From 273c11270d3715c4c06d4df1607a1a60034d887b Mon Sep 17 00:00:00 2001 From: Miklos Vajna Date: Tue, 13 May 2008 18:38:56 +0200 Subject: x86/PCI: janitor work in irq.c Wrapped long lines, removed trailing whitespaces, fixed case indentation inside switch and so. Signed-off-by: Miklos Vajna Signed-off-by: Jesse Barnes --- arch/x86/pci/irq.c | 511 ++++++++++++++++++++++++++++++----------------------- 1 file changed, 294 insertions(+), 217 deletions(-) (limited to 'arch') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index ca8df9c260bc..c422e10337be 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -11,8 +11,8 @@ #include #include #include -#include -#include +#include +#include #include #include #include @@ -45,7 +45,8 @@ struct irq_router { char *name; u16 vendor, device; int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); - int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); + int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, + int new); }; struct irq_router_handler { @@ -61,7 +62,7 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL; * and perform checksum verification. */ -static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr) +static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) { struct irq_routing_table *rt; int i; @@ -74,10 +75,11 @@ static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr) rt->size < sizeof(struct irq_routing_table)) return NULL; sum = 0; - for (i=0; i < rt->size; i++) + for (i = 0; i < rt->size; i++) sum += addr[i]; if (!sum) { - DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", rt); + DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", + rt); return rt; } return NULL; @@ -100,7 +102,8 @@ static struct irq_routing_table * __init pirq_find_routing_table(void) return rt; printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); } - for(addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { + for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); + addr += 16) { rt = pirq_check_routing_table(addr); if (rt) return rt; @@ -122,20 +125,23 @@ static void __init pirq_peer_trick(void) struct irq_info *e; memset(busmap, 0, sizeof(busmap)); - for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) { + for (i = 0; i < (rt->size - sizeof(struct irq_routing_table)) / + sizeof(struct irq_info); i++) { e = &rt->slots[i]; #ifdef DEBUG { int j; - DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); - for(j=0; j<4; j++) - DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); + DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, + e->devfn/8, e->slot); + for (j = 0; j < 4; j++) + DBG(" %d:%02x/%04x", j, e->irq[j].link, + e->irq[j].bitmap); DBG("\n"); } #endif busmap[e->bus] = 1; } - for(i = 1; i < 256; i++) { + for (i = 1; i < 256; i++) { int node; if (!busmap[i] || pci_find_bus(0, i)) continue; @@ -174,7 +180,8 @@ void eisa_set_level_irq(unsigned int irq) * Common IRQ routing practice: nibbles in config space, * offset by some magic constant. */ -static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr) +static unsigned int +read_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr) { u8 x; unsigned reg = offset + (nr >> 1); @@ -183,7 +190,8 @@ static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, return (nr & 1) ? (x >> 4) : (x & 0xf); } -static void write_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr, unsigned int val) +static void write_config_nybble(struct pci_dev *router, unsigned offset, + unsigned nr, unsigned int val) { u8 x; unsigned reg = offset + (nr >> 1); @@ -200,15 +208,18 @@ static void write_config_nybble(struct pci_dev *router, unsigned offset, unsigne */ static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { - static const unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0, 12, 0, 14, 0, 15 }; + static const unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, + 11, 0, 12, 0, 14, 0, 15 }; WARN_ON_ONCE(pirq > 16); return irqmap[read_config_nybble(router, 0x48, pirq-1)]; } -static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - static const unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 }; + static const unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, + 3, 9, 11, 0, 13, 15 }; unsigned int val = irqmap[irq]; WARN_ON_ONCE(pirq > 16); @@ -231,7 +242,8 @@ static int pirq_piix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return (x < 16) ? x : 0; } -static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { pci_write_config_byte(router, pirq, irq); return 1; @@ -247,7 +259,8 @@ static int pirq_via_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return read_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq); } -static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { write_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq, irq); return 1; @@ -258,7 +271,8 @@ static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i * but without the ugly irq number munging. * However, for 82C586, nibble map is different . */ -static int pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int +pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 }; @@ -266,7 +280,8 @@ static int pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq return read_config_nybble(router, 0x55, pirqmap[pirq-1]); } -static int pirq_via586_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_via586_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 }; @@ -285,10 +300,11 @@ static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq) static const unsigned char pirqmap[4] = { 1, 0, 2, 3 }; WARN_ON_ONCE(pirq > 4); - return read_config_nybble(router,0x43, pirqmap[pirq-1]); + return read_config_nybble(router, 0x43, pirqmap[pirq-1]); } -static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { static const unsigned char pirqmap[4] = { 1, 0, 2, 3 }; @@ -306,7 +322,8 @@ static int pirq_opti_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return read_config_nybble(router, 0xb8, pirq >> 4); } -static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { write_config_nybble(router, 0xb8, pirq >> 4, irq); return 1; @@ -314,7 +331,7 @@ static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, /* * Cyrix: nibble offset 0x5C - * 0x5C bits 7:4 is INTB bits 3:0 is INTA + * 0x5C bits 7:4 is INTB bits 3:0 is INTA * 0x5D bits 7:4 is INTD bits 3:0 is INTC */ static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) @@ -322,7 +339,8 @@ static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return read_config_nybble(router, 0x5C, (pirq-1)^1); } -static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { write_config_nybble(router, 0x5C, (pirq-1)^1, irq); return 1; @@ -350,7 +368,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * Apparently there are systems implementing PCI routing table using * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D. * We try our best to handle both link mappings. - * + * * Currently (2003-05-21) it appears most SiS chipsets follow the * definition of routing registers from the SiS-5595 southbridge. * According to the SiS 5595 datasheets the revision id's of the @@ -370,7 +388,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * * 0x62: USBIRQ: * bit 6 OHCI function disabled (0), enabled (1) - * + * * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved * * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved @@ -405,7 +423,8 @@ static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); } -static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { u8 x; int reg; @@ -439,7 +458,8 @@ static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq) return read_config_nybble(router, 0x74, pirq-1); } -static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { WARN_ON_ONCE(pirq >= 9); if (pirq > 8) { @@ -461,13 +481,15 @@ static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * 0x00 for ACPI (SCI), 0x01 for USB, 0x02 for IDE0, 0x04 for IDE1, * and 0x03 for SMBus. */ -static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int +pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { outb(pirq, 0xc00); return inb(0xc01) & 0xf; } -static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) { outb(pirq, 0xc00); outb(irq, 0xc01); @@ -482,27 +504,27 @@ static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, int * offset 0x56 0-3 PIRQA 4-7 PIRQB * offset 0x57 0-3 PIRQC 4-7 PIRQD */ -static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int +pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { u8 irq; irq = 0; if (pirq <= 4) - { irq = read_config_nybble(router, 0x56, pirq - 1); - } - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", + printk(KERN_INFO + "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", dev->vendor, dev->device, pirq, irq); return irq; } -static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", + printk(KERN_INFO + "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", dev->vendor, dev->device, pirq, irq); if (pirq <= 4) - { write_config_nybble(router, 0x56, pirq - 1, irq); - } return 1; } @@ -528,7 +550,8 @@ static int pirq_pico_set(struct pci_dev *router, struct pci_dev *dev, int pirq, #ifdef CONFIG_PCI_BIOS -static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int +pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { struct pci_dev *bridge; int pin = pci_get_interrupt_pin(dev, &bridge); @@ -537,11 +560,14 @@ static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, #endif -static __init int intel_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +intel_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { static struct pci_device_id __initdata pirq_440gx[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_0) }, - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_2) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82443GX_0) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82443GX_2) }, { }, }; @@ -549,50 +575,49 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route if (pci_dev_present(pirq_440gx)) return 0; - switch(device) - { - case PCI_DEVICE_ID_INTEL_82371FB_0: - case PCI_DEVICE_ID_INTEL_82371SB_0: - case PCI_DEVICE_ID_INTEL_82371AB_0: - case PCI_DEVICE_ID_INTEL_82371MX: - case PCI_DEVICE_ID_INTEL_82443MX_0: - case PCI_DEVICE_ID_INTEL_82801AA_0: - case PCI_DEVICE_ID_INTEL_82801AB_0: - case PCI_DEVICE_ID_INTEL_82801BA_0: - case PCI_DEVICE_ID_INTEL_82801BA_10: - case PCI_DEVICE_ID_INTEL_82801CA_0: - case PCI_DEVICE_ID_INTEL_82801CA_12: - case PCI_DEVICE_ID_INTEL_82801DB_0: - case PCI_DEVICE_ID_INTEL_82801E_0: - case PCI_DEVICE_ID_INTEL_82801EB_0: - case PCI_DEVICE_ID_INTEL_ESB_1: - case PCI_DEVICE_ID_INTEL_ICH6_0: - case PCI_DEVICE_ID_INTEL_ICH6_1: - case PCI_DEVICE_ID_INTEL_ICH7_0: - case PCI_DEVICE_ID_INTEL_ICH7_1: - case PCI_DEVICE_ID_INTEL_ICH7_30: - case PCI_DEVICE_ID_INTEL_ICH7_31: - case PCI_DEVICE_ID_INTEL_ESB2_0: - case PCI_DEVICE_ID_INTEL_ICH8_0: - case PCI_DEVICE_ID_INTEL_ICH8_1: - case PCI_DEVICE_ID_INTEL_ICH8_2: - case PCI_DEVICE_ID_INTEL_ICH8_3: - case PCI_DEVICE_ID_INTEL_ICH8_4: - case PCI_DEVICE_ID_INTEL_ICH9_0: - case PCI_DEVICE_ID_INTEL_ICH9_1: - case PCI_DEVICE_ID_INTEL_ICH9_2: - case PCI_DEVICE_ID_INTEL_ICH9_3: - case PCI_DEVICE_ID_INTEL_ICH9_4: - case PCI_DEVICE_ID_INTEL_ICH9_5: - case PCI_DEVICE_ID_INTEL_TOLAPAI_0: - case PCI_DEVICE_ID_INTEL_ICH10_0: - case PCI_DEVICE_ID_INTEL_ICH10_1: - case PCI_DEVICE_ID_INTEL_ICH10_2: - case PCI_DEVICE_ID_INTEL_ICH10_3: - r->name = "PIIX/ICH"; - r->get = pirq_piix_get; - r->set = pirq_piix_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_INTEL_82371FB_0: + case PCI_DEVICE_ID_INTEL_82371SB_0: + case PCI_DEVICE_ID_INTEL_82371AB_0: + case PCI_DEVICE_ID_INTEL_82371MX: + case PCI_DEVICE_ID_INTEL_82443MX_0: + case PCI_DEVICE_ID_INTEL_82801AA_0: + case PCI_DEVICE_ID_INTEL_82801AB_0: + case PCI_DEVICE_ID_INTEL_82801BA_0: + case PCI_DEVICE_ID_INTEL_82801BA_10: + case PCI_DEVICE_ID_INTEL_82801CA_0: + case PCI_DEVICE_ID_INTEL_82801CA_12: + case PCI_DEVICE_ID_INTEL_82801DB_0: + case PCI_DEVICE_ID_INTEL_82801E_0: + case PCI_DEVICE_ID_INTEL_82801EB_0: + case PCI_DEVICE_ID_INTEL_ESB_1: + case PCI_DEVICE_ID_INTEL_ICH6_0: + case PCI_DEVICE_ID_INTEL_ICH6_1: + case PCI_DEVICE_ID_INTEL_ICH7_0: + case PCI_DEVICE_ID_INTEL_ICH7_1: + case PCI_DEVICE_ID_INTEL_ICH7_30: + case PCI_DEVICE_ID_INTEL_ICH7_31: + case PCI_DEVICE_ID_INTEL_ESB2_0: + case PCI_DEVICE_ID_INTEL_ICH8_0: + case PCI_DEVICE_ID_INTEL_ICH8_1: + case PCI_DEVICE_ID_INTEL_ICH8_2: + case PCI_DEVICE_ID_INTEL_ICH8_3: + case PCI_DEVICE_ID_INTEL_ICH8_4: + case PCI_DEVICE_ID_INTEL_ICH9_0: + case PCI_DEVICE_ID_INTEL_ICH9_1: + case PCI_DEVICE_ID_INTEL_ICH9_2: + case PCI_DEVICE_ID_INTEL_ICH9_3: + case PCI_DEVICE_ID_INTEL_ICH9_4: + case PCI_DEVICE_ID_INTEL_ICH9_5: + case PCI_DEVICE_ID_INTEL_TOLAPAI_0: + case PCI_DEVICE_ID_INTEL_ICH10_0: + case PCI_DEVICE_ID_INTEL_ICH10_1: + case PCI_DEVICE_ID_INTEL_ICH10_2: + case PCI_DEVICE_ID_INTEL_ICH10_3: + r->name = "PIIX/ICH"; + r->get = pirq_piix_get; + r->set = pirq_piix_set; + return 1; } return 0; } @@ -606,7 +631,7 @@ static __init int via_router_probe(struct irq_router *r, * workarounds for some buggy BIOSes */ if (device == PCI_DEVICE_ID_VIA_82C586_0) { - switch(router->device) { + switch (router->device) { case PCI_DEVICE_ID_VIA_82C686: /* * Asus k7m bios wrongly reports 82C686A @@ -631,7 +656,7 @@ static __init int via_router_probe(struct irq_router *r, } } - switch(device) { + switch (device) { case PCI_DEVICE_ID_VIA_82C586_0: r->name = "VIA"; r->get = pirq_via586_get; @@ -652,88 +677,89 @@ static __init int via_router_probe(struct irq_router *r, return 0; } -static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_VLSI_82C534: - r->name = "VLSI 82C534"; - r->get = pirq_vlsi_get; - r->set = pirq_vlsi_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_VLSI_82C534: + r->name = "VLSI 82C534"; + r->get = pirq_vlsi_get; + r->set = pirq_vlsi_set; + return 1; } return 0; } -static __init int serverworks_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int serverworks_router_probe(struct irq_router *r, + struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_SERVERWORKS_OSB4: - case PCI_DEVICE_ID_SERVERWORKS_CSB5: - r->name = "ServerWorks"; - r->get = pirq_serverworks_get; - r->set = pirq_serverworks_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_SERVERWORKS_OSB4: + case PCI_DEVICE_ID_SERVERWORKS_CSB5: + r->name = "ServerWorks"; + r->get = pirq_serverworks_get; + r->set = pirq_serverworks_set; + return 1; } return 0; } -static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { if (device != PCI_DEVICE_ID_SI_503) return 0; - + r->name = "SIS"; r->get = pirq_sis_get; r->set = pirq_sis_set; return 1; } -static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_CYRIX_5520: - r->name = "NatSemi"; - r->get = pirq_cyrix_get; - r->set = pirq_cyrix_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_CYRIX_5520: + r->name = "NatSemi"; + r->get = pirq_cyrix_get; + r->set = pirq_cyrix_set; + return 1; } return 0; } -static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_OPTI_82C700: - r->name = "OPTI"; - r->get = pirq_opti_get; - r->set = pirq_opti_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_OPTI_82C700: + r->name = "OPTI"; + r->get = pirq_opti_get; + r->set = pirq_opti_set; + return 1; } return 0; } -static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_ITE_IT8330G_0: - r->name = "ITE"; - r->get = pirq_ite_get; - r->set = pirq_ite_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_ITE_IT8330G_0: + r->name = "ITE"; + r->get = pirq_ite_get; + r->set = pirq_ite_set; + return 1; } return 0; } -static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { + switch (device) { case PCI_DEVICE_ID_AL_M1533: case PCI_DEVICE_ID_AL_M1563: printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n"); @@ -745,28 +771,29 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, return 0; } -static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int +amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_AMD_VIPER_740B: - r->name = "AMD756"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7413: - r->name = "AMD766"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7443: - r->name = "AMD768"; - break; - default: - return 0; + switch (device) { + case PCI_DEVICE_ID_AMD_VIPER_740B: + r->name = "AMD756"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7413: + r->name = "AMD766"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7443: + r->name = "AMD768"; + break; + default: + return 0; } r->get = pirq_amd756_get; r->set = pirq_amd756_set; return 1; } - -static __init int pico_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) + +static __init int +pico_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { switch (device) { case PCI_DEVICE_ID_PICOPOWER_PT86C523: @@ -807,7 +834,7 @@ static struct pci_dev *pirq_router_dev; * FIXME: should we have an option to say "generic for * chipset" ? */ - + static void __init pirq_find_router(struct irq_router *r) { struct irq_routing_table *rt = pirq_table; @@ -826,7 +853,7 @@ static void __init pirq_find_router(struct irq_router *r) r->name = "default"; r->get = NULL; r->set = NULL; - + DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for %04x:%04x\n", rt->rtr_vendor, rt->rtr_device); @@ -837,12 +864,14 @@ static void __init pirq_find_router(struct irq_router *r) return; } - for( h = pirq_routers; h->vendor; h++) { + for (h = pirq_routers; h->vendor; h++) { /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev, rt->rtr_device)) + if (rt->rtr_vendor == h->vendor && + h->probe(r, pirq_router_dev, rt->rtr_device)) break; /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && h->probe(r, pirq_router_dev, pirq_router_dev->device)) + if (pirq_router_dev->vendor == h->vendor && + h->probe(r, pirq_router_dev, pirq_router_dev->device)) break; } printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n", @@ -857,11 +886,13 @@ static void __init pirq_find_router(struct irq_router *r) static struct irq_info *pirq_get_info(struct pci_dev *dev) { struct irq_routing_table *rt = pirq_table; - int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + int entries = (rt->size - sizeof(struct irq_routing_table)) / + sizeof(struct irq_info); struct irq_info *info; for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + if (info->bus == dev->bus->number && + PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) return info; return NULL; } @@ -889,7 +920,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - + DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin); info = pirq_get_info(dev); if (!info) { @@ -902,7 +933,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) DBG(" -> not routed\n" KERN_DEBUG); return 0; } - DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, pirq_table->exclusive_irqs); + DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, + pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -915,7 +947,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */ - if (acer_tm360_irqrouting && dev->irq == 11 && dev->vendor == PCI_VENDOR_ID_O2) { + if (acer_tm360_irqrouting && dev->irq == 11 && + dev->vendor == PCI_VENDOR_ID_O2) { pirq = 0x68; mask = 0x400; dev->irq = r->get(pirq_router_dev, dev, pirq); @@ -928,17 +961,20 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) */ newirq = dev->irq; if (newirq && !((1 << newirq) & mask)) { - if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0; - else printk("\n" KERN_WARNING - "PCI: IRQ %i for device %s doesn't match PIRQ mask " - "- try pci=usepirqmask\n" KERN_DEBUG, newirq, - pci_name(dev)); + if (pci_probe & PCI_USE_PIRQ_MASK) + newirq = 0; + else + printk("\n" KERN_WARNING + "PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n" + KERN_DEBUG, newirq, + pci_name(dev)); } if (!newirq && assign) { for (i = 0; i < 16; i++) { if (!(mask & (1 << i))) continue; - if (pirq_penalty[i] < pirq_penalty[newirq] && can_request_irq(i, IRQF_SHARED)) + if (pirq_penalty[i] < pirq_penalty[newirq] && + can_request_irq(i, IRQF_SHARED)) newirq = i; } } @@ -949,12 +985,13 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) irq = pirq & 0xf; DBG(" -> hardcoded IRQ %d\n", irq); msg = "Hardcoded"; - } else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ - ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) { + } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ + ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { DBG(" -> got IRQ %d\n", irq); msg = "Found"; eisa_set_level_irq(irq); - } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { + } else if (newirq && r->set && + (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { DBG(" -> assigning IRQ %d", newirq); if (r->set(pirq_router_dev, dev, pirq, newirq)) { eisa_set_level_irq(newirq); @@ -972,7 +1009,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else return 0; } - printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, pci_name(dev)); + printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, + pci_name(dev)); /* Update IRQ for all devices with the same pirq value */ while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { @@ -984,20 +1022,26 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!info) continue; if (info->irq[pin].link == pirq) { - /* We refuse to override the dev->irq information. Give a warning! */ - if ( dev2->irq && dev2->irq != irq && \ + /* + * We refuse to override the dev->irq + * information. Give a warning! + */ + if (dev2->irq && dev2->irq != irq && \ (!(pci_probe & PCI_USE_PIRQ_MASK) || \ - ((1 << dev2->irq) & mask)) ) { + ((1 << dev2->irq) & mask))) { #ifndef CONFIG_PCI_MSI - printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", - pci_name(dev2), dev2->irq, irq); + printk(KERN_INFO + "IRQ routing conflict for %s, have irq %d, want irq %d\n", + pci_name(dev2), dev2->irq, irq); #endif - continue; - } + continue; + } dev2->irq = irq; pirq_penalty[irq]++; if (dev != dev2) - printk(KERN_INFO "PCI: Sharing IRQ %d with %s\n", irq, pci_name(dev2)); + printk(KERN_INFO + "PCI: Sharing IRQ %d with %s\n", + irq, pci_name(dev2)); } } return 1; @@ -1011,15 +1055,21 @@ static void __init pcibios_fixup_irqs(void) DBG(KERN_DEBUG "PCI: IRQ fixup\n"); while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { /* - * If the BIOS has set an out of range IRQ number, just ignore it. - * Also keep track of which IRQ's are already in use. + * If the BIOS has set an out of range IRQ number, just + * ignore it. Also keep track of which IRQ's are + * already in use. */ if (dev->irq >= 16) { - DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n", pci_name(dev), dev->irq); + DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n", + pci_name(dev), dev->irq); dev->irq = 0; } - /* If the IRQ is already assigned to a PCI device, ignore its ISA use penalty */ - if (pirq_penalty[dev->irq] >= 100 && pirq_penalty[dev->irq] < 100000) + /* + * If the IRQ is already assigned to a PCI device, + * ignore its ISA use penalty + */ + if (pirq_penalty[dev->irq] >= 100 && + pirq_penalty[dev->irq] < 100000) pirq_penalty[dev->irq] = 0; pirq_penalty[dev->irq]++; } @@ -1031,31 +1081,40 @@ static void __init pcibios_fixup_irqs(void) /* * Recalculate IRQ numbers if we use the I/O APIC. */ - if (io_apic_assign_pci_irqs) - { + if (io_apic_assign_pci_irqs) { int irq; if (pin) { - pin--; /* interrupt pins are numbered starting from 1 */ - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + /* + * interrupt pins are numbered starting + * from 1 + */ + pin--; + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, + PCI_SLOT(dev->devfn), pin); /* * Busses behind bridges are typically not listed in the MP-table. * In this case we have to look up the IRQ based on the parent bus, * parent slot, and pin number. The SMP code detects such bridged * busses itself so we should get into this branch reliably. */ - if (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; + if (irq < 0 && dev->bus->parent) { + /* go back to the bridge */ + struct pci_dev *bridge = dev->bus->self; pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, - PCI_SLOT(bridge->devfn), pin); + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + PCI_SLOT(bridge->devfn), + pin); if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); + printk(KERN_WARNING + "PCI: using PPB %s[%c] to get irq %d\n", + pci_name(bridge), + 'A' + pin, irq); } if (irq >= 0) { - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", + printk(KERN_INFO + "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", pci_name(dev), 'A' + pin, irq); dev->irq = irq; } @@ -1078,7 +1137,8 @@ static int __init fix_broken_hp_bios_irq9(const struct dmi_system_id *d) { if (!broken_hp_bios_irq9) { broken_hp_bios_irq9 = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", + d->ident); } return 0; } @@ -1091,7 +1151,8 @@ static int __init fix_acer_tm360_irqrouting(const struct dmi_system_id *d) { if (!acer_tm360_irqrouting) { acer_tm360_irqrouting = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", + d->ident); } return 0; } @@ -1103,7 +1164,8 @@ static struct dmi_system_id __initdata pciirq_dmi_table[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"), - DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook Model GE"), + DMI_MATCH(DMI_PRODUCT_VERSION, + "HP Pavilion Notebook Model GE"), DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"), }, }, @@ -1138,11 +1200,14 @@ static int __init pcibios_irq_init(void) pirq_find_router(&pirq_router); if (pirq_table->exclusive_irqs) { int i; - for (i=0; i<16; i++) + for (i = 0; i < 16; i++) if (!