diff options
Diffstat (limited to 'arch/powerpc')
43 files changed, 1224 insertions, 681 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2729c6663d8a..cdf7a0a64406 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -134,6 +134,7 @@ config PPC select GENERIC_IRQ_SHOW_LEVEL select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS + select HAVE_BPF_JIT if (PPC64 && NET) config EARLY_PRINTK bool diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index b7212b619c52..b94740f36b1a 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -154,7 +154,8 @@ core-y += arch/powerpc/kernel/ \ arch/powerpc/lib/ \ arch/powerpc/sysdev/ \ arch/powerpc/platforms/ \ - arch/powerpc/math-emu/ + arch/powerpc/math-emu/ \ + arch/powerpc/net/ core-$(CONFIG_XMON) += arch/powerpc/xmon/ core-$(CONFIG_KVM) += arch/powerpc/kvm/ diff --git a/arch/powerpc/include/asm/8253pit.h b/arch/powerpc/include/asm/8253pit.h deleted file mode 100644 index a71c9c1455a7..000000000000 --- a/arch/powerpc/include/asm/8253pit.h +++ /dev/null @@ -1,3 +0,0 @@ -/* - * 8253/8254 Programmable Interval Timer - */ diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 45921672b97a..2cc41c715d2b 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -78,14 +78,14 @@ extern void ppc_warn_emulated_print(const char *type); #define PPC_WARN_EMULATED(type, regs) \ do { \ perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, \ - 1, 0, regs, 0); \ + 1, regs, 0); \ __PPC_WARN_EMULATED(type); \ } while (0) #define PPC_WARN_ALIGNMENT(type, regs) \ do { \ perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, \ - 1, 0, regs, regs->dar); \ + 1, regs, regs->dar); \ __PPC_WARN_EMULATED(type); \ } while (0) diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 1c33ec17ca36..80fd4d2b4a62 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -57,7 +57,7 @@ void hw_breakpoint_pmu_read(struct perf_event *bp); extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); extern struct pmu perf_ops_bp; -extern void ptrace_triggered(struct perf_event *bp, int nmi, +extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); static inline void hw_breakpoint_disable(void) { diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b90dbf8e5cd9..90bd3ed48165 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -171,15 +171,9 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) #ifndef CONFIG_PPC64 -static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) -{ - struct pci_controller *host; - - if (bus->self) - return pci_device_to_OF_node(bus->self); - host = pci_bus_to_host(bus); - return host ? host->dn : NULL; -} +extern int pci_device_from_OF_node(struct device_node *node, + u8 *bus, u8 *devfn); +extern void pci_create_OF_bus_map(void); static inline int isa_vaddr_is_ioport(void __iomem *address) { @@ -223,17 +217,8 @@ struct pci_dn { /* Get the pointer to a device_node's pci_dn */ #define PCI_DN(dn) ((struct pci_dn *) (dn)->data) -extern struct device_node *fetch_dev_dn(struct pci_dev *dev); extern void * update_dn_pci_info(struct device_node *dn, void *data); -/* Get a device_node from a pci_dev. This code must be fast except - * in the case where the sysdata is incorrect and needs to be fixed - * up (this will only happen once). */ -static inline struct device_node *pci_device_to_OF_node(struct pci_dev *dev) -{ - return dev->dev.of_node ? dev->dev.of_node : fetch_dev_dn(dev); -} - static inline int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) { @@ -244,14 +229,6 @@ static inline int pci_device_from_OF_node(struct device_node *np, return 0; } -static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) -{ - if (bus->self) - return pci_device_to_OF_node(bus->self); - else - return bus->dev.of_node; /* Must be root bus (PHB) */ -} - /** Find the bus corresponding to the indicated device node */ extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn); diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 7d7790954e02..1f522680ea17 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -179,8 +179,7 @@ extern int remove_phb_dynamic(struct pci_controller *phb); extern struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn); -extern void of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev); +extern void of_scan_pci_bridge(struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index e472659d906c..e980faae4225 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -71,6 +71,42 @@ #define PPC_INST_ERATSX 0x7c000126 #define PPC_INST_ERATSX_DOT 0x7c000127 +/* Misc instructions for BPF compiler */ +#define PPC_INST_LD 0xe8000000 +#define PPC_INST_LHZ 0xa0000000 +#define PPC_INST_LWZ 0x80000000 +#define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDU 0xf8000001 +#define PPC_INST_MFLR 0x7c0802a6 +#define PPC_INST_MTLR 0x7c0803a6 +#define PPC_INST_CMPWI 0x2c000000 +#define PPC_INST_CMPDI 0x2c200000 +#define PPC_INST_CMPLW 0x7c000040 +#define PPC_INST_CMPLWI 0x28000000 +#define PPC_INST_ADDI 0x38000000 +#define PPC_INST_ADDIS 0x3c000000 +#define PPC_INST_ADD 0x7c000214 +#define PPC_INST_SUB 0x7c000050 +#define PPC_INST_BLR 0x4e800020 +#define PPC_INST_BLRL 0x4e800021 +#define PPC_INST_MULLW 0x7c0001d6 +#define PPC_INST_MULHWU 0x7c000016 +#define PPC_INST_MULLI 0x1c000000 +#define PPC_INST_DIVWU 0x7c0003d6 +#define PPC_INST_RLWINM 0x54000000 +#define PPC_INST_RLDICR 0x78000004 +#define PPC_INST_SLW 0x7c000030 +#define PPC_INST_SRW 0x7c000430 +#define PPC_INST_AND 0x7c000038 +#define PPC_INST_ANDDOT 0x7c000039 +#define PPC_INST_OR 0x7c000378 +#define PPC_INST_ANDI 0x70000000 +#define PPC_INST_ORI 0x60000000 +#define PPC_INST_ORIS 0x64000000 +#define PPC_INST_NEG 0x7c0000d0 +#define PPC_INST_BRANCH 0x48000000 +#define PPC_INST_BRANCH_COND 0x40800000 + /* macros to insert fields into opcodes */ #define __PPC_RA(a) (((a) & 0x1f) << 16) #define __PPC_RB(b) (((b) & 0x1f) << 11) @@ -83,6 +119,10 @@ #define __PPC_T_TLB(t) (((t) & 0x3) << 21) #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) +#define __PPC_SH(s) __PPC_WS(s) +#define __PPC_MB(s) (((s) & 0x1f) << 6) +#define __PPC_ME(s) (((s) & 0x1f) << 1) +#define __PPC_BI(s) (((s) & 0x1f) << 16) /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index c189aa5fe1f4..b823536375dc 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -22,20 +22,6 @@ #define HAVE_ARCH_DEVTREE_FIXUPS -#ifdef CONFIG_PPC32 -/* - * PCI <-> OF matching functions - * (XXX should these be here?) - */ -struct pci_bus; -struct pci_dev; -extern int pci_device_from_OF_node(struct device_node *node, - u8* bus, u8* devfn); -extern struct device_node* pci_busdev_to_OF_node(struct pci_bus *, int); -extern struct device_node* pci_device_to_OF_node(struct pci_dev *); -extern void pci_create_OF_bus_map(void); -#endif - /* * OF address retreival & translation */ diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c index b150b510510f..cb2e2949c8d1 100644 --- a/arch/powerpc/kernel/e500-pmu.c +++ b/arch/powerpc/kernel/e500-pmu.c @@ -75,6 +75,11 @@ static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static int num_events = 128; diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index 2cc5e0301d0b..845a58478890 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -388,6 +388,11 @@ static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; struct power_pmu mpc7450_pmu = { diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 893af2a9cd03..a3c92770e422 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1097,9 +1097,6 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Setup OF node pointer in the device */ - dev->dev.of_node = pci_device_to_OF_node(dev); - /* Fixup NUMA node as it may not be setup yet by the generic * code and is needed by the DMA init */ @@ -1685,6 +1682,13 @@ int early_find_capability(struct pci_controller *hose, int bus, int devfn, return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); } +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + return of_node_get(hose->dn); +} + /** * pci_scan_phb - Given a pci_controller, setup and scan the PCI bus * @hose: Pointer to the PCI host controller instance structure @@ -1705,7 +1709,6 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) hose->global_number); return; } - bus->dev.of_node = of_node_get(node); bus->secondary = hose->first_busno; hose->bus = bus; diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index bedb370459f2..86585508e9c1 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -167,150 +167,26 @@ pcibios_make_OF_bus_map(void) #endif } -typedef int (*pci_OF_scan_iterator)(struct device_node* node, void* data); - -static struct device_node* -scan_OF_pci_childs(struct device_node *parent, pci_OF_scan_iterator filter, void* data) -{ - struct device_node *node; - struct device_node* sub_node; - - for_each_child_of_node(parent, node) { - const unsigned int *class_code; - - if (filter(node, data)) { - of_node_put(node); - return node; - } - - /* For PCI<->PCI bridges or CardBus bridges, we go down - * Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. - */ - class_code = of_get_property(node, "class-code", NULL); - if ((!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI && - (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) && - strcmp(node->name, "multifunc-device")) - continue; - sub_node = scan_OF_pci_childs(node, filter, data); - if (sub_node) { - of_node_put(node); - return sub_node; - } - } - return NULL; -} - -static struct device_node *scan_OF_for_pci_dev(struct device_node *parent, - unsigned int devfn) -{ - struct device_node *np, *cnp; - const u32 *reg; - unsigned int psize; - - for_each_child_of_node(parent, np) { - reg = of_get_property(np, "reg", &psize); - if (reg && psize >= 4 && ((reg[0] >> 8) & 0xff) == devfn) - return np; - - /* Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. */ - if (!strcmp(np->name, "multifunc-device")) { - cnp = scan_OF_for_pci_dev(np, devfn); - if (cnp) - return cnp; - } - } - return NULL; -} - - -static struct device_node *scan_OF_for_pci_bus(struct pci_bus *bus) -{ - struct device_node *parent, *np; - - /* Are we a root bus ? */ - if (bus->self == NULL || bus->parent == NULL) { - struct pci_controller *hose = pci_bus_to_host(bus); - if (hose == NULL) - return NULL; - return of_node_get(hose->dn); - } - - /* not a root bus, we need to get our parent */ - parent = scan_OF_for_pci_bus(bus->parent); - if (parent == NULL) - return NULL; - - /* now iterate for children for a match */ - np = scan_OF_for_pci_dev(parent, bus->self->devfn); - of_node_put(parent); - - return np; -} - -/* - * Scans the OF tree for a device node matching a PCI device - */ -struct device_node * -pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) -{ - struct device_node *parent, *np; - - pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); - parent = scan_OF_for_pci_bus(bus); - if (parent == NULL) - return NULL; - pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>"); - np = scan_OF_for_pci_dev(parent, devfn); - of_node_put(parent); - pr_debug(" result is %s\n", np ? np->full_name : "<NULL>"); - - /* XXX most callers don't release the returned node - * mostly because ppc64 doesn't increase the refcount, - * we need to fix that. - */ - return np; -} -EXPORT_SYMBOL(pci_busdev_to_OF_node); - -struct device_node* -pci_device_to_OF_node(struct pci_dev *dev) -{ - return pci_busdev_to_OF_node(dev->bus, dev->devfn); -} -EXPORT_SYMBOL(pci_device_to_OF_node); - -static int -find_OF_pci_device_filter(struct device_node* node, void* data) -{ - return ((void *)node == data); -} /* * Returns the PCI device matching a given OF node */ -int -pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) +int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) { - const unsigned int *reg; - struct pci_controller* hose; - struct pci_dev* dev = NULL; - - /* Make sure it's really a PCI device */ - hose = pci_find_hose_for_OF_device(node); - if (!hose || !hose->dn) - return -ENODEV; - if (!scan_OF_pci_childs(hose->dn, - find_OF_pci_device_filter, (void *)node)) + struct pci_dev *dev = NULL; + const __be32 *reg; + int size; + + /* Check if it might have a chance to be a PCI device */ + if (!pci_find_hose_for_OF_device(node)) return -ENODEV; - reg = of_get_property(node, "reg", NULL); - if (!reg) + + reg = of_get_property(node, "reg", &size); + if (!reg || size < 5 * sizeof(u32)) return -ENODEV; - *bus = (reg[0] >> 16) & 0xff; - *devfn = ((reg[0] >> 8) & 0xff); + + *bus = (be32_to_cpup(®[0]) >> 16) & 0xff; + *devfn = (be32_to_cpup(®[0]) >> 8) & 0xff; /* Ok, here we need some tweak. If we have already renumbered * all busses, we can't rely on the OF bus number any more. diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 6baabc13306a..478f8d78716b 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -142,53 +142,6 @@ void __devinit pci_devs_phb_init_dynamic(struct pci_controller *phb) traverse_pci_devices(dn, update_dn_pci_info, phb); } -/* - * Traversal func that looks for a <busno,devfcn> value. - * If found, the pci_dn is returned (thus terminating the traversal). - */ -static void *is_devfn_node(struct device_node *dn, void *data) -{ - int busno = ((unsigned long)data >> 8) & 0xff; - int devfn = ((unsigned long)data) & 0xff; - struct pci_dn *pci = dn->data; - - if (pci && (devfn == pci->devfn) && (busno == pci->busno)) - return dn; - return NULL; -} - -/* - * This is the "slow" path for looking up a device_node from a - * pci_dev. It will hunt for the device under its parent's - * phb and then update of_node pointer. - * - * It may also do fixups on the actual device since this happens - * on the first read/write. - * - * Note that it also must deal with devices that don't exist. - * In this case it may probe for real hardware ("just in case") - * and add a device_node to the device tree if necessary. - * - * Is this function necessary anymore now that dev->dev.of_node is - * used to store the node pointer? - * - */ -struct device_node *fetch_dev_dn(struct pci_dev *dev) -{ - struct pci_controller *phb = dev->sysdata; - struct device_node *dn; - unsigned long searchval = (dev->bus->number << 8) | dev->devfn; - - if (WARN_ON(!phb)) - return NULL; - - dn = traverse_pci_devices(phb->dn, is_devfn_node, (void *)searchval); - if (dn) - dev->dev.of_node = dn; - return dn; -} -EXPORT_SYMBOL(fetch_dev_dn); - /** * pci_devs_phb_init - Initialize phbs and pci devs under them. * diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 1e89a72fd030..fe0a5ad6f73e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -202,9 +202,9 @@ EXPORT_SYMBOL(of_create_pci_dev); * this routine in turn call of_scan_bus() recusively to scan for more child * devices. */ -void __devinit of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev) +void __devinit of_scan_pci_bridge(struct pci_dev *dev) { + struct device_node *node = dev->dev.of_node; struct pci_bus *bus; const u32 *busrange, *ranges; int len, i, mode; @@ -238,7 +238,6 @@ void __devinit of_scan_pci_bridge(struct device_node *node, bus->primary = dev->bus->number; bus->subordinate = busrange[1]; bus->bridge_ctl = 0; - bus->dev.of_node = of_node_get(node); /* parse ranges property */ /* PCI #address-cells == 3 and #size-cells == 2 always */ @@ -335,9 +334,7 @@ static void __devinit __of_scan_bus(struct device_node *node, list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { - struct device_node *child = pci_device_to_OF_node(dev); - if (child) - of_scan_pci_bridge(child, dev); + of_scan_pci_bridge(dev); } } } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 822f63008ae1..14967de98876 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1207,7 +1207,7 @@ struct pmu power_pmu = { * here so there is no possibility of being interrupted. */ static void record_and_restart(struct perf_event *event, unsigned long val, - struct pt_regs *regs, int nmi) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -1258,7 +1258,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } } @@ -1346,7 +1346,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if ((int)val < 0) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } } diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index b0dc8f7069cd..0a6d2a9d569c 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -568,7 +568,7 @@ static struct pmu fsl_emb_pmu = { * here so there is no possibility of being interrupted. */ static void record_and_restart(struct perf_event *event, unsigned long val, - struct pt_regs *regs, int nmi) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -616,7 +616,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) fsl_emb_pmu_stop(event, 0); } } @@ -644,7 +644,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if (event) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } else { /* * Disabled counter is negative, diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index ead8b3c2649e..e9dbc2d35c9c 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -587,6 +587,11 @@ static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power4_pmu = { diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index eca0ac595cb6..f58a2bd41b59 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -653,6 +653,11 @@ static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5p_pmu = { diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index d5ff0f64a5e6..b1acab684142 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -595,6 +595,11 @@ static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5_pmu = { diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 31603927e376..b24a3a23d073 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -516,6 +516,11 @@ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power6_pmu = { diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 593740fcb799..6d9dccb2ea59 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -342,6 +342,11 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power7_pmu = { diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 9a6e093858fe..b121de9658eb 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -467,6 +467,11 @@ static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu ppc970_pmu = { diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index cb22024f2b42..05b7dd217f60 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -882,7 +882,7 @@ void user_disable_single_step(struct task_struct *task) } #ifdef CONFIG_HAVE_HW_BREAKPOINT -void ptrace_triggered(struct perf_event *bp, int nmi, +void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct perf_event_attr attr; @@ -973,7 +973,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, &attr.bp_type); thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr, - ptrace_triggered, task); + ptrace_triggered, NULL, task); if (IS_ERR(bp)) { thread->ptrace_bps[0] = NULL; ptrace_put_breakpoints(task); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f33acfd872ad..03b29a6759ab 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -544,7 +544,7 @@ DEFINE_PER_CPU(u8, irq_work_pending); #endif /* 32 vs 64 bit */ -void set_irq_work_pending(void) +void arch_irq_work_raise(void) { preempt_disable(); set_irq_work_pending_flag(); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index b7baff78f90c..105b6918b23e 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -99,6 +99,5 @@ config KVM_E500 If unsure, say N. source drivers/vhost/Kconfig -source drivers/virtio/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index ad35f66c69e8..5efe8c96d37f 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -174,7 +174,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, die("Weird page fault", regs, SIGSEGV); } - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -320,7 +320,7 @@ good_area: } if (ret & VM_FAULT_MAJOR) { current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); #ifdef CONFIG_PPC_SMLPAR if (firmware_has_feature(FW_FEATURE_CMO)) { @@ -331,7 +331,7 @@ good_area: #endif } else { current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } up_read(&mm->mmap_sem); diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile new file mode 100644 index 000000000000..266b3950c3ac --- /dev/null +++ b/arch/powerpc/net/Makefile @@ -0,0 +1,4 @@ +# +# Arch-specific network modules +# +obj-$(CONFIG_BPF_JIT) += bpf_jit_64.o bpf_jit_comp.o diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h new file mode 100644 index 000000000000..af1ab5e9a691 --- /dev/null +++ b/arch/powerpc/net/bpf_jit.h @@ -0,0 +1,227 @@ +/* bpf_jit.h: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#define BPF_PPC_STACK_LOCALS 32 +#define BPF_PPC_STACK_BASIC (48+64) +#define BPF_PPC_STACK_SAVE (18*8) +#define BPF_PPC_STACKFRAME (BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \ + BPF_PPC_STACK_SAVE) +#define BPF_PPC_SLOWPATH_FRAME (48+64) + +/* + * Generated code register usage: + * + * As normal PPC C ABI (e.g. r1=sp, r2=TOC), with: + * + * skb r3 (Entry parameter) + * A register r4 + * X register r5 + * addr param r6 + * r7-r10 scratch + * skb->data r14 + * skb headlen r15 (skb->len - skb->data_len) + * m[0] r16 + * m[...] ... + * m[15] r31 + */ +#define r_skb 3 +#define r_ret 3 +#define r_A 4 +#define r_X 5 +#define r_addr 6 +#define r_scratch1 7 +#define r_D 14 +#define r_HL 15 +#define r_M 16 + +#ifndef __ASSEMBLY__ + +/* + * Assembly helpers from arch/powerpc/net/bpf_jit.S: + */ +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; + +#define FUNCTION_DESCR_SIZE 24 + +/* + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + */ +#define IMM_H(i) ((uintptr_t)(i)>>16) +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ + (((uintptr_t)(i) & 0x8000) >> 15)) +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) + +#define PLANT_INSTR(d, idx, instr) \ + do { if (d) { (d)[idx] = instr; } idx++; } while (0) +#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) + +#define PPC_NOP() EMIT(PPC_INST_NOP) +#define PPC_BLR() EMIT(PPC_INST_BLR) +#define PPC_BLRL() EMIT(PPC_INST_BLRL) +#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | __PPC_RT(r)) +#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_MR(d, a) PPC_OR(d, a, a) +#define PPC_LI(r, i) PPC_ADDI(r, 0, i) +#define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \ + __PPC_RS(d) | __PPC_RA(a) | IMM_L(i)) +#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) +#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | __PPC_RS(r) | \ + __PPC_RA(base) | ((i) & 0xfffc)) + +#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +/* Convenience helpers for the above with 'far' offsets: */ +#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LD(r, r, IMM_L(i)); } } while(0) + +#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LWZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LHZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | __PPC_RA(a) | __PPC_RB(b)) + +#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | __PPC_RT(d) | \ + __PPC_RB(a) | __PPC_RA(b)) +#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MUL(d, a, b) EMIT(PPC_INST_MULLW | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ +#define PPC_SLWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(0) | __PPC_ME(31-(i))) +/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ +#define PPC_SRWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(32-(i)) | \ + __PPC_MB(i) | __PPC_ME(31)) +/* sldi = rldicr Rx, Ry, n, 63-n */ +#define PPC_SLDI(d, a, i) EMIT(PPC_INST_RLDICR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(63-(i)) | (((i) & 0x20) >> 4)) +#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | __PPC_RT(d) | __PPC_RA(a)) + +/* Long jump; (unconditional 'branch') */ +#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ + (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +/* "cond" here covers BO:BI fields. */ +#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ + (((cond) & 0x3ff) << 16) | \ + (((dest) - (ctx->idx * 4)) & \ + 0xfffc)) +#define PPC_LI32(d, i) do { PPC_LI(d, IMM_L(i)); \ + if ((u32)(uintptr_t)(i) >= 32768) { \ + PPC_ADDIS(d, d, IMM_HA(i)); \ + } } while(0) +#define PPC_LI64(d, i) do { \ + if (!((uintptr_t)(i) & 0xffffffff00000000ULL)) \ + PPC_LI32(d, i); \ + else { \ + PPC_LIS(d, ((uintptr_t)(i) >> 48)); \ + if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \ + PPC_ORI(d, d, \ + ((uintptr_t)(i) >> 32) & 0xffff); \ + PPC_SLDI(d, d, 32); \ + if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \ + PPC_ORIS(d, d, \ + ((uintptr_t)(i) >> 16) & 0xffff); \ + if ((uintptr_t)(i) & 0x000000000000ffffULL) \ + PPC_ORI(d, d, (uintptr_t)(i) & 0xffff); \ + } } while (0); + +static inline bool is_nearbranch(int offset) +{ + return (offset < 32768) && (offset >= -32768); +} + +/* + * The fly in the ointment of code size changing from pass to pass is + * avoided by padding the short branch case with a NOP. If code size differs + * with different branch reaches we will have the issue of code moving from + * one pass to the next and will need a few passes to converge on a stable + * state. + */ +#define PPC_BCC(cond, dest) do { \ + if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + PPC_BCC_SHORT(cond, dest); \ + PPC_NOP(); \ + } else { \ + /* Flip the 'T or F' bit to invert comparison */ \ + PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \ + PPC_JMP(dest); \ + } } while(0) + +/* To create a branch condition, select a bit of cr0... */ +#define CR0_LT 0 +#define CR0_GT 1 +#define CR0_EQ 2 +/* ...and modify BO[3] */ +#define COND_CMP_TRUE 0x100 +#define COND_CMP_FALSE 0x000 +/* Together, they make all required comparisons: */ +#define COND_GT (CR0_GT | COND_CMP_TRUE) +#define COND_GE (CR0_LT | COND_CMP_FALSE) +#define COND_EQ (CR0_EQ | COND_CMP_TRUE) +#define COND_NE (CR0_EQ | COND_CMP_FALSE) +#define COND_LT (CR0_LT | COND_CMP_TRUE) + +#define SEEN_DATAREF 0x10000 /* might call external helpers */ +#define SEEN_XREG 0x20000 /* X reg is used */ +#define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary + * storage */ +#define SEEN_MEM_MSK 0x0ffff + +struct codegen_context { + unsigned int seen; + unsigned int idx; + int pc_ret0; /* bpf index of first RET #0 instruction (if any) */ +}; + +#endif + +#endif diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S new file mode 100644 index 000000000000..ff4506e85cce --- /dev/null +++ b/arch/powerpc/net/bpf_jit_64.S @@ -0,0 +1,138 @@ +/* bpf_jit.S: Packet/header access helper functions + * for PPC64 BPF compiler. + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <asm/ppc_asm.h> +#include "bpf_jit.h" + +/* + * All of these routines are called directly from generated code, + * whose register usage is: + * + * r3 skb + * r4,r5 A,X + * r6 *** address parameter to helper *** + * r7-r10 scratch + * r14 skb->data + * r15 skb headlen + * r16-31 M[] + */ + +/* + * To consider: These helpers are so small it could be better to just + * generate them inline. Inline code can do the simple headlen check + * then branch directly to slow_path_XXX if required. (In fact, could + * load a spare GPR with the address of slow_path_generic and pass size + * as an argument, making the call site a mtlr, li and bllr.) + * + * Technically, the "is addr < 0" check is unnecessary & slowing down + * the ABS path, as it's statically checked on generation. + */ + .globl sk_load_word +sk_load_word: + cmpdi r_addr, 0 + blt bpf_error + /* Are we accessing past headlen? */ + subi r_scratch1, r_HL, 4 + cmpd r_scratch1, r_addr + blt bpf_slow_path_word + /* Nope, just hitting the header. cr0 here is eq or gt! */ + lwzx r_A, r_D, r_addr + /* When big endian we don't need to byteswap. */ + blr /* Return success, cr0 != LT */ + + .globl sk_load_half +sk_load_half: + cmpdi r_addr, 0 + blt bpf_error + subi r_scratch1, r_HL, 2 + cmpd r_scratch1, r_addr + blt bpf_slow_path_half + lhzx r_A, r_D, r_addr + blr + + .globl sk_load_byte +sk_load_byte: + cmpdi r_addr, 0 + blt bpf_error + cmpd r_HL, r_addr + ble bpf_slow_path_byte + lbzx r_A, r_D, r_addr + blr + +/* + * BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf) + * r_addr is the offset value, already known positive + */ + .globl sk_load_byte_msh +sk_load_byte_msh: + cmpd r_HL, r_addr + ble bpf_slow_path_byte_msh + lbzx r_X, r_D, r_addr + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr + +bpf_error: + /* Entered with cr0 = lt */ + li r3, 0 + /* Generated code will 'blt epilogue', returning 0. */ + blr + +/* Call out to skb_copy_bits: + * We'll need to back up our volatile regs first; we have + * local variable space at r1+(BPF_PPC_STACK_BASIC). + * Allocate a new stack frame here to remain ABI-compliant in + * stashing LR. + */ +#define bpf_slow_path_common(SIZE) \ + mflr r0; \ + std r0, 16(r1); \ + /* R3 goes in parameter space of caller's frame */ \ + std r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + std r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + std r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + addi r5, r1, BPF_PPC_STACK_BASIC+(2*8); \ + stdu r1, -BPF_PPC_SLOWPATH_FRAME(r1); \ + /* R3 = r_skb, as passed */ \ + mr r4, r_addr; \ + li r6, SIZE; \ + bl skb_copy_bits; \ + /* R3 = 0 on success */ \ + addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ + ld r0, 16(r1); \ + ld r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + ld r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + mtlr r0; \ + cmpdi r3, 0; \ + blt bpf_error; /* cr0 = LT */ \ + ld r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + /* Great success! */ + +bpf_slow_path_word: + bpf_slow_path_common(4) + /* Data value is on stack, and cr0 != LT */ + lwz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_half: + bpf_slow_path_common(2) + lhz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte: + bpf_slow_path_common(1) + lbz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte_msh: + bpf_slow_path_common(1) + lbz r_X, BPF_PPC_STACK_BASIC+(2*8)(r1) + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c new file mode 100644 index 000000000000..73619d3aeb6c --- /dev/null +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -0,0 +1,694 @@ +/* bpf_jit_comp.c: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * Based on the x86 BPF compiler, by Eric Dumazet (eric.dumazet@gmail.