u64)delta_exec, curr->statistics.exec_max));
-
-        curr->sum_exec_runtime += delta_exec;
-        schedstat_add(cfs_rq, exec_clock, delta_exec);
-        delta_exec_weighted = calc_delta_fair(delta_exec, curr);
-
-        curr->vruntime += delta_exec_weighted;
-        update_min_vruntime(cfs_rq);
-}
-
 static void update_curr(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *curr = cfs_rq->curr;
         u64 now = rq_clock_task(rq_of(cfs_rq));
-        unsigned long delta_exec;
+        u64 delta_exec;
 
         if (unlikely(!curr))
                 return;
 
-        /*
-         * Get the amount of time the current task was running
-         * since the last time we changed load (this cannot
-         * overflow on 32 bits):
-         */
-        delta_exec = (unsigned long)(now - curr->exec_start);
-        if (!delta_exec)
+        delta_exec = now - curr->exec_start;
+        if (unlikely((s64)delta_exec <= 0))
                 return;
 
-        __update_curr(cfs_rq, curr, delta_exec);
         curr->exec_start = now;
 
+        schedstat_set(curr->statistics.exec_max,
+                      max(delta_exec, curr->statistics.exec_max));
+
+        curr->sum_exec_runtime += delta_exec;
+        schedstat_add(cfs_rq, exec_clock, delta_exec);
+
+        curr->vruntime += calc_delta_fair(delta_exec, curr);
+        update_min_vruntime(cfs_rq);
+
         if (entity_is_task(curr)) {
                 struct task_struct *curtask = task_of(curr);
 
@@ -3015,8 +3001,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
         }
 }
 
-static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-                                     unsigned long delta_exec)
+static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
         /* dock delta_exec before expiring quota (as it could span periods) */
         cfs_rq->runtime_remaining -= delta_exec;
@@ -3034,7 +3019,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 }
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
         if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
                 return;
@@ -3574,8 +3559,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
         return rq_clock_task(rq_of(cfs_rq));
 }
 
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-                                     unsigned long delta_exec) {}
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index dc4de3762111..bcf1d2f0b791 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -18,9 +18,9 @@
 #include "helpers/bitmask.h"
 
 static struct option set_opts[] = {
-        { .name = "perf-bias",  .has_arg = optional_argument,   .flag = NULL,   .val = 'b'},
-        { .name = "sched-mc",   .has_arg = optional_argument,   .flag = NULL,   .val = 'm'},
-        { .name = "sched-smt",  .has_arg = optional_argument,   .flag = NULL,   .val = 's'},
+        { .name = "perf-bias",  .has_arg = required_argument,   .flag = NULL,   .val = 'b'},
+        { .name = "sched-mc",   .has_arg = required_argument,   .flag = NULL,   .val = 'm'},
+        { .name = "sched-smt",  .has_arg = required_argument,   .flag = NULL,   .val = 's'},
         { },
 };