(pirq_table->exclusive_irqs & (1 << i))) pirq_penalty[i] += 100; } - /* If we're using the I/O APIC, avoid using the PCI IRQ routing table */ + /* + * If we're using the I/O APIC, avoid using the PCI IRQ + * routing table + */ if (io_apic_assign_pci_irqs) pirq_table = NULL; } @@ -1189,33 +1254,40 @@ static int pirq_enable_irq(struct pci_dev *dev) if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) { char *msg = ""; - pin--; /* interrupt pins are numbered starting from 1 */ + pin--; /* interrupt pins are numbered starting from 1 */ if (io_apic_assign_pci_irqs) { int irq; - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, + PCI_SLOT(dev->devfn), pin); /* - * Busses behind bridges are typically not listed in the MP-table. - * In this case we have to look up the IRQ based on the parent bus, - * parent slot, and pin number. The SMP code detects such bridged - * busses itself so we should get into this branch reliably. + * Busses behind bridges are typically not + * listed in the MP-table. In this case we have + * to look up the IRQ based on the parent bus, + * parent slot, and pin number. The SMP code + * detects such bridged busses itself so we + * should get into this branch reliably. */ temp_dev = dev; - while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; + while (irq < 0 && dev->bus->parent) { + /* go back to the bridge */ + struct pci_dev *bridge = dev->bus->self; pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin); if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); + printk(KERN_WARNING + "PCI: using PPB %s[%c] to get irq %d\n", + pci_name(bridge), + 'A' + pin, irq); dev = bridge; } dev = temp_dev; if (irq >= 0) { - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", + printk(KERN_INFO + "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", pci_name(dev), 'A' + pin, irq); dev->irq = irq; return 0; @@ -1226,12 +1298,17 @@ static int pirq_enable_irq(struct pci_dev *dev) else msg = " Please try using pci=biosirq."; - /* With IDE legacy devices the IRQ lookup failure is not a problem.. */ - if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && !(dev->class & 0x5)) + /* + * With IDE legacy devices the IRQ lookup failure is not + * a problem.. + */ + if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && + !(dev->class & 0x5)) return 0; - printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", - 'A' + pin, pci_name(dev), msg); + printk(KERN_WARNING + "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", + 'A' + pin, pci_name(dev), msg); } return 0; } -- cgit v1.2.3 From bb71ad880204b79d60331d3384103976e086cb9f Mon Sep 17 00:00:00 2001 From: Gary Hade Date: Mon, 12 May 2008 13:57:46 -0700 Subject: PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade Signed-off-by: Jesse Barnes --- Documentation/kernel-parameters.txt | 3 +++ arch/x86/pci/common.c | 22 ++++++++++++++++++++++ arch/x86/pci/pci.h | 1 + 3 files changed, 26 insertions(+) (limited to 'arch') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e07c432c731f..9cf7b34f2db0 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1496,6 +1496,9 @@ and is between 256 and 4096 characters. It is defined in the file Use with caution as certain devices share address decoders between ROMs and other resources. + norom [X86-32,X86_64] Do not assign address space to + expansion ROMs that do not already have + BIOS assigned address ranges. irqmask=0xMMMM [X86-32] Set a bit mask of IRQs allowed to be assigned automatically to PCI devices. You can make the kernel exclude IRQs of your ISA cards diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 6e64aaf00d1d..3a5261bdff5d 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -121,6 +121,21 @@ void __init dmi_check_skip_isa_align(void) dmi_check_system(can_skip_pciprobe_dmi_table); } +static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) +{ + struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; + + if (pci_probe & PCI_NOASSIGN_ROMS) { + if (rom_r->parent) + return; + if (rom_r->start) { + /* we deal with BIOS assigned ROM later */ + return; + } + rom_r->start = rom_r->end = rom_r->flags = 0; + } +} + /* * Called after each bus is probed, but before its children * are examined. @@ -128,7 +143,11 @@ void __init dmi_check_skip_isa_align(void) void __devinit pcibios_fixup_bus(struct pci_bus *b) { + struct pci_dev *dev; + pci_read_bridge_bases(b); + list_for_each_entry(dev, &b->devices, bus_list) + pcibios_fixup_device_resources(dev); } /* @@ -483,6 +502,9 @@ char * __devinit pcibios_setup(char *str) else if (!strcmp(str, "rom")) { pci_probe |= PCI_ASSIGN_ROMS; return NULL; + } else if (!strcmp(str, "norom")) { + pci_probe |= PCI_NOASSIGN_ROMS; + return NULL; } else if (!strcmp(str, "assign-busses")) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; return NULL; diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h index 720c4c554534..291dafec07b7 100644 --- a/arch/x86/pci/pci.h +++ b/arch/x86/pci/pci.h @@ -27,6 +27,7 @@ #define PCI_CAN_SKIP_ISA_ALIGN 0x8000 #define PCI_USE__CRS 0x10000 #define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 +#define PCI_NOASSIGN_ROMS 0x40000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; -- cgit v1.2.3 From 1eede070a59e1cc73da51e1aaa00d9ab86572cfc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 20 May 2008 23:00:01 +0200 Subject: Introduce new top level suspend and hibernation callbacks Introduce 'struct pm_ops' and 'struct pm_ext_ops' ('ext' meaning 'extended') representing suspend and hibernation operations for bus types, device classes, device types and device drivers. Modify the PM core to use 'struct pm_ops' and 'struct pm_ext_ops' objects, if defined, instead of the ->suspend(), ->resume(), ->suspend_late(), and ->resume_early() callbacks (the old callbacks will be considered as legacy and gradually phased out). The main purpose of doing this is to separate suspend (aka S2RAM and standby) callbacks from hibernation callbacks in such a way that the new callbacks won't take arguments and the semantics of each of them will be clearly specified. This has been requested for multiple times by many people, including Linus himself, and the reason is that within the current scheme if ->resume() is called, for example, it's difficult to say why it's been called (ie. is it a resume from RAM or from hibernation or a suspend/hibernation failure etc.?). The second purpose is to make the suspend/hibernation callbacks more flexible so that device drivers can handle more than they can within the current scheme. For example, some drivers may need to prevent new children of the device from being registered before their ->suspend() callbacks are executed or they may want to carry out some operations requiring the availability of some other devices, not directly bound via the parent-child relationship, in order to prepare for the execution of ->suspend(), etc. Ultimately, we'd like to stop using the freezing of tasks for suspend and therefore the drivers' suspend/hibernation code will have to take care of the handling of the user space during suspend/hibernation. That, in turn, would be difficult within the current scheme, without the new ->prepare() and ->complete() callbacks. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Jesse Barnes --- arch/x86/kernel/apm_32.c | 8 +- drivers/base/power/main.c | 675 +++++++++++++++++++++++++++++++++++---------- drivers/base/power/power.h | 2 +- drivers/base/power/trace.c | 4 +- include/linux/device.h | 9 + include/linux/pm.h | 314 +++++++++++++++++++-- kernel/power/disk.c | 22 +- kernel/power/main.c | 6 +- 8 files changed, 845 insertions(+), 195 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index bf9290e29013..c1735f61a2c0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1211,9 +1211,9 @@ static int suspend(int vetoable) if (err != APM_SUCCESS) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; - device_power_up(); + device_power_up(PMSG_RESUME); local_irq_enable(); - device_resume(); + device_resume(PMSG_RESUME); queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); for (as = user_list; as != NULL; as = as->next) { @@ -1238,7 +1238,7 @@ static void standby(void) apm_error("standby", err); local_irq_disable(); - device_power_up(); + device_power_up(PMSG_RESUME); local_irq_enable(); } @@ -1324,7 +1324,7 @@ static void check_events(void) ignore_bounce = 1; if ((event != APM_NORMAL_RESUME) || (ignore_normal_resume == 0)) { - device_resume(); + device_resume(PMSG_RESUME); queue_event(event, NULL); } ignore_normal_resume = 0; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 45cc3d9eacb8..d571204aaff7 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -12,11 +12,9 @@ * and add it to the list of power-controlled devices. sysfs entries for * controlling device power management will also be added. * - * A different set of lists than the global subsystem list are used to - * keep track of power info because we use different lists to hold - * devices based on what stage of the power management process they - * are in. The power domain dependencies may also differ from the - * ancestral dependencies that the subsystem list maintains. + * A separate list is used for keeping track of power info, because the power + * domain dependencies may differ from the ancestral dependencies that the + * subsystem list maintains. */ #include @@ -30,31 +28,40 @@ #include "power.h" /* - * The entries in the dpm_active list are in a depth first order, simply + * The entries in the dpm_list list are in a depth first order, simply * because children are guaranteed to be discovered after parents, and * are inserted at the back of the list on discovery. * - * All the other lists are kept in the same order, for consistency. - * However the lists aren't always traversed in the same order. - * Semaphores must be acquired from the top (i.e., front) down - * and released in the opposite order. Devices must be suspended - * from the bottom (i.e., end) up and resumed in the opposite order. - * That way no parent will be suspended while it still has an active - * child. - * * Since device_pm_add() may be called with a device semaphore held, * we must never try to acquire a device semaphore while holding * dpm_list_mutex. */ -LIST_HEAD(dpm_active); -static LIST_HEAD(dpm_off); -static LIST_HEAD(dpm_off_irq); +LIST_HEAD(dpm_list); static DEFINE_MUTEX(dpm_list_mtx); -/* 'true' if all devices have been suspended, protected by dpm_list_mtx */ -static bool all_sleeping; +/* + * Set once the preparation of devices for a PM transition has started, reset + * before starting to resume devices. Protected by dpm_list_mtx. + */ +static bool transition_started; + +/** + * device_pm_lock - lock the list of active devices used by the PM core + */ +void device_pm_lock(void) +{ + mutex_lock(&dpm_list_mtx); +} + +/** + * device_pm_unlock - unlock the list of active devices used by the PM core + */ +void device_pm_unlock(void) +{ + mutex_unlock(&dpm_list_mtx); +} /** * device_pm_add - add a device to the list of active devices @@ -68,17 +75,25 @@ int device_pm_add(struct device *dev) dev->bus ? dev->bus->name : "No Bus", kobject_name(&dev->kobj)); mutex_lock(&dpm_list_mtx); - if ((dev->parent && dev->parent->power.sleeping) || all_sleeping) { - if (dev->parent->power.sleeping) - dev_warn(dev, "parent %s is sleeping\n", + if (dev->parent) { + if (dev->parent->power.status >= DPM_SUSPENDING) { + dev_warn(dev, "parent %s is sleeping, will not add\n", dev->parent->bus_id); - else - dev_warn(dev, "all devices are sleeping\n"); + WARN_ON(true); + } + } else if (transition_started) { + /* + * We refuse to register parentless devices while a PM + * transition is in progress in order to avoid leaving them + * unhandled down the road + */ WARN_ON(true); } error = dpm_sysfs_add(dev); - if (!error) - list_add_tail(&dev->power.entry, &dpm_active); + if (!error) { + dev->power.status = DPM_ON; + list_add_tail(&dev->power.entry, &dpm_list); + } mutex_unlock(&dpm_list_mtx); return error; } @@ -100,73 +115,243 @@ void device_pm_remove(struct device *dev) mutex_unlock(&dpm_list_mtx); } +/** + * pm_op - execute the PM operation appropiate for given PM event + * @dev: Device. + * @ops: PM operations to choose from. + * @state: PM transition of the system being carried out. + */ +static int pm_op(struct device *dev, struct pm_ops *ops, pm_message_t state) +{ + int error = 0; + + switch (state.event) { +#ifdef CONFIG_SUSPEND + case PM_EVENT_SUSPEND: + if (ops->suspend) { + error = ops->suspend(dev); + suspend_report_result(ops->suspend, error); + } + break; + case PM_EVENT_RESUME: + if (ops->resume) { + error = ops->resume(dev); + suspend_report_result(ops->resume, error); + } + break; +#endif /* CONFIG_SUSPEND */ +#ifdef CONFIG_HIBERNATION + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + if (ops->freeze) { + error = ops->freeze(dev); + suspend_report_result(ops->freeze, error); + } + break; + case PM_EVENT_HIBERNATE: + if (ops->poweroff) { + error = ops->poweroff(dev); + suspend_report_result(ops->poweroff, error); + } + break; + case PM_EVENT_THAW: + case PM_EVENT_RECOVER: + if (ops->thaw) { + error = ops->thaw(dev); + suspend_report_result(ops->thaw, error); + } + break; + case PM_EVENT_RESTORE: + if (ops->restore) { + error = ops->restore(dev); + suspend_report_result(ops->restore, error); + } + break; +#endif /* CONFIG_HIBERNATION */ + default: + error = -EINVAL; + } + return error; +} + +/** + * pm_noirq_op - execute the PM operation appropiate for given PM event + * @dev: Device. + * @ops: PM operations to choose from. + * @state: PM transition of the system being carried out. + * + * The operation is executed with interrupts disabled by the only remaining + * functional CPU in the system. + */ +static int pm_noirq_op(struct device *dev, struct pm_ext_ops *ops, + pm_message_t state) +{ + int error = 0; + + switch (state.event) { +#ifdef CONFIG_SUSPEND + case PM_EVENT_SUSPEND: + if (ops->suspend_noirq) { + error = ops->suspend_noirq(dev); + suspend_report_result(ops->suspend_noirq, error); + } + break; + case PM_EVENT_RESUME: + if (ops->resume_noirq) { + error = ops->resume_noirq(dev); + suspend_report_result(ops->resume_noirq, error); + } + break; +#endif /* CONFIG_SUSPEND */ +#ifdef CONFIG_HIBERNATION + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + if (ops->freeze_noirq) { + error = ops->freeze_noirq(dev); + suspend_report_result(ops->freeze_noirq, error); + } + break; + case PM_EVENT_HIBERNATE: + if (ops->poweroff_noirq) { + error = ops->poweroff_noirq(dev); + suspend_report_result(ops->poweroff_noirq, error); + } + break; + case PM_EVENT_THAW: + case PM_EVENT_RECOVER: + if (ops->thaw_noirq) { + error = ops->thaw_noirq(dev); + suspend_report_result(ops->thaw_noirq, error); + } + break; + case PM_EVENT_RESTORE: + if (ops->restore_noirq) { + error = ops->restore_noirq(dev); + suspend_report_result(ops->restore_noirq, error); + } + break; +#endif /* CONFIG_HIBERNATION */ + default: + error = -EINVAL; + } + return error; +} + +static char *pm_verb(int event) +{ + switch (event) { + case PM_EVENT_SUSPEND: + return "suspend"; + case PM_EVENT_RESUME: + return "resume"; + case PM_EVENT_FREEZE: + return "freeze"; + case PM_EVENT_QUIESCE: + return "quiesce"; + case PM_EVENT_HIBERNATE: + return "hibernate"; + case PM_EVENT_THAW: + return "thaw"; + case PM_EVENT_RESTORE: + return "restore"; + case PM_EVENT_RECOVER: + return "recover"; + default: + return "(unknown PM event)"; + } +} + +static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info) +{ + dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event), + ((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ? + ", may wakeup" : ""); +} + +static void pm_dev_err(struct device *dev, pm_message_t state, char *info, + int error) +{ + printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n", + kobject_name(&dev->kobj), pm_verb(state.event), info, error); +} + /*------------------------- Resume routines -------------------------*/ /** - * resume_device_early - Power on one device (early resume). + * resume_device_noirq - Power on one device (early resume). * @dev: Device. + * @state: PM transition of the system being carried out. * * Must be called with interrupts disabled. */ -static int resume_device_early(struct device *dev) +static int resume_device_noirq(struct device *dev, pm_message_t state) { int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); - if (dev->bus && dev->bus->resume_early) { - dev_dbg(dev, "EARLY resume\n"); + if (!dev->bus) + goto End; + + if (dev->bus->pm) { + pm_dev_dbg(dev, state, "EARLY "); + error = pm_noirq_op(dev, dev->bus->pm, state); + } else if (dev->bus->resume_early) { + pm_dev_dbg(dev, state, "legacy EARLY "); error = dev->bus->resume_early(dev); } - + End: TRACE_RESUME(error); return error; } /** * dpm_power_up - Power on all regular (non-sysdev) devices. + * @state: PM transition of the system being carried out. * - * Walk the dpm_off_irq list and power each device up. This - * is used for devices that required they be powered down with - * interrupts disabled. As devices are powered on, they are moved - * to the dpm_off list. + * Execute the appropriate "noirq resume" callback for all devices marked + * as DPM_OFF_IRQ. * * Must be called with interrupts disabled and only one CPU running. */ -static void dpm_power_up(void) +static void dpm_power_up(pm_message_t state) { + struct device *dev; - while (!list_empty(&dpm_off_irq)) { - struct list_head *entry = dpm_off_irq.next; - struct device *dev = to_device(entry); + list_for_each_entry(dev, &dpm_list, power.entry) + if (dev->power.status > DPM_OFF) { + int error; - list_move_tail(entry, &dpm_off); - resume_device_early(dev); - } + dev->power.status = DPM_OFF; + error = resume_device_noirq(dev, state); + if (error) + pm_dev_err(dev, state, " early", error); + } } /** * device_power_up - Turn on all devices that need special attention. + * @state: PM transition of the system being carried out. * * Power on system devices, then devices that required we shut them down * with interrupts disabled. * * Must be called with interrupts disabled. */ -void device_power_up(void) +void device_power_up(pm_message_t state) { sysdev_resume(); - dpm_power_up(); + dpm_power_up(state); } EXPORT_SYMBOL_GPL(device_power_up); /** * resume_device - Restore state for one device. * @dev: Device. - * + * @state: PM transition of the system being carried out. */ -static int resume_device(struct device *dev) +static int resume_device(struct device *dev, pm_message_t state) { int error = 0; @@ -175,21 +360,40 @@ static int resume_device(struct device *dev) down(&dev->sem); - if (dev->bus && dev->bus->resume) { - dev_dbg(dev,"resuming\n"); - error = dev->bus->resume(dev); + if (dev->bus) { + if (dev->bus->pm) { + pm_dev_dbg(dev, state, ""); + error = pm_op(dev, &dev->bus->pm->base, state); + } else if (dev->bus->resume) { + pm_dev_dbg(dev, state, "legacy "); + error = dev->bus->resume(dev); + } + if (error) + goto End; } - if (!error && dev->type && dev->type->resume) { - dev_dbg(dev,"resuming\n"); - error = dev->type->resume(dev); + if (dev->type) { + if (dev->type->pm) { + pm_dev_dbg(dev, state, "type "); + error = pm_op(dev, dev->type->pm, state); + } else if (dev->type->resume) { + pm_dev_dbg(dev, state, "legacy type "); + error = dev->type->resume(dev); + } + if (error) + goto End; } - if (!error && dev->class && dev->class->resume) { - dev_dbg(dev,"class resume\n"); - error = dev->class->resume(dev); + if (dev->class) { + if (dev->class->pm) { + pm_dev_dbg(dev, state, "class "); + error = pm_op(dev, dev->class->pm, state); + } else if (dev->class->resume) { + pm_dev_dbg(dev, state, "legacy class "); + error = dev->class->resume(dev); + } } - + End: up(&dev->sem); TRACE_RESUME(error); @@ -198,78 +402,161 @@ static int resume_device(struct device *dev) /** * dpm_resume - Resume every device. + * @state: PM transition of the system being carried out. * - * Resume the devices that have either not gone through - * the late suspend, or that did go through it but also - * went through the early resume. + * Execute the appropriate "resume" callback for all devices the status of + * which indicates that they are inactive. + */ +static void dpm_resume(pm_message_t state) +{ + struct list_head list; + + INIT_LIST_HEAD(&list); + mutex_lock(&dpm_list_mtx); + transition_started = false; + while (!list_empty(&dpm_list)) { + struct device *dev = to_device(dpm_list.next); + + get_device(dev); + if (dev->power.status >= DPM_OFF) { + int error; + + dev->power.status = DPM_RESUMING; + mutex_unlock(&dpm_list_mtx); + + error = resume_device(dev, state); + + mutex_lock(&dpm_list_mtx); + if (error) + pm_dev_err(dev, state, "", error); + } else if (dev->power.status == DPM_SUSPENDING) { + /* Allow new children of the device to be registered */ + dev->power.status = DPM_RESUMING; + } + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &list); + put_device(dev); + } + list_splice(&list, &dpm_list); + mutex_unlock(&dpm_list_mtx); +} + +/** + * complete_device - Complete a PM transition for given device + * @dev: Device. + * @state: PM transition of the system being carried out. + */ +static void complete_device(struct device *dev, pm_message_t state) +{ + down(&dev->sem); + + if (dev->class && dev->class->pm && dev->class->pm->complete) { + pm_dev_dbg(dev, state, "completing class "); + dev->class->pm->complete(dev); + } + + if (dev->type && dev->type->pm && dev->type->pm->complete) { + pm_dev_dbg(dev, state, "completing type "); + dev->type->pm->complete(dev); + } + + if (dev->bus && dev->bus->pm && dev->bus->pm->base.complete) { + pm_dev_dbg(dev, state, "completing "); + dev->bus->pm->base.complete(dev); + } + + up(&dev->sem); +} + +/** + * dpm_complete - Complete a PM transition for all devices. + * @state: PM transition of the system being carried out. * - * Take devices from the dpm_off_list, resume them, - * and put them on the dpm_locked list. + * Execute the ->complete() callbacks for all devices that are not marked + * as DPM_ON. */ -static void dpm_resume(void) +static void dpm_complete(pm_message_t state) { + struct list_head list; + + INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); - all_sleeping = false; - while(!list_empty(&dpm_off)) { - struct list_head *entry = dpm_off.next; - struct device *dev = to_device(entry); + while (!list_empty(&dpm_list)) { + struct device *dev = to_device(dpm_list.prev); - list_move_tail(entry, &dpm_active); - dev->power.sleeping = false; - mutex_unlock(&dpm_list_mtx); - resume_device(dev); - mutex_lock(&dpm_list_mtx); + get_device(dev); + if (dev->power.status > DPM_ON) { + dev->power.status = DPM_ON; + mutex_unlock(&dpm_list_mtx); + + complete_device(dev, state); + + mutex_lock(&dpm_list_mtx); + } + if (!list_empty(&dev->power.entry)) + list_move(&dev->power.entry, &list); + put_device(dev); } + list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); } /** * device_resume - Restore state of each device in system. + * @state: PM transition of the system being carried out. * * Resume all the devices, unlock them all, and allow new * devices to be registered once again. */ -void device_resume(void) +void device_resume(pm_message_t state) { might_sleep(); - dpm_resume(); + dpm_resume(state); + dpm_complete(state); } EXPORT_SYMBOL_GPL(device_resume); /*------------------------- Suspend routines -------------------------*/ -static inline char *suspend_verb(u32 event) +/** + * resume_event - return a PM message representing the resume event + * corresponding to given sleep state. + * @sleep_state: PM message representing a sleep state. + */ +static pm_message_t resume_event(pm_message_t sleep_state) { - switch (event) { - case PM_EVENT_SUSPEND: return "suspend"; - case PM_EVENT_FREEZE: return "freeze"; - case PM_EVENT_PRETHAW: return "prethaw"; - default: return "(unknown suspend event)"; + switch (sleep_state.event) { + case PM_EVENT_SUSPEND: + return PMSG_RESUME; + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + return PMSG_RECOVER; + case PM_EVENT_HIBERNATE: + return PMSG_RESTORE; } -} - -static void -suspend_device_dbg(struct device *dev, pm_message_t state, char *info) -{ - dev_dbg(dev, "%s%s%s\n", info, suspend_verb(state.event), - ((state.event == PM_EVENT_SUSPEND) && device_may_wakeup(dev)) ? - ", may wakeup" : ""); + return PMSG_ON; } /** - * suspend_device_late - Shut down one device (late suspend). + * suspend_device_noirq - Shut down one device (late suspend). * @dev: Device. - * @state: Power state device is entering. + * @state: PM transition of the system being carried out. * * This is called with interrupts off and only a single CPU running. */ -static int suspend_device_late(struct device *dev, pm_message_t state) +static int suspend_device_noirq(struct device *dev, pm_message_t state) { int error = 0; - if (dev->bus && dev->bus->suspend_late) { - suspend_device_dbg(dev, state, "LATE "); + if (!dev->bus) + return 0; + + if (dev->bus->pm) { + pm_dev_dbg(dev, state, "LATE "); + error = pm_noirq_op(dev, dev->bus->pm, state); + } else if (dev->bus->suspend_late) { + pm_dev_dbg(dev, state, "legacy LATE "); error = dev->bus->suspend_late(dev, state); suspend_report_result(dev->bus->suspend_late, error); } @@ -278,37 +565,30 @@ static int suspend_device_late(struct device *dev, pm_message_t state) /** * device_power_down - Shut down special devices. - * @state: Power state to enter. + * @state: PM transition of the system being carried out. * - * Power down devices that require interrupts to be disabled - * and move them from the dpm_off list to the dpm_off_irq list. + * Power down devices that require interrupts to be disabled. * Then power down system devices. * * Must be called with interrupts disabled and only one CPU running. */ int device_power_down(pm_message_t state) { + struct device *dev; int error = 0; - while (!list_empty(&dpm_off)) { - struct list_head *entry = dpm_off.prev; - struct device *dev = to_device(entry); - - error = suspend_device_late(dev, state); + list_for_each_entry_reverse(dev, &dpm_list, power.entry) { + error = suspend_device_noirq(dev, state); if (error) { - printk(KERN_ERR "Could not power down device %s: " - "error %d\n", - kobject_name(&dev->kobj), error); + pm_dev_err(dev, state, " late", error); break; } - if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_off_irq); + dev->power.status = DPM_OFF_IRQ; } - if (!error) error = sysdev_suspend(state); if (error) - dpm_power_up(); + dpm_power_up(resume_event(state)); return error; } EXPORT_SYMBOL_GPL(device_power_down); @@ -316,7 +596,7 @@ EXPORT_SYMBOL_GPL(device_power_down); /** * suspend_device - Save state of one device. * @dev: Device. - * @state: Power state device is entering. + * @state: PM transition of the system being carried out. */ static int suspend_device(struct device *dev, pm_message_t state) { @@ -324,24 +604,43 @@ static int suspend_device(struct device *dev, pm_message_t state) down(&dev->sem); - if (dev->class && dev->class->suspend) { - suspend_device_dbg(dev, state, "class "); - error = dev->class->suspend(dev, state); - suspend_report_result(dev->class->suspend, error); + if (dev->class) { + if (dev->class->pm) { + pm_dev_dbg(dev, state, "class "); + error = pm_op(dev, dev->class->pm, state); + } else if (dev->class->suspend) { + pm_dev_dbg(dev, state, "legacy class "); + error = dev->class->suspend(dev, state); + suspend_report_result(dev->class->suspend, error); + } + if (error) + goto End; } - if (!error && dev->type && dev->type->suspend) { - suspend_device_dbg(dev, state, "type "); - error = dev->type->suspend(dev, state); - suspend_report_result(dev->type->suspend, error); + if (dev->type) { + if (dev->type->pm) { + pm_dev_dbg(dev, state, "type "); + error = pm_op(dev, dev->type->pm, state); + } else if (dev->type->suspend) { + pm_dev_dbg(dev, state, "legacy type "); + error = dev->type->suspend(dev, state); + suspend_report_result(dev->type->suspend, error); + } + if (error) + goto End; } - if (!error && dev->bus && dev->bus->suspend) { - suspend_device_dbg(dev, state, ""); - error = dev->bus->suspend(dev, state); - suspend_report_result(dev->bus->suspend, error); + if (dev->bus) { + if (dev->bus->pm) { + pm_dev_dbg(dev, state, ""); + error = pm_op(dev, &dev->bus->pm->base, state); + } else if (dev->bus->suspend) { + pm_dev_dbg(dev, state, "legacy "); + error = dev->bus->suspend(dev, state); + suspend_report_result(dev->bus->suspend, error); + } } - + End: up(&dev->sem); return error; @@ -349,67 +648,141 @@ static int suspend_device(struct device *dev, pm_message_t state) /** * dpm_suspend - Suspend every device. - * @state: Power state to put each device in. + * @state: PM transition of the system being carried out. * - * Walk the dpm_locked list. Suspend each device and move it - * to the dpm_off list. - * - * (For historical reasons, if it returns -EAGAIN, that used to mean - * that the device would be called again with interrupts disabled. - * These days, we use the "suspend_late()" callback for that, so we - * print a warning and consider it an error). + * Execute the appropriate "suspend" callbacks for all devices. */ static int dpm_suspend(pm_message_t state) { + struct list_head list; int error = 0; + INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); - while (!list_empty(&dpm_active)) { - struct list_head *entry = dpm_active.prev; - struct device *dev = to_device(entry); - - WARN_ON(dev->parent && dev->parent->power.sleeping); + while (!list_empty(&dpm_list)) { + struct device *dev = to_device(dpm_list.prev); - dev->power.sleeping = true; + get_device(dev); mutex_unlock(&dpm_list_mtx); + error = suspend_device(dev, state); + mutex_lock(&dpm_list_mtx); if (error) { - printk(KERN_ERR "Could not suspend device %s: " - "error %d%s\n", - kobject_name(&dev->kobj), - error, - (error == -EAGAIN ? - " (please convert to suspend_late)" : - "")); - dev->power.sleeping = false; + pm_dev_err(dev, state, "", error); + put_device(dev); break; } + dev->power.status = DPM_OFF; if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_off); + list_move(&dev->power.entry, &list); + put_device(dev); } - if (!error) - all_sleeping = true; + list_splice(&list, dpm_list.prev); mutex_unlock(&dpm_list_mtx); + return error; +} + +/** + * prepare_device - Execute the ->prepare() callback(s) for given device. + * @dev: Device. + * @state: PM transition of the system being carried out. + */ +static int prepare_device(struct device *dev, pm_message_t state) +{ + int error = 0; + + down(&dev->sem); + + if (dev->bus && dev->bus->pm && dev->bus->pm->base.prepare) { + pm_dev_dbg(dev, state, "preparing "); + error = dev->bus->pm->base.prepare(dev); + suspend_report_result(dev->bus->pm->base.prepare, error); + if (error) + goto End; + } + + if (dev->type && dev->type->pm && dev->type->pm->prepare) { + pm_dev_dbg(dev, state, "preparing type "); + error = dev->type->pm->prepare(dev); + suspend_report_result(dev->type->pm->prepare, error); + if (error) + goto End; + } + + if (dev->class && dev->class->pm && dev->class->pm->prepare) { + pm_dev_dbg(dev, state, "preparing class "); + error = dev->class->pm->prepare(dev); + suspend_report_result(dev->class->pm->prepare, error); + } + End: + up(&dev->sem); + + return error; +} +/** + * dpm_prepare - Prepare all devices for a PM transition. + * @state: PM transition of the system being carried out. + * + * Execute the ->prepare() callback for all devices. + */ +static int dpm_prepare(pm_message_t state) +{ + struct list_head list; + int error = 0; + + INIT_LIST_HEAD(&list); + mutex_lock(&dpm_list_mtx); + transition_started = true; + while (!list_empty(&dpm_list)) { + struct device *dev = to_device(dpm_list.next); + + get_device(dev); + dev->power.status = DPM_PREPARING; + mutex_unlock(&dpm_list_mtx); + + error = prepare_device(dev, state); + + mutex_lock(&dpm_list_mtx); + if (error) { + dev->power.status = DPM_ON; + if (error == -EAGAIN) { + put_device(dev); + continue; + } + printk(KERN_ERR "PM: Failed to prepare device %s " + "for power transition: error %d\n", + kobject_name(&dev->kobj), error); + put_device(dev); + break; + } + dev->power.status = DPM_SUSPENDING; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &list); + put_device(dev); + } + list_splice(&list, &dpm_list); + mutex_unlock(&dpm_list_mtx); return error; } /** * device_suspend - Save state and stop all devices in system. - * @state: new power management state + * @state: PM transition of the system being carried out. * - * Prevent new devices from being registered, then lock all devices - * and suspend them. + * Prepare and suspend all devices. */ int device_suspend(pm_message_t state) { int error; might_sleep(); - error = dpm_suspend(state); + error = dpm_prepare(state); + if (!error) + error = dpm_suspend(state); if (error) - device_resume(); + device_resume(resume_event(state)); return error; } EXPORT_SYMBOL_GPL(device_suspend); diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index a6894f2a4b99..a3252c0e2887 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -4,7 +4,7 @@ * main.c */ -extern struct list_head dpm_active; /* The active device list */ +extern struct list_head dpm_list; /* The active device list */ static inline struct device *to_device(struct list_head *entry) { diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 2b4b392dcbc1..8c1e656b5f8b 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -188,9 +188,9 @@ static int show_file_hash(unsigned int value) static int show_dev_hash(unsigned int value) { int match = 0; - struct list_head * entry = dpm_active.prev; + struct list_head *entry = dpm_list.prev; - while (entry != &dpm_active) { + while (entry != &dpm_list) { struct device * dev = to_device(entry); unsigned int hash = hash_string(DEVSEED, dev->bus_id, DEVHASH); if (hash == value) { diff --git a/include/linux/device.h b/include/linux/device.h index 6a2d04c011bc..f71a78d123ae 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -68,6 +68,8 @@ struct bus_type { int (*resume_early)(struct device *dev); int (*resume)(struct device *dev); + struct pm_ext_ops *pm; + struct bus_type_private *p; }; @@ -131,6 +133,8 @@ struct device_driver { int (*resume) (struct device *dev); struct attribute_group **groups; + struct pm_ops *pm; + struct driver_private *p; }; @@ -197,6 +201,8 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + + struct pm_ops *pm; }; extern int __must_check class_register(struct class *class); @@ -248,8 +254,11 @@ struct device_type { struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); void (*release)(struct device *dev); + int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + + struct pm_ops *pm; }; /* interface for exporting device attributes */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 39a7ee859b67..4ad9de94449a 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -112,7 +112,9 @@ typedef struct pm_message { int event; } pm_message_t; -/* +/** + * struct pm_ops - device PM callbacks + * * Several driver power state transitions are externally visible, affecting * the state of pending I/O queues and (for drivers that touch hardware) * interrupts, wakeups, DMA, and other hardware state. There may also be @@ -120,6 +122,284 @@ typedef struct pm_message { * to the rest of the driver stack (such as a driver that's ON gating off * clocks which are not in active use). * + * The externally visible transitions are handled with the help of the following + * callbacks included in this structure: + * + * @prepare: Prepare the device for the upcoming transition, but do NOT change + * its hardware state. Prevent new children of the device from being + * registered after @prepare() returns (the driver's subsystem and + * generally the rest of the kernel is supposed to prevent new calls to the + * probe method from being made too once @prepare() has succeeded). If + * @prepare() detects a situation it cannot handle (e.g. registration of a + * child already in progress), it may return -EAGAIN, so that the PM core + * can execute it once again (e.g. after the new child has been registered) + * to recover from the race condition. This method is executed for all + * kinds of suspend transitions and is followed by one of the suspend + * callbacks: @suspend(), @freeze(), or @poweroff(). + * The PM core executes @prepare() for all devices before starting to + * execute suspend callbacks for any of them, so drivers may assume all of + * the other devices to be present and functional while @prepare() is being + * executed. In particular, it is safe to make GFP_KERNEL memory + * allocations from within @prepare(). However, drivers may NOT assume + * anything about the availability of the user space at that time and it + * is not correct to request firmware from within @prepare() (it's too + * late to do that). [To work around this limitation, drivers may + * register suspend and hibernation notifiers that are executed before the + * freezing of tasks.] + * + * @complete: Undo the changes made by @prepare(). This method is executed for + * all kinds of resume transitions, following one of the resume callbacks: + * @resume(), @thaw(), @restore(). Also called if the state transition + * fails before the driver's suspend callback (@suspend(), @freeze(), + * @poweroff()) can be executed (e.g. if the suspend callback fails for one + * of the other devices that the PM core has unsuccessfully attempted to + * suspend earlier). + * The PM core executes @complete() after it has executed the appropriate + * resume callback for all devices. + * + * @suspend: Executed before putting the system into a sleep state in which the + * contents of main memory are preserved. Quiesce the device, put it into + * a low power state appropriate for the upcoming system state (such as + * PCI_D3hot), and enable wakeup events as appropriate. + * + * @resume: Executed after waking the system up from a sleep state in which the + * contents of main memory were preserved. Put the device into the + * appropriate state, according to the information saved in memory by the + * preceding @suspend(). The driver starts working again, responding to + * hardware events and software requests. The hardware may have gone + * through a power-off reset, or it may have maintained state from the + * previous suspend() which the driver may rely on while resuming. On most + * platforms, there are no restrictions on availability of resources like + * clocks during @resume(). + * + * @freeze: Hibernation-specific, executed before creating a hibernation image. + * Quiesce operations so that a consistent image can be created, but do NOT + * otherwise put the device into a low power device state and do NOT emit + * system wakeup events. Save in main memory the device settings to be + * used by @restore() during the subsequent resume from hibernation or by + * the subsequent @thaw(), if the creation of the image or the restoration + * of main memory contents from it fails. + * + * @thaw: Hibernation-specific, executed after creating a hibernation image OR + * if the