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#include <linux/moduleloader.h> +#include <asm/cacheflush.h> +#include <linux/netdevice.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +#ifndef __BIG_ENDIAN +/* There are endianness assumptions herein. */ +#error "Little-endian PPC not supported in BPF compiler" +#endif + +int bpf_jit_enable __read_mostly; + + +static inline void bpf_flush_icache(void *start, void *end) +{ + smp_wmb(); + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx) +{ + int i; + const struct sock_filter *filter = fp->insns; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + /* Make stackframe */ + if (ctx->seen & SEEN_DATAREF) { + /* If we call any helpers (for loads), save LR */ + EMIT(PPC_INST_MFLR | __PPC_RT(0)); + PPC_STD(0, 1, 16); + + /* Back up non-volatile regs. */ + PPC_STD(r_D, 1, -(8*(32-r_D))); + PPC_STD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* + * Conditionally save regs r15-r31 as some will be used + * for M[] data. + */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_STD(i, 1, -(8*(32-i))); + } + } + EMIT(PPC_INST_STDU | __PPC_RS(1) | __PPC_RA(1) | + (-BPF_PPC_STACKFRAME & 0xfffc)); + } + + if (ctx->seen & SEEN_DATAREF) { + /* + * If this filter needs to access skb data, + * prepare r_D and r_HL: + * r_HL = skb->len - skb->data_len + * r_D = skb->data + */ + PPC_LWZ_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + data_len)); + PPC_LWZ_OFFS(r_HL, r_skb, offsetof(struct sk_buff, len)); + PPC_SUB(r_HL, r_HL, r_scratch1); + PPC_LD_OFFS(r_D, r_skb, offsetof(struct sk_buff, data)); + } + + if (ctx->seen & SEEN_XREG) { + /* + * TODO: Could also detect whether first instr. sets X and + * avoid this (as below, with A). + */ + PPC_LI(r_X, 0); + } + + switch (filter[0].code) { + case BPF_S_RET_K: + case BPF_S_LD_W_LEN: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_CPU: + case BPF_S_ANC_QUEUE: + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + /* first instruction sets A register (or is RET 'constant') */ + break; + default: + /* make sure we dont leak kernel information to user */ + PPC_LI(r_A, 0); + } +} + +static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + int i; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + PPC_ADDI(1, 1, BPF_PPC_STACKFRAME); + if (ctx->seen & SEEN_DATAREF) { + PPC_LD(0, 1, 16); + PPC_MTLR(0); + PPC_LD(r_D, 1, -(8*(32-r_D))); + PPC_LD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* Restore any saved non-vol registers */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_LD(i, 1, -(8*(32-i))); + } + } + } + /* The RETs have left a return value in R3. */ + + PPC_BLR(); +} + +/* Assemble the body code between the prologue & epilogue. */ +static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx, + unsigned int *addrs) +{ + const struct sock_filter *filter = fp->insns; + int flen = fp->len; + u8 *func; + unsigned int true_cond; + int i; + + /* Start of epilogue code */ + unsigned int exit_addr = addrs[flen]; + + for (i = 0; i < flen; i++) { + unsigned int K = filter[i].k; + + /* + * addrs[] maps a BPF bytecode address into a real offset from + * the start of the body code. + */ + addrs[i] = ctx->idx * 4; + + switch (filter[i].code) { + /*** ALU ops ***/ + case BPF_S_ALU_ADD_X: /* A += X; */ + ctx->seen |= SEEN_XREG; + PPC_ADD(r_A, r_A, r_X); + break; + case BPF_S_ALU_ADD_K: /* A += K; */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(K)); + break; + case BPF_S_ALU_SUB_X: /* A -= X; */ + ctx->seen |= SEEN_XREG; + PPC_SUB(r_A, r_A, r_X); + break; + case BPF_S_ALU_SUB_K: /* A -= K */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(-K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(-K)); + break; + case BPF_S_ALU_MUL_X: /* A *= X; */ + ctx->seen |= SEEN_XREG; + PPC_MUL(r_A, r_A, r_X); + break; + case BPF_S_ALU_MUL_K: /* A *= K */ + if (K < 32768) + PPC_MULI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_MUL(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_DIV_X: /* A /= X; */ + ctx->seen |= SEEN_XREG; + PPC_CMPWI(r_X, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* + * Exit, returning 0; first pass hits here + * (longer worst-case code size). + */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + PPC_DIVWU(r_A, r_A, r_X); + break; + case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ + PPC_LI32(r_scratch1, K); + /* Top 32 bits of 64bit result -> A */ + PPC_MULHWU(r_A, r_A, r_scratch1); + break; + case BPF_S_ALU_AND_X: + ctx->seen |= SEEN_XREG; + PPC_AND(r_A, r_A, r_X); + break; + case BPF_S_ALU_AND_K: + if (!IMM_H(K)) + PPC_ANDI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_OR_X: + ctx->seen |= SEEN_XREG; + PPC_OR(r_A, r_A, r_X); + break; + case BPF_S_ALU_OR_K: + if (IMM_L(K)) + PPC_ORI(r_A, r_A, IMM_L(K)); + if (K >= 65536) + PPC_ORIS(r_A, r_A, IMM_H(K)); + break; + case BPF_S_ALU_LSH_X: /* A <<= X; */ + ctx->seen |= SEEN_XREG; + PPC_SLW(r_A, r_A, r_X); + break; + case BPF_S_ALU_LSH_K: + if (K == 0) + break; + else + PPC_SLWI(r_A, r_A, K); + break; + case BPF_S_ALU_RSH_X: /* A >>= X; */ + ctx->seen |= SEEN_XREG; + PPC_SRW(r_A, r_A, r_X); + break; + case BPF_S_ALU_RSH_K: /* A >>= K; */ + if (K == 0) + break; + else + PPC_SRWI(r_A, r_A, K); + break; + case BPF_S_ALU_NEG: + PPC_NEG(r_A, r_A); + break; + case BPF_S_RET_K: + PPC_LI32(r_ret, K); + if (!K) { + if (ctx->pc_ret0 == -1) + ctx->pc_ret0 = i; + } + /* + * If this isn't the very last instruction, branch to + * the epilogue if we've stuff to clean up. Otherwise, + * if there's nothing to tidy, just return. If we /are/ + * the last instruction, we're about to fall through to + * the epilogue to return. + */ + if (i != flen - 1) { + /* + * Note: 'seen' is properly valid only on pass + * #2. Both parts of this conditional are the + * same instruction size though, meaning the + * first pass will still correctly determine the + * code size/addresses. + */ + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_RET_A: + PPC_MR(r_ret, r_A); + if (i != flen - 1) { + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_MISC_TAX: /* X = A */ + PPC_MR(r_X, r_A); + break; + case BPF_S_MISC_TXA: /* A = X */ + ctx->seen |= SEEN_XREG; + PPC_MR(r_A, r_X); + break; + + /*** Constant loads/M[] access ***/ + case BPF_S_LD_IMM: /* A = K */ + PPC_LI32(r_A, K); + break; + case BPF_S_LDX_IMM: /* X = K */ + PPC_LI32(r_X, K); + break; + case BPF_S_LD_MEM: /* A = mem[K] */ + PPC_MR(r_A, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LDX_MEM: /* X = mem[K] */ + PPC_MR(r_X, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_ST: /* mem[K] = A */ + PPC_MR(r_M + (K & 0xf), r_A); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_STX: /* mem[K] = X */ + PPC_MR(r_M + (K & 0xf), r_X); + ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LD_W_LEN: /* A = skb->len; */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); + break; + case BPF_S_LDX_W_LEN: /* X = skb->len; */ + PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); + break; + + /*** Ancillary