creation of the image fails. Also executed after a failing + * attempt to restore the contents of main memory from such an image. + * Undo the changes made by the preceding @freeze(), so the device can be + * operated in the same way as immediately before the call to @freeze(). + * + * @poweroff: Hibernation-specific, executed after saving a hibernation image. + * Quiesce the device, put it into a low power state appropriate for the + * upcoming system state (such as PCI_D3hot), and enable wakeup events as + * appropriate. + * + * @restore: Hibernation-specific, executed after restoring the contents of main + * memory from a hibernation image. Driver starts working again, + * responding to hardware events and software requests. Drivers may NOT + * make ANY assumptions about the hardware state right prior to @restore(). + * On most platforms, there are no restrictions on availability of + * resources like clocks during @restore(). + * + * All of the above callbacks, except for @complete(), return error codes. + * However, the error codes returned by the resume operations, @resume(), + * @thaw(), and @restore(), do not cause the PM core to abort the resume + * transition during which they are returned. The error codes returned in + * that cases are only printed by the PM core to the system logs for debugging + * purposes. Still, it is recommended that drivers only return error codes + * from their resume methods in case of an unrecoverable failure (i.e. when the + * device being handled refuses to resume and becomes unusable) to allow us to + * modify the PM core in the future, so that it can avoid attempting to handle + * devices that failed to resume and their children. + * + * It is allowed to unregister devices while the above callbacks are being + * executed. However, it is not allowed to unregister a device from within any + * of its own callbacks. + */ + +struct pm_ops { + int (*prepare)(struct device *dev); + void (*complete)(struct device *dev); + int (*suspend)(struct device *dev); + int (*resume)(struct device *dev); + int (*freeze)(struct device *dev); + int (*thaw)(struct device *dev); + int (*poweroff)(struct device *dev); + int (*restore)(struct device *dev); +}; + +/** + * struct pm_ext_ops - extended device PM callbacks + * + * Some devices require certain operations related to suspend and hibernation + * to be carried out with interrupts disabled. Thus, 'struct pm_ext_ops' below + * is defined, adding callbacks to be executed with interrupts disabled to + * 'struct pm_ops'. + * + * The following callbacks included in 'struct pm_ext_ops' are executed with + * the nonboot CPUs switched off and with interrupts disabled on the only + * functional CPU. They also are executed with the PM core list of devices + * locked, so they must NOT unregister any devices. + * + * @suspend_noirq: Complete the operations of ->suspend() by carrying out any + * actions required for suspending the device that need interrupts to be + * disabled + * + * @resume_noirq: Prepare for the execution of ->resume() by carrying out any + * actions required for resuming the device that need interrupts to be + * disabled + * + * @freeze_noirq: Complete the operations of ->freeze() by carrying out any + * actions required for freezing the device that need interrupts to be + * disabled + * + * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any + * actions required for thawing the device that need interrupts to be + * disabled + * + * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any + * actions required for handling the device that need interrupts to be + * disabled + * + * @restore_noirq: Prepare for the execution of ->restore() by carrying out any + * actions required for restoring the operations of the device that need + * interrupts to be disabled + * + * All of the above callbacks return error codes, but the error codes returned + * by the resume operations, @resume_noirq(), @thaw_noirq(), and + * @restore_noirq(), do not cause the PM core to abort the resume transition + * during which they are returned. The error codes returned in that cases are + * only printed by the PM core to the system logs for debugging purposes. + * Still, as stated above, it is recommended that drivers only return error + * codes from their resume methods if the device being handled fails to resume + * and is not usable any more. + */ + +struct pm_ext_ops { + struct pm_ops base; + int (*suspend_noirq)(struct device *dev); + int (*resume_noirq)(struct device *dev); + int (*freeze_noirq)(struct device *dev); + int (*thaw_noirq)(struct device *dev); + int (*poweroff_noirq)(struct device *dev); + int (*restore_noirq)(struct device *dev); +}; + +/** + * PM_EVENT_ messages + * + * The following PM_EVENT_ messages are defined for the internal use of the PM + * core, in order to provide a mechanism allowing the high level suspend and + * hibernation code to convey the necessary information to the device PM core + * code: + * + * ON No transition. + * + * FREEZE System is going to hibernate, call ->prepare() and ->freeze() + * for all devices. + * + * SUSPEND System is going to suspend, call ->prepare() and ->suspend() + * for all devices. + * + * HIBERNATE Hibernation image has been saved, call ->prepare() and + * ->poweroff() for all devices. + * + * QUIESCE Contents of main memory are going to be restored from a (loaded) + * hibernation image, call ->prepare() and ->freeze() for all + * devices. + * + * RESUME System is resuming, call ->resume() and ->complete() for all + * devices. + * + * THAW Hibernation image has been created, call ->thaw() and + * ->complete() for all devices. + * + * RESTORE Contents of main memory have been restored from a hibernation + * image, call ->restore() and ->complete() for all devices. + * + * RECOVER Creation of a hibernation image or restoration of the main + * memory contents from a hibernation image has failed, call + * ->thaw() and ->complete() for all devices. + */ + +#define PM_EVENT_ON 0x0000 +#define PM_EVENT_FREEZE 0x0001 +#define PM_EVENT_SUSPEND 0x0002 +#define PM_EVENT_HIBERNATE 0x0004 +#define PM_EVENT_QUIESCE 0x0008 +#define PM_EVENT_RESUME 0x0010 +#define PM_EVENT_THAW 0x0020 +#define PM_EVENT_RESTORE 0x0040 +#define PM_EVENT_RECOVER 0x0080 + +#define PM_EVENT_SLEEP (PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE) + +#define PMSG_FREEZE ((struct pm_message){ .event = PM_EVENT_FREEZE, }) +#define PMSG_QUIESCE ((struct pm_message){ .event = PM_EVENT_QUIESCE, }) +#define PMSG_SUSPEND ((struct pm_message){ .event = PM_EVENT_SUSPEND, }) +#define PMSG_HIBERNATE ((struct pm_message){ .event = PM_EVENT_HIBERNATE, }) +#define PMSG_RESUME ((struct pm_message){ .event = PM_EVENT_RESUME, }) +#define PMSG_THAW ((struct pm_message){ .event = PM_EVENT_THAW, }) +#define PMSG_RESTORE ((struct pm_message){ .event = PM_EVENT_RESTORE, }) +#define PMSG_RECOVER ((struct pm_message){ .event = PM_EVENT_RECOVER, }) +#define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) + +/** + * Device power management states + * + * These state labels are used internally by the PM core to indicate the current + * status of a device with respect to the PM core operations. + * + * DPM_ON Device is regarded as operational. Set this way + * initially and when ->complete() is about to be called. + * Also set when ->prepare() fails. + * + * DPM_PREPARING Device is going to be prepared for a PM transition. Set + * when ->prepare() is about to be called. + * + * DPM_RESUMING Device is going to be resumed. Set when ->resume(), + * ->thaw(), or ->restore() is about to be called. + * + * DPM_SUSPENDING Device has been prepared for a power transition. Set + * when ->prepare() has just succeeded. + * + * DPM_OFF Device is regarded as inactive. Set immediately after + * ->suspend(), ->freeze(), or ->poweroff() has succeeded. + * Also set when ->resume()_noirq, ->thaw_noirq(), or + * ->restore_noirq() is about to be called. + * + * DPM_OFF_IRQ Device is in a "deep sleep". Set immediately after + * ->suspend_noirq(), ->freeze_noirq(), or + * ->poweroff_noirq() has just succeeded. + */ + +enum dpm_state { + DPM_INVALID, + DPM_ON, + DPM_PREPARING, + DPM_RESUMING, + DPM_SUSPENDING, + DPM_OFF, + DPM_OFF_IRQ, +}; + +struct dev_pm_info { + pm_message_t power_state; + unsigned can_wakeup:1; + unsigned should_wakeup:1; + enum dpm_state status; /* Owned by the PM core */ +#ifdef CONFIG_PM_SLEEP + struct list_head entry; +#endif +}; + +/* + * The PM_EVENT_ messages are also used by drivers implementing the legacy + * suspend framework, based on the ->suspend() and ->resume() callbacks common + * for suspend and hibernation transitions, according to the rules below. + */ + +/* Necessary, because several drivers use PM_EVENT_PRETHAW */ +#define PM_EVENT_PRETHAW PM_EVENT_QUIESCE + +/* * One transition is triggered by resume(), after a suspend() call; the * message is implicit: * @@ -164,35 +444,13 @@ typedef struct pm_message { * or from system low-power states such as standby or suspend-to-RAM. */ -#define PM_EVENT_ON 0 -#define PM_EVENT_FREEZE 1 -#define PM_EVENT_SUSPEND 2 -#define PM_EVENT_HIBERNATE 4 -#define PM_EVENT_PRETHAW 8 - -#define PM_EVENT_SLEEP (PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE) - -#define PMSG_FREEZE ((struct pm_message){ .event = PM_EVENT_FREEZE, }) -#define PMSG_PRETHAW ((struct pm_message){ .event = PM_EVENT_PRETHAW, }) -#define PMSG_SUSPEND ((struct pm_message){ .event = PM_EVENT_SUSPEND, }) -#define PMSG_HIBERNATE ((struct pm_message){ .event = PM_EVENT_HIBERNATE, }) -#define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) - -struct dev_pm_info { - pm_message_t power_state; - unsigned can_wakeup:1; - unsigned should_wakeup:1; - bool sleeping:1; /* Owned by the PM core */ -#ifdef CONFIG_PM_SLEEP - struct list_head entry; -#endif -}; +#ifdef CONFIG_PM_SLEEP +extern void device_pm_lock(void); +extern void device_power_up(pm_message_t state); +extern void device_resume(pm_message_t state); +extern void device_pm_unlock(void); extern int device_power_down(pm_message_t state); -extern void device_power_up(void); -extern void device_resume(void); - -#ifdef CONFIG_PM_SLEEP extern int device_suspend(pm_message_t state); extern int device_prepare_suspend(pm_message_t state); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 14a656cdc652..d416be0efa8a 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -193,6 +193,7 @@ static int create_image(int platform_mode) if (error) return error; + device_pm_lock(); local_irq_disable(); /* At this point, device_suspend() has been called, but *not* * device_power_down(). We *must* call device_power_down() now. @@ -224,9 +225,11 @@ static int create_image(int platform_mode) /* NOTE: device_power_up() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ - device_power_up(); + device_power_up(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); Enable_irqs: local_irq_enable(); + device_pm_unlock(); return error; } @@ -280,7 +283,8 @@ int hibernation_snapshot(int platform_mode) Finish: platform_finish(platform_mode); Resume_devices: - device_resume(); + device_resume(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); Resume_console: resume_console(); Close: @@ -300,8 +304,9 @@ static int resume_target_kernel(void) { int error; + device_pm_lock(); local_irq_disable(); - error = device_power_down(PMSG_PRETHAW); + error = device_power_down(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); @@ -329,9 +334,10 @@ static int resume_target_kernel(void) swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); - device_power_up(); + device_power_up(PMSG_RECOVER); Enable_irqs: local_irq_enable(); + device_pm_unlock(); return error; } @@ -350,7 +356,7 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); - error = device_suspend(PMSG_PRETHAW); + error = device_suspend(PMSG_QUIESCE); if (error) goto Finish; @@ -362,7 +368,7 @@ int hibernation_restore(int platform_mode) enable_nonboot_cpus(); } platform_restore_cleanup(platform_mode); - device_resume(); + device_resume(PMSG_RECOVER); Finish: resume_console(); pm_restore_console(); @@ -403,6 +409,7 @@ int hibernation_platform_enter(void) if (error) goto Finish; + device_pm_lock(); local_irq_disable(); error = device_power_down(PMSG_HIBERNATE); if (!error) { @@ -411,6 +418,7 @@ int hibernation_platform_enter(void) while (1); } local_irq_enable(); + device_pm_unlock(); /* * We don't need to reenable the nonboot CPUs or resume consoles, since @@ -419,7 +427,7 @@ int hibernation_platform_enter(void) Finish: hibernation_ops->finish(); Resume_devices: - device_resume(); + device_resume(PMSG_RESTORE); Resume_console: resume_console(); Close: diff --git a/kernel/power/main.c b/kernel/power/main.c index 6a6d5eb3524e..d023b6b584e5 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -228,6 +228,7 @@ static int suspend_enter(suspend_state_t state) { int error = 