info loads ***/ + + /* None of the BPF_S_ANC* codes appear to be passed by + * sk_chk_filter(). The interpreter and the x86 BPF + * compiler implement them so we do too -- they may be + * planted in future. + */ + case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + protocol) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + protocol)); + /* ntohs is a NOP with BE loads. */ + break; + case BPF_S_ANC_IFINDEX: + PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + dev)); + PPC_CMPDI(r_scratch1, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* Exit, returning 0; first pass hits here. */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + ifindex) != 4); + PPC_LWZ_OFFS(r_A, r_scratch1, + offsetof(struct net_device, ifindex)); + break; + case BPF_S_ANC_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + mark)); + break; + case BPF_S_ANC_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + rxhash)); + break; + case BPF_S_ANC_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + queue_mapping) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + queue_mapping)); + break; + case BPF_S_ANC_CPU: +#ifdef CONFIG_SMP + /* + * PACA ptr is r13: + * raw_smp_processor_id() = local_paca->paca_index + */ + BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, + paca_index) != 2); + PPC_LHZ_OFFS(r_A, 13, + offsetof(struct paca_struct, paca_index)); +#else + PPC_LI(r_A, 0); +#endif + break; + + /*** Absolute loads from packet header/data ***/ + case BPF_S_LD_W_ABS: + func = sk_load_word; + goto common_load; + case BPF_S_LD_H_ABS: + func = sk_load_half; + goto common_load; + case BPF_S_LD_B_ABS: + func = sk_load_byte; + common_load: + /* + * Load from [K]. Reference with the (negative) + * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported. + */ + ctx->seen |= SEEN_DATAREF; + if ((int)K < 0) + return -ENOTSUPP; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_LI32(r_addr, K); + PPC_BLRL(); + /* + * Helper returns 'lt' condition on error, and an + * appropriate return value in r3 + */ + PPC_BCC(COND_LT, exit_addr); + break; + + /*** Indirect loads from packet header/data ***/ + case BPF_S_LD_W_IND: + func = sk_load_word; + goto common_load_ind; + case BPF_S_LD_H_IND: + func = sk_load_half; + goto common_load_ind; + case BPF_S_LD_B_IND: + func = sk_load_byte; + common_load_ind: + /* + * Load from [X + K]. Negative offsets are tested for + * in the helper functions, and result in a 'ret 0'. + */ + ctx->seen |= SEEN_DATAREF | SEEN_XREG; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_ADDI(r_addr, r_X, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_addr, r_addr, IMM_HA(K)); + PPC_BLRL(); + /* If error, cr0.LT set */ + PPC_BCC(COND_LT, exit_addr); + break; + + case BPF_S_LDX_B_MSH: + /* + * x86 version drops packet (RET 0) when K<0, whereas + * interpreter does allow K<0 (__load_pointer, special + * ancillary data). common_load returns ENOTSUPP if K<0, + * so we fall back to interpreter & filter works. + */ + func = sk_load_byte_msh; + goto common_load; + break; + + /*** Jump and branches ***/ + case BPF_S_JMP_JA: + if (K != 0) + PPC_JMP(addrs[i + 1 + K]); + break; + + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + true_cond = COND_GT; + goto cond_branch; + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + true_cond = COND_GE; + goto cond_branch; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + true_cond = COND_EQ; + goto cond_branch; + case BPF_S_JMP_JSET_K: + case BPF_S_JMP_JSET_X: + true_cond = COND_NE; + /* Fall through */ + cond_branch: + /* same targets, can avoid doing the test :) */ + if (filter[i].jt == filter[i].jf) { + if (filter[i].jt > 0) + PPC_JMP(addrs[i + 1 + filter[i].jt]); + break; + } + + switch (filter[i].code) { + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JEQ_X: + ctx->seen |= SEEN_XREG; + PPC_CMPLW(r_A, r_X); + break; + case BPF_S_JMP_JSET_X: + ctx->seen |= SEEN_XREG; + PPC_AND_DOT(r_scratch1, r_A, r_X); + break; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGE_K: + if (K < 32768) + PPC_CMPLWI(r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_CMPLW(r_A, r_scratch1); + } + break; + case BPF_S_JMP_JSET_K: + if (K < 32768) + /* PPC_ANDI is /only/ dot-form */ + PPC_ANDI(r_scratch1, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND_DOT(r_scratch1, r_A, + r_scratch1); + } + break; + } + /* Sometimes branches are constructed "backward", with + * the false path being the branch and true path being + * a fallthrough to the next instruction. + */ + if (filter[i].jt == 0) + /* Swap the sense of the branch */ + PPC_BCC(true_cond ^ COND_CMP_TRUE, + addrs[i + 1 + filter[i].jf]); + else { + PPC_BCC(true_cond, addrs[i + 1 + filter[i].jt]); + if (filter[i].jf != 0) + PPC_JMP(addrs[i + 1 + filter[i].jf]); + } + break; + default: + /* The filter contains something cruel & unusual. + * We don't handle it, but also there shouldn't be + * anything missing from our list. + */ + if (printk_ratelimit()) + pr_err("BPF filter opcode %04x (@%d) unsupported\n", + filter[i].code, i); + return -ENOTSUPP; + } + + } + /* Set end-of-body-code address for exit. */ + addrs[i] = ctx->idx * 4; + + return 0; +} + +void bpf_jit_compile(struct sk_filter *fp) +{ + unsigned int proglen; + unsigned int alloclen; + u32 *image = NULL; + u32 *code_base; + unsigned int *addrs; + struct codegen_context cgctx; + int pass; + int flen = fp->len; + + if (!bpf_jit_enable) + return; + + addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL); + if (addrs == NULL) + return; + + /* + * There are multiple assembly passes as the generated code will change + * size as it settles down, figuring out the max branch offsets/exit + * paths required. + * + * The range of standard conditional branches is +/- 32Kbytes. Since + * BPF_MAXINSNS = 4096, we can only jump from (worst case) start to + * finish with 8 bytes/instruction. Not feasible, so long jumps are + * used, distinct from short branches. + * + * Current: + * + * For now, both branch types assemble to 2 words (short branches padded + * with a NOP); this is less efficient, but assembly will always complete + * after exactly 3 passes: + * + * First pass: No code buffer; Program is "faux-generated" -- no code + * emitted but maximum size of output determined (and addrs[] filled + * in). Also, we note whether we use M[], whether we use skb data, etc. + * All generation choices assumed to be 'worst-case', e.g. branches all + * far (2 instructions), return path code reduction not available, etc. + * + * Second pass: Code buffer allocated with size determined previously. + * Prologue generated to support features we have seen used. Exit paths + * determined and addrs[] is filled in again, as code may be slightly + * smaller as a result. + * + * Third pass: Code generated 'for real', and branch destinations + * determined from now-accurate addrs[] map. + * + * Ideal: + * + * If we optimise this, near branches will be shorter. On the + * first assembly pass, we should err on the side of caution and + * generate the biggest code. On subsequent passes, branches will be + * generated short or long and code size will reduce. With smaller + * code, more branches may fall into the short category, and code will + * reduce more. + * + * Finally, if we see one pass generate code the same size as the + * previous pass we have converged and should now generate code for + * real. Allocating at the end will also save the memory that would + * otherwise be wasted by the (small) current code shrinkage. + * Preferably, we should do a small number of passes (e.g. 5) and if we + * haven't converged by then, get impatient and force code to generate + * as-is, even if the odd branch would be left long. The chances of a + * long jump are tiny with all but the most enormous of BPF filter + * inputs, so we should usually converge on the third pass. + */ + + cgctx.idx = 0; + cgctx.seen = 0; + cgctx.pc_ret0 = -1; + /* Scouting faux-generate pass 0 */ + if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) + /* We hit something illegal or unsupported. */ + goto out; + + /* + * Pretend to build prologue, given the features we've seen. This will + * update ctgtx.idx as it pretends to output instructions, then we can + * calculate total size from idx. + */ + bpf_jit_build_prologue(fp, 0, &cgctx); + bpf_jit_build_epilogue(0, &cgctx); + + proglen = cgctx.idx * 4; + alloclen = proglen + FUNCTION_DESCR_SIZE; + image = module_alloc(max_t(unsigned int, alloclen, + sizeof(struct work_struct))); + if (!image) + goto out; + + code_base = image + (FUNCTION_DESCR_SIZE/4); + + /* Code generation passes 1-2 */ + for (pass = 1; pass < 3; pass++) { + /* Now build the prologue, body code & epilogue for real. */ + cgctx.idx = 0; + bpf_jit_build_prologue(fp, code_base, &cgctx); + bpf_jit_build_body(fp, code_base, &cgctx, addrs); + bpf_jit_build_epilogue(code_base, &cgctx); + + if (bpf_jit_enable > 1) + pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass, + proglen - (cgctx.idx * 4), cgctx.seen); + } + + if (bpf_jit_enable > 1) + pr_info("flen=%d proglen=%u pass=%d image=%p\n", + flen, proglen, pass, image); + + if (image) { + if (bpf_jit_enable > 1) + print_hex_dump(KERN_ERR, "JIT code: ", + DUMP_PREFIX_ADDRESS, + 16, 1, code_base, + proglen, false); + + bpf_flush_icache(code_base, code_base + (proglen/4)); + /* Function descriptor nastiness: Address + TOC */ + ((u64 *)image)[0] = (u64)code_base; + ((u64 *)image)[1] = local_paca->kernel_toc; + fp->bpf_func = (void *)image; + } +out: + kfree(addrs); + return; +} + +static void jit_free_defer(struct work_struct *arg) +{ + module_free(NULL, arg); +} + +/* run from softirq, we must use a work_struct to call + * module_free() from process context + */ +void bpf_jit_free(struct sk_filter *fp) +{ + if (fp->bpf_func != sk_run_filter) { + struct work_struct *work = (struct work_struct *)fp->bpf_func; + + INIT_WORK(work, jit_free_defer); + schedule_work(work); + } +} diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 47ea1be1481b..90f4496017e4 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -55,14 +55,6 @@ config PPC_MPC5200_BUGFIX It is safe to say 'Y' here -config PPC_MPC5200_GPIO - bool "MPC5200 GPIO support" - depends on PPC_MPC52xx - select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO - help - Enable gpiolib support for mpc5200 based boards - config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" depends on PPC_MPC52xx diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index 2bc8cd0c5cfc..4e62486791e9 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -14,5 +14,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y) obj-$(CONFIG_PM) += lite5200_sleep.o lite5200_pm.o endif -obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o obj-$(CONFIG_PPC_MPC5200_LPBFIFO) += mpc52xx_lpbfifo.o diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c deleted file mode 100644 index 1757d1db4b51..000000000000 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ /dev/null @@ -1,380 +0,0 @@ -/* - * MPC52xx gpio driver - * - * Copyright (c) 2008 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/of.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/of_gpio.h> -#include <linux/io.h> -#include <linux/of_platform.h> - -#include <asm/gpio.h> -#include <asm/mpc52xx.h> -#include <sysdev/fsl_soc.h> - -static DEFINE_SPINLOCK(gpio_lock); - -struct mpc52xx_gpiochip { - struct of_mm_gpio_chip mmchip; - unsigned int shadow_dvo; - unsigned int shadow_gpioe; - unsigned int shadow_ddr; -}; - -/* - * GPIO LIB API implementation for wakeup GPIOs. - * - * There's a maximum of 8 wakeup GPIOs. Which of these are available - * for use depends on your board setup. - * - * 0 -> GPIO_WKUP_7 - * 1 -> GPIO_WKUP_6 - * 2 -> PSC6_1 - * 3 -> PSC6_0 - * 4 -> ETH_17 - * 5 -> PSC3_9 - * 6 -> PSC2_4 - * 7 -> PSC1_4 - * - */ -static int mpc52xx_wkup_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_8(®s->wkup_ival) >> (7 - gpio)) & 1; - - pr_debug("%s: gpio: %d ret: %d\n", __func__, gpio, ret); - - return ret; -} - -static inline void -__mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (7 - gpio); - else - chip->shadow_dvo &= ~(1 << (7 - gpio)); - - out_8(®s->wkup_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_wkup_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (7 - gpio)); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_wkup_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (7 - gpio); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct mpc52xx_gpio_wkup __iomem *regs; - struct gpio_chip *gc; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 8; - gc->direction_input = mpc52xx_wkup_gpio_dir_in; - gc->direction_output = mpc52xx_wkup_gpio_dir_out; - gc->get = mpc52xx_wkup_gpio_get; - gc->set = mpc52xx_wkup_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_8(®s->wkup_gpioe); - chip->shadow_ddr = in_8(®s->wkup_ddr); - chip->shadow_dvo = in_8(®s->wkup_dvo); - - return 0; -} - -static int mpc52xx_gpiochip_remove(struct platform_device *ofdev) -{ - return -EBUSY; -} - -static const struct of_device_id mpc52xx_wkup_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio-wkup", - }, - {} -}; - -static struct platform_driver mpc52xx_wkup_gpiochip_driver = { - .driver = { - .name = "gpio_wkup", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_wkup_gpiochip_match, - }, - .probe = mpc52xx_wkup_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -/* - * GPIO LIB API implementation for simple GPIOs - * - * There's a maximum of 32 simple GPIOs. Which of these are available - * for use depends on your board setup. - * The numbering reflects the bit numbering in the port registers: - * - * 0..1 > reserved - * 2..3 > IRDA - * 4..7 > ETHR - * 8..11 > reserved - * 12..15 > USB - * 16..17 > reserved - * 18..23 > PSC3 - * 24..27 > PSC2 - * 28..31 > PSC1 - */ -static int mpc52xx_simple_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_be32(®s->simple_ival) >> (31 - gpio)) & 1; - - return ret; -} - -static inline void -__mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (31 - gpio); - else - chip->shadow_dvo &= ~(1 << (31 - gpio)); - out_be32(®s->simple_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_simple_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_simple_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (31 - gpio)); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_simple_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* First set initial value */ - __mpc52xx_simple_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (31 - gpio); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct gpio_chip *gc; - struct mpc52xx_gpio __iomem *regs; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 32; - gc->direction_input = mpc52xx_simple_gpio_dir_in; - gc->direction_output = mpc52xx_simple_gpio_dir_out; - gc->get = mpc52xx_simple_gpio_get; - gc->set = mpc52xx_simple_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_be32(®s->simple_gpioe); - chip->shadow_ddr = in_be32(®s->simple_ddr); - chip->shadow_dvo = in_be32(®s->simple_dvo); - - return 0; -} - -static const struct of_device_id mpc52xx_simple_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio", - }, - {} -}; - -static struct platform_driver mpc52xx_simple_gpiochip_driver = { - .driver = { - .name = "gpio", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_simple_gpiochip_match, - }, - .probe = mpc52xx_simple_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -static int __init mpc52xx_gpio_init(void) -{ - if (platform_driver_register(&mpc52xx_wkup_gpiochip_driver)) - printk(KERN_ERR "Unable to register wakeup GPIO driver\n"); - - if (platform_driver_register(&mpc52xx_simple_gpiochip_driver)) - printk(KERN_ERR "Unable to register simple GPIO driver\n"); - - return 0; -} - - -/* Make sure we get initialised before anyone else tries to use us */ -subsys_initcall(mpc52xx_gpio_init); - -/* No exit call at the moment as we cannot unregister of gpio chips */ - -MODULE_DESCRIPTION("Freescale MPC52xx gpio driver"); -MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de"); -MODULE_LICENSE("GPL v2"); - diff --git a/arch/powerpc/platforms/amigaone/Kconfig b/arch/powerpc/platforms/amigaone/Kconfig index 022476717718..128de25cc284 100644 --- a/arch/powerpc/platforms/amigaone/Kconfig +++ b/arch/powerpc/platforms/amigaone/Kconfig @@ -8,7 +8,7 @@ config AMIGAONE select NOT_COHERENT_CACHE select CHECK_CACHE_COHERENCY select DEFAULT_UIMAGE - select PCSPKR_PLATFORM + select HAVE_PCSPKR_PLATFORM help Select AmigaOne for the following machines: - AmigaOne SE/Teron CX (G3 only) diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 3c7c3f82d842..fb59c46e9e9e 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1850,9 +1850,16 @@ out: return ret; } -static int spufs_mfc_fsync(struct file *file, int datasync) +static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - return spufs_mfc_flush(file, NULL); + struct inode *inode = file->f_path.dentry->d_inode; + int err = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (!err) { + mutex_lock(&inode->i_mutex); + err = spufs_mfc_flush(file, NULL); + mutex_unlock(&inode->i_mutex); + } + return err; } static int spufs_mfc_fasync(int fd, struct file *file, int on) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 856e9c398068..e481f6b9a789 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -611,15 +611,14 @@ out: static struct file_system_type spufs_type; -long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode, - struct file *filp) +long spufs_create(struct path *path, struct dentry *dentry, + unsigned int flags, mode_t mode, struct file *filp) { - struct dentry *dentry; int ret; ret = -EINVAL; /* check if we are on spufs */ - if (nd->path.dentry->d_sb->s_type != &spufs_type) + if (path->dentry->d_sb->s_type != &spufs_type) goto out; /* don't accept undefined flags */ @@ -627,33 +626,27 @@ long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode, goto out; /* only threads can be underneath a gang */ - if (nd->path.dentry != nd->path.dentry->d_sb->s_root) { + if (path->dentry != path->dentry->d_sb->s_root) { if ((flags & SPU_CREATE_GANG) || - !SPUFS_I(nd->path.dentry->d_inode)->i_gang) + !SPUFS_I(path->dentry->d_inode)->i_gang) goto out; } - dentry = lookup_create(nd, 1); - ret = PTR_ERR(dentry); - if (IS_ERR(dentry)) - goto out_dir; - mode &= ~current_umask(); if (flags & SPU_CREATE_GANG) - ret = spufs_create_gang(nd->path.dentry->d_inode, - dentry, nd->path.mnt, mode); + ret = spufs_create_gang(path->dentry->d_inode, + dentry, path->mnt, mode); else - ret = spufs_create_context(nd->path.dentry->d_inode, - dentry, nd->path.mnt, flags, mode, + ret = spufs_create_context(path->dentry->d_inode, + dentry, path->mnt, flags, mode, filp); if (ret >= 0) - fsnotify_mkdir(nd->path.dentry->d_inode, dentry); + fsnotify_mkdir(path->dentry->d_inode, dentry); return ret; -out_dir: - mutex_unlock(&nd->path.dentry->d_inode->i_mutex); out: + mutex_unlock(&path->dentry->d_inode->i_mutex); return ret; } diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index c448bac65518..099245f230b2 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -248,7 +248,7 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[]; /* system call implementation */ extern struct spufs_calls spufs_calls; long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status); -long spufs_create(struct nameidata *nd, unsigned int flags, +long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags, mode_t mode, struct file *filp); /* ELF coredump callbacks for writing SPU ELF notes */ extern int spufs_coredump_extra_notes_size(void); diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c index a3d2ce54ea2e..609e016e92d0 100644 --- a/arch/powerpc/platforms/cell/spufs/syscalls.c +++ b/arch/powerpc/platforms/cell/spufs/syscalls.c @@ -62,21 +62,17 @@ out: static long do_spu_create(const char __user *pathname, unsigned int flags, mode_t mode, struct file *neighbor) { - char *tmp; + struct path path; + struct dentry *dentry; int ret; - tmp = getname(pathname); - ret = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - struct nameidata nd; - - ret = kern_path_parent(tmp, &nd); - if (!ret) { - nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE; - ret = spufs_create(&nd, flags, mode, neighbor); - path_put(&nd.path); - } - putname(tmp); + dentry = user_path_create(AT_FDCWD, pathname, &path, 1); + ret = PTR_ERR(dentry); + if (!IS_ERR(dentry)) { + ret = spufs_create(&path, dentry, flags, mode, neighbor); + mutex_unlock(&path.dentry->d_inode->i_mutex); + dput(dentry); + path_put(&path); } return ret; diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig index bc0b0efdc5fe..d3cdab582c5d 100644 --- a/arch/powerpc/platforms/chrp/Kconfig +++ b/arch/powerpc/platforms/chrp/Kconfig @@ -1,6 +1,7 @@ config PPC_CHRP bool "Common Hardware Reference Platform (CHRP) based machines" depends on 6xx + select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 select PPC_INDIRECT_PCI diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index f33e08d573ce..abe8d7e2ebeb 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/bootmem.h> #include <linux/irq.h> +#include <linux/of_pci.h> #include <asm/sections.h> #include <asm/io.h> @@ -235,7 +236,7 @@ static int chaos_validate_dev(struct pci_bus *bus, int devfn, int offset) if (offset >= 0x100) return PCIBIOS_BAD_REGISTER_NUMBER; - np = pci_busdev_to_OF_node(bus, devfn); + np = of_pci_find_child_device(bus->dev.of_node, devfn); if (np == NULL) return PCIBIOS_DEVICE_NOT_FOUND; diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig index bf8330ef2e76..f0536c7cda9f 100644 --- a/arch/powerpc/platforms/prep/Kconfig +++ b/arch/powerpc/platforms/prep/Kconfig @@ -1,6 +1,7 @@ config PPC_PREP bool "PowerPC Reference Platform (PReP) based machines" depends on 6xx && BROKEN + select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 select PPC_INDIRECT_PCI diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 71af4c5d6c05..05cf4769b88c 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -1,6 +1,7 @@ config PPC_PSERIES depends on PPC64 && PPC_BOOK3S bool "IBM pSeries & new (POWER5-based) iSeries" + select HAVE_PCSPKR_PLATFORM select MPIC select PCI_MSI select PPC_XICS |