0; + device_pm_lock(); arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); @@ -239,10 +240,11 @@ static int suspend_enter(suspend_state_t state) if (!suspend_test(TEST_CORE)) error = suspend_ops->enter(state); - device_power_up(); + device_power_up(PMSG_RESUME); Done: arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); + device_pm_unlock(); return error; } @@ -291,7 +293,7 @@ int suspend_devices_and_enter(suspend_state_t state) if (suspend_ops->finish) suspend_ops->finish(); Resume_devices: - device_resume(); + device_resume(PMSG_RESUME); Resume_console: resume_console(); Close: -- cgit v1.2.3 From e7891c733f9b26c851edde50cf886a30bd133dbd Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 22 May 2008 14:35:21 -0700 Subject: PCI/x86: write_pci_config_byte fix offset also add write_pci_config_16 Signed-off-by: Yinghai Lu Signed-off-by: Jesse Barnes --- arch/x86/pci/early.c | 9 ++++++++- include/asm-x86/pci-direct.h | 1 + 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index 42df4b6606df..8e2821e8dac5 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -49,7 +49,14 @@ void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val) { PDprintk("%x writing to %x: %x\n", slot, offset, val); outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); - outb(val, 0xcfc); + outb(val, 0xcfc + (offset&3)); +} + +void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val) +{ + PDprintk("%x writing to %x: %x\n", slot, offset, val); + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + outw(val, 0xcfc + (offset&2)); } int early_pci_allowed(void) diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h index 5b21485be573..7bd40b4de751 100644 --- a/include/asm-x86/pci-direct.h +++ b/include/asm-x86/pci-direct.h @@ -11,6 +11,7 @@ extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset); extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset); extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val); extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); +extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); extern int early_pci_allowed(void); -- cgit v1.2.3 From e3f2baebf4209b5927e23fa65d5977d31db936b3 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 22 May 2008 14:35:11 -0700 Subject: PCI/x86: early dump pci conf space v2 Allows us to dump PCI space before any kernel changes have been made. Signed-off-by: Yinghai Lu Signed-off-by: Jesse Barnes --- arch/x86/kernel/setup_64.c | 5 +++++ arch/x86/pci/common.c | 4 ++++ arch/x86/pci/early.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ include/asm-x86/pci-direct.h | 3 +++ 4 files changed, 63 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 6dff1286ad8a..524b6850b2c0 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -361,6 +361,11 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); +#ifdef CONFIG_PCI + if (pci_early_dump_regs) + early_dump_pci_devices(); +#endif + #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT if (init_ohci1394_dma_early) init_ohci1394_dma_on_all_controllers(); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 3a5261bdff5d..d19fd07bafd6 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -20,6 +20,7 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; +unsigned int pci_early_dump_regs; static int pci_bf_sort; int pci_routeirq; int pcibios_last_bus = -1; @@ -511,6 +512,9 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "use_crs")) { pci_probe |= PCI_USE__CRS; return NULL; + } else if (!strcmp(str, "earlydump")) { + pci_early_dump_regs = 1; + return NULL; } else if (!strcmp(str, "routeirq")) { pci_routeirq = 1; return NULL; diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index 8e2821e8dac5..858dbe3399f9 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -64,3 +64,54 @@ int early_pci_allowed(void) return (pci_probe & (PCI_PROBE_CONF1|PCI_PROBE_NOEARLY)) == PCI_PROBE_CONF1; } + +void early_dump_pci_device(u8 bus, u8 slot, u8 func) +{ + int i; + int j; + u32 val; + + printk("PCI: %02x:%02x:%02x", bus, slot, func); + + for (i = 0; i < 256; i += 4) { + if (!(i & 0x0f)) + printk("\n%04x:",i); + + val = read_pci_config(bus, slot, func, i); + for (j = 0; j < 4; j++) { + printk(" %02x", val & 0xff); + val >>= 8; + } + } + printk("\n"); +} + +void early_dump_pci_devices(void) +{ + unsigned bus, slot, func; + + if (!early_pci_allowed()) + return; + + for (bus = 0; bus < 256; bus++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class; + u8 type; + class = read_pci_config(bus, slot, func, + PCI_CLASS_REVISION); + if (class == 0xffffffff) + break; + + early_dump_pci_device(bus, slot, func); + + /* No multi-function device? */ + type = read_pci_config_byte(bus, slot, func, + PCI_HEADER_TYPE); + if (!(type & 0x80)) + break; + } + } + } +} + diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h index 7bd40b4de751..80c775d9fe20 100644 --- a/include/asm-x86/pci-direct.h +++ b/include/asm-x86/pci-direct.h @@ -15,4 +15,7 @@ extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); extern int early_pci_allowed(void); +extern unsigned int pci_early_dump_regs; +extern void early_dump_pci_device(u8 bus, u8 slot, u8 func); +extern void early_dump_pci_devices(void); #endif -- cgit v1.2.3 From d8f3de0d2412bb91639cfefc5b3c79dbf3812212 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 12 Jun 2008 23:24:06 +0200 Subject: Suspend-related patches for 2.6.27 ACPI PM: Add possibility to change suspend sequence There are some systems out there that don't work correctly with our current suspend/hibernation code ordering. Provide a workaround for these systems allowing them to pass 'acpi_sleep=old_ordering' in the kernel command line so that it will use the pre-ACPI 2.0 ("old") suspend code ordering. Unfortunately, this requires us to add a platform hook to the resuming of devices for recovering the platform in case one of the device drivers' .suspend() routines returns error code. Namely, ACPI 1.0 specifies that _PTS should be called before suspending devices, but _WAK still should be called before resuming them in order to undo the changes made by _PTS. However, if there is an error during suspending devices, they are automatically resumed without returning control to the PM core, so the _WAK has to be called from within device_resume() in that cases. The patch also reorders and refactors the ACPI suspend/hibernation code to avoid duplication as far as reasonably possible. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Jesse Barnes --- Documentation/kernel-parameters.txt | 6 +- arch/x86/kernel/acpi/sleep.c | 2 + drivers/acpi/sleep/main.c | 276 +++++++++++++++++++++--------------- drivers/base/power/main.c | 2 - include/linux/acpi.h | 3 + include/linux/suspend.h | 14 +- kernel/power/disk.c | 28 +++- kernel/power/main.c | 10 +- 8 files changed, 215 insertions(+), 126 deletions(-) (limited to 'arch') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9cf7b34f2db0..18d793ea0dd3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -147,10 +147,14 @@ and is between 256 and 4096 characters. It is defined in the file default: 0 acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep } + Format: { s3_bios, s3_mode, s3_beep, old_ordering } See Documentation/power/video.txt for s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. + old_ordering causes the ACPI 1.0 ordering of the _PTS + control method, wrt putting devices into low power + states, to be enforced (the ACPI 2.0 ordering of _PTS is + used by default). acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode Format: { level | edge | high | low } diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index afc25ee9964b..882e970032d5 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -124,6 +124,8 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; + if (strncmp(str, "old_ordering", 12) == 0) + acpi_old_suspend_ordering(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c index 0f2caea2fc83..4addf8ad50ae 100644 --- a/drivers/acpi/sleep/main.c +++ b/drivers/acpi/sleep/main.c @@ -24,10 +24,6 @@ u8 sleep_states[ACPI_S_STATE_COUNT]; -#ifdef CONFIG_PM_SLEEP -static u32 acpi_target_sleep_state = ACPI_STATE_S0; -#endif - static int acpi_sleep_prepare(u32 acpi_state) { #ifdef CONFIG_ACPI_SLEEP @@ -50,9 +46,96 @@ static int acpi_sleep_prepare(u32 acpi_state) return 0; } -#ifdef CONFIG_SUSPEND -static struct platform_suspend_ops acpi_suspend_ops; +#ifdef CONFIG_PM_SLEEP +static u32 acpi_target_sleep_state = ACPI_STATE_S0; + +/* + * ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the + * user to request that behavior by using the 'acpi_old_suspend_ordering' + * kernel command line option that causes the following variable to be set. + */ +static bool old_suspend_ordering; + +void __init acpi_old_suspend_ordering(void) +{ + old_suspend_ordering = true; +} + +/** + * acpi_pm_disable_gpes - Disable the GPEs. + */ +static int acpi_pm_disable_gpes(void) +{ + acpi_hw_disable_all_gpes(); + return 0; +} + +/** + * __acpi_pm_prepare - Prepare the platform to enter the target state. + * + * If necessary, set the firmware waking vector and do arch-specific + * nastiness to get the wakeup code to the waking vector. + */ +static int __acpi_pm_prepare(void) +{ + int error = acpi_sleep_prepare(acpi_target_sleep_state); + + if (error) + acpi_target_sleep_state = ACPI_STATE_S0; + return error; +} + +/** + * acpi_pm_prepare - Prepare the platform to enter the target sleep + * state and disable the GPEs. + */ +static int acpi_pm_prepare(void) +{ + int error = __acpi_pm_prepare(); + + if (!error) + acpi_hw_disable_all_gpes(); + return error; +} + +/** + * acpi_pm_finish - Instruct the platform to leave a sleep state. + * + * This is called after we wake back up (or if entering the sleep state + * failed). + */ +static void acpi_pm_finish(void) +{ + u32 acpi_state = acpi_target_sleep_state; + + if (acpi_state == ACPI_STATE_S0) + return; + printk(KERN_INFO PREFIX "Waking up from system sleep state S%d\n", + acpi_state); + acpi_disable_wakeup_device(acpi_state); + acpi_leave_sleep_state(acpi_state); + + /* reset firmware waking vector */ + acpi_set_firmware_waking_vector((acpi_physical_address) 0); + + acpi_target_sleep_state = ACPI_STATE_S0; +} + +/** + * acpi_pm_end - Finish up suspend sequence. + */ +static void acpi_pm_end(void) +{ + /* + * This is necessary in case acpi_pm_finish() is not called during a + * failing transition to a sleep state. + */ + acpi_target_sleep_state = ACPI_STATE_S0; +} +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_SUSPEND extern void do_suspend_lowlevel(void); static u32 acpi_suspend_states[] = { @@ -66,7 +149,6 @@ static u32 acpi_suspend_states[] = { * acpi_suspend_begin - Set the target system sleep state to the state * associated with given @pm_state, if supported. */ - static int acpi_suspend_begin(suspend_state_t pm_state) { u32 acpi_state = acpi_suspend_states[pm_state]; @@ -82,25 +164,6 @@ static int acpi_suspend_begin(suspend_state_t pm_state) return error; } -/** - * acpi_suspend_prepare - Do preliminary suspend work. - * - * If necessary, set the firmware waking vector and do arch-specific - * nastiness to get the wakeup code to the waking vector. - */ - -static int acpi_suspend_prepare(void) -{ - int error = acpi_sleep_prepare(acpi_target_sleep_state); - - if (error) { - acpi_target_sleep_state = ACPI_STATE_S0; - return error; - } - - return ACPI_SUCCESS(acpi_hw_disable_all_gpes()) ? 0 : -EFAULT; -} - /** * acpi_suspend_enter - Actually enter a sleep state. * @pm_state: ignored @@ -109,7 +172,6 @@ static int acpi_suspend_prepare(void) * assembly, which in turn call acpi_enter_sleep_state(). * It's unfortunate, but it works. Please fix if you're feeling frisky. */ - static int acpi_suspend_enter(suspend_state_t pm_state) { acpi_status status = AE_OK; @@ -166,39 +228,6 @@ static int acpi_suspend_enter(suspend_state_t pm_state) return ACPI_SUCCESS(status) ? 0 : -EFAULT; } -/** - * acpi_suspend_finish - Instruct the platform to leave a sleep state. - * - * This is called after we wake back up (or if entering the sleep state - * failed). - */ - -static void acpi_suspend_finish(void) -{ - u32 acpi_state = acpi_target_sleep_state; - - acpi_disable_wakeup_device(acpi_state); - acpi_leave_sleep_state(acpi_state); - - /* reset firmware waking vector */ - acpi_set_firmware_waking_vector((acpi_physical_address) 0); - - acpi_target_sleep_state = ACPI_STATE_S0; -} - -/** - * acpi_suspend_end - Finish up suspend sequence. - */ - -static void acpi_suspend_end(void) -{ - /* - * This is necessary in case acpi_suspend_finish() is not called during a - * failing transition to a sleep state. - */ - acpi_target_sleep_state = ACPI_STATE_S0; -} - static int acpi_suspend_state_valid(suspend_state_t pm_state) { u32 acpi_state; @@ -218,10 +247,39 @@ static int acpi_suspend_state_valid(suspend_state_t pm_state) static struct platform_suspend_ops acpi_suspend_ops = { .valid = acpi_suspend_state_valid, .begin = acpi_suspend_begin, - .prepare = acpi_suspend_prepare, + .prepare = acpi_pm_prepare, + .enter = acpi_suspend_enter, + .finish = acpi_pm_finish, + .end = acpi_pm_end, +}; + +/** + * acpi_suspend_begin_old - Set the target system sleep state to the + * state associated with given @pm_state, if supported, and + * execute the _PTS control method. This function is used if the + * pre-ACPI 2.0 suspend ordering has been requested. + */ +static int acpi_suspend_begin_old(suspend_state_t pm_state) +{ + int error = acpi_suspend_begin(pm_state); + + if (!error) + error = __acpi_pm_prepare(); + return error; +} + +/* + * The following callbacks are used if the pre-ACPI 2.0 suspend ordering has + * been requested. + */ +static struct platform_suspend_ops acpi_suspend_ops_old = { + .valid = acpi_suspend_state_valid, + .begin = acpi_suspend_begin_old, + .prepare = acpi_pm_disable_gpes, .enter = acpi_suspend_enter, - .finish = acpi_suspend_finish, - .end = acpi_suspend_end, + .finish = acpi_pm_finish, + .end = acpi_pm_end, + .recover = acpi_pm_finish, }; #endif /* CONFIG_SUSPEND */ @@ -229,22 +287,9 @@ static struct platform_suspend_ops acpi_suspend_ops = { static int acpi_hibernation_begin(void) { acpi_target_sleep_state = ACPI_STATE_S4; - return 0; } -static int acpi_hibernation_prepare(void) -{ - int error = acpi_sleep_prepare(ACPI_STATE_S4); - - if (error) { - acpi_target_sleep_state = ACPI_STATE_S0; - return error; - } - - return ACPI_SUCCESS(acpi_hw_disable_all_gpes()) ? 0 : -EFAULT; -} - static int acpi_hibernation_enter(void) { acpi_status status = AE_OK; @@ -274,52 +319,55 @@ static void acpi_hibernation_leave(void) acpi_leave_sleep_state_prep(ACPI_STATE_S4); } -static void acpi_hibernation_finish(void) +static void acpi_pm_enable_gpes(void) { - acpi_disable_wakeup_device(ACPI_STATE_S4); - acpi_leave_sleep_state(ACPI_STATE_S4); - - /* reset firmware waking vector */ - acpi_set_firmware_waking_vector((acpi_physical_address) 0); - - acpi_target_sleep_state = ACPI_STATE_S0; + acpi_hw_enable_all_runtime_gpes(); } -static void acpi_hibernation_end(void) -{ - /* - * This is necessary in case acpi_hibernation_finish() is not called - * during a failing transition to the sleep state. - */ - acpi_target_sleep_state = ACPI_STATE_S0; -} +static struct platform_hibernation_ops acpi_hibernation_ops = { + .begin = acpi_hibernation_begin, + .end = acpi_pm_end, + .pre_snapshot = acpi_pm_prepare, + .finish = acpi_pm_finish, + .prepare = acpi_pm_prepare, + .enter = acpi_hibernation_enter, + .leave = acpi_hibernation_leave, + .pre_restore = acpi_pm_disable_gpes, + .restore_cleanup = acpi_pm_enable_gpes, +}; -static int acpi_hibernation_pre_restore(void) +/** + * acpi_hibernation_begin_old - Set the target system sleep state to + * ACPI_STATE_S4 and execute the _PTS control method. This + * function is used if the pre-ACPI 2.0 suspend ordering has been + * requested. + */ +static int acpi_hibernation_begin_old(void) { - acpi_status status; - - status = acpi_hw_disable_all_gpes(); - - return ACPI_SUCCESS(status) ? 0 : -EFAULT; -} + int error = acpi_sleep_prepare(ACPI_STATE_S4); -static void acpi_hibernation_restore_cleanup(void) -{ - acpi_hw_enable_all_runtime_gpes(); + if (!error) + acpi_target_sleep_state = ACPI_STATE_S4; + return error; } -static struct platform_hibernation_ops acpi_hibernation_ops = { - .begin = acpi_hibernation_begin, - .end = acpi_hibernation_end, - .pre_snapshot = acpi_hibernation_prepare, - .finish = acpi_hibernation_finish, - .prepare = acpi_hibernation_prepare, +/* + * The following callbacks are used if the pre-ACPI 2.0 suspend ordering has + * been requested. + */ +static struct platform_hibernation_ops acpi_hibernation_ops_old = { + .begin = acpi_hibernation_begin_old, + .end = acpi_pm_end, + .pre_snapshot = acpi_pm_disable_gpes, + .finish = acpi_pm_finish, + .prepare = acpi_pm_disable_gpes, .enter = acpi_hibernation_enter, .leave = acpi_hibernation_leave, - .pre_restore = acpi_hibernation_pre_restore, - .restore_cleanup = acpi_hibernation_restore_cleanup, + .pre_restore = acpi_pm_disable_gpes, + .restore_cleanup = acpi_pm_enable_gpes, + .recover = acpi_pm_finish, }; -#endif /* CONFIG_HIBERNATION */ +#endif /* CONFIG_HIBERNATION */ int acpi_suspend(u32 acpi_state) { @@ -461,13 +509,15 @@ int __init acpi_sleep_init(void) } } - suspend_set_ops(&acpi_suspend_ops); + suspend_set_ops(old_suspend_ordering ? + &acpi_suspend_ops_old : &acpi_suspend_ops); #endif #ifdef CONFIG_HIBERNATION status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b); if (ACPI_SUCCESS(status)) { - hibernation_set_ops(&acpi_hibernation_ops); + hibernation_set_ops(old_suspend_ordering ? + &acpi_hibernation_ops_old : &acpi_hibernation_ops); sleep_states[ACPI_STATE_S4] = 1; printk(" S4"); } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index d571204aaff7..3250c5257b74 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -781,8 +781,6 @@ int device_suspend(pm_message_t state) error = dpm_prepare(state); if (!error) error = dpm_suspend(state); - if (error) - device_resume(resume_event(state)); return error; } EXPORT_SYMBOL_GPL(device_suspend); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 41f7ce7edd7a..33adcf91ef41 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -234,6 +234,9 @@ int acpi_check_region(resource_size_t start, resource_size_t n, int acpi_check_mem_region(resource_size_t start, resource_size_t n, const char *name); +#ifdef CONFIG_PM_SLEEP +void __init acpi_old_suspend_ordering(void); +#endif /* CONFIG_PM_SLEEP */ #else /* CONFIG_ACPI */ static inline int early_acpi_boot_init(void) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index a6977423baf7..e8e69159af71 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -86,6 +86,11 @@ typedef int __bitwise suspend_state_t; * that implement @begin(), but platforms implementing @begin() should * also provide a @end() which cleans up transitions aborted before * @enter(). + * + * @recover: Recover the platform from a suspend failure. + * Called by the PM core if the suspending of devices fails. + * This callback is optional and should only be implemented by platforms + * which require special recovery actions in that situation. */ struct platform_suspend_ops { int (*valid)(suspend_state_t state); @@ -94,6 +99,7 @@ struct platform_suspend_ops { int (*enter)(suspend_state_t state); void (*finish)(void); void (*end)(void); + void (*recover)(void); }; #ifdef CONFIG_SUSPEND @@ -149,7 +155,7 @@ extern void mark_free_pages(struct zone *zone); * The methods in this structure allow a platform to carry out special * operations required by it during a hibernation transition. * - * All the methods below must be implemented. + * All the methods below, except for @recover(), must be implemented. * * @begin: Tell the platform driver that we're starting hibernation. * Called right after shrinking memory and before freezing devices. @@ -189,6 +195,11 @@ extern void mark_free_pages(struct zone *zone); * @restore_cleanup: Clean up after a failing image restoration. * Called right after the nonboot CPUs have been enabled and before * thawing devices (runs with IRQs on). + * + * @recover: Recover the platform from a failure to suspend devices. + * Called by the PM core if the suspending of devices during hibernation + * fails. This callback is optional and should only be implemented by + * platforms which require special recovery actions in that situation. */ struct platform_hibernation_ops { int (*begin)(void); @@ -200,6 +211,7 @@ struct platform_hibernation_ops { void (*leave)(void); int (*pre_restore)(void); void (*restore_cleanup)(void); + void (*recover)(void); }; #ifdef CONFIG_HIBERNATION diff --git a/kernel/power/disk.c b/kernel/power/disk.c index d416be0efa8a..f011e0870b52 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -179,6 +179,17 @@ static void platform_restore_cleanup(int platform_mode) hibernation_ops->restore_cleanup(); } +/** + * platform_recover - recover the platform from a failure to suspend + * devices. + */ + +static void platform_recover(int platform_mode) +{ + if (platform_mode && hibernation_ops && hibernation_ops->recover) + hibernation_ops->recover(); +} + /** * create_image - freeze devices that need to be frozen with interrupts * off, create the hibernation image and thaw those devices. Control @@ -258,10 +269,10 @@ int hibernation_snapshot(int platform_mode) suspend_console(); error = device_suspend(PMSG_FREEZE); if (error) - goto Resume_console; + goto Recover_platform; if (hibernation_test(TEST_DEVICES)) - goto Resume_devices; + goto Recover_platform; error = platform_pre_snapshot(platform_mode); if (error || hibernation_test(TEST_PLATFORM)) @@ -285,11 +296,14 @@ int hibernation_snapshot(int platform_mode) Resume_devices: device_resume(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - Resume_console: resume_console(); Close: platform_end(platform_mode); return error; + + Recover_platform: + platform_recover(platform_mode); + goto Resume_devices; } /** @@ -398,8 +412,11 @@ int hibernation_platform_enter(void) suspend_console(); error = device_suspend(PMSG_HIBERNATE); - if (error) - goto Resume_console; + if (error) { + if (hibernation_ops->recover) + hibernation_ops->recover(); + goto Resume_devices; + } error = hibernation_ops->prepare(); if (error) @@ -428,7 +445,6 @@ int hibernation_platform_enter(void) hibernation_ops->finish(); Resume_devices: device_resume(PMSG_RESTORE); - Resume_console: resume_console(); Close: hibernation_ops->end(); diff --git a/kernel/power/main.c b/kernel/power/main.c index d023b6b584e5..3398f4651aa1 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -269,11 +269,11 @@ int suspend_devices_and_enter(suspend_state_t state) error = device_suspend(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to suspend\n"); - goto Resume_console; + goto Recover_platform; } if (suspend_test(TEST_DEVICES)) - goto Resume_devices; + goto Recover_platform; if (suspend_ops->prepare) { error = suspend_ops->prepare(); @@ -294,12 +294,16 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_ops->finish(); Resume_devices: device_resume(PMSG_RESUME); - Resume_console: resume_console(); Close: if (suspend_ops->end) suspend_ops->end(); return error; + + Recover_platform: + if (suspend_ops->recover) + suspend_ops->recover(); + goto Resume_devices; } /** -- cgit v1.2.3 From 15650a2f644a2f15738cf22807c090d89328f500 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Mon, 16 Jun 2008 15:29:45 -0700 Subject: x86/PCI: fixup early quirk probing On x86, we do early PCI probing to apply some quirks for chipset bugs. However, in a recent cleanup (7bcbc78dea92fdf0947fa48e248da3c993a5690f) a thinko was introduced that causes us to probe all subfunctions of even single function devices (a function was factored out of an inner loop and a "break" became a "return"). Fix that up by making check_dev_quirk() return a value so we can keep the factored code intact. Acked-by: Ingo Molnar Signed-off-by: Jesse Barnes --- arch/x86/kernel/early-quirks.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 9f51e1ea9e82..8566fea647eb 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -133,7 +133,18 @@ static struct chipset early_qrk[] __initdata = { {} }; -static void __init check_dev_quirk(int num, int slot, int func) +/** + * check_dev_quirk - apply early quirks to a given PCI device + * @num: bus number + * @slot: slot number + * @func: PCI function + * + * Check the vendor & device ID against the early quirks table. + * + * If the device is single function, let early_quirks() know so we don't + * poke at this device again. + */ +static int __init check_dev_quirk(int num, int slot, int func) { u16 class; u16 vendor; @@ -144,7 +155,7 @@ static void __init check_dev_quirk(int num, int slot, int func) class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); if (class == 0xffff) - return; + return -1; /* no class, treat as single function */ vendor = read_pci_config_16(num, slot, func, PCI_VENDOR_ID); @@ -167,7 +178,9 @@ static void __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); if (!(type & 0x80)) - return; + return -1; + + return 0; } void __init early_quirks(void) @@ -180,6 +193,9 @@ void __init early_quirks(void) /* Poor man's PCI discovery */ for (num = 0; num < 32; num++) for (slot = 0; slot < 32; slot++) - for (func = 0; func < 8; func++) - check_dev_quirk(num, slot, func); + for (func = 0; func < 8; func++) { + /* Only probe function 0 on single fn devices */ + if (check_dev_quirk(num, slot, func)) + break; + } } -- cgit v1.2.3 From 0aea531326d1a17ccef7d9a538429c5b32cf4f12 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 18 Jun 2008 01:33:32 +0300 Subject: PCI: remove unused arch pcibios_update_resource() functions Russell King did the following back in 2003: <-- snip --> [PCI] pci-9: Kill per-architecture pcibios_update_resource() Kill pcibios_update_resource(), replacing it with pci_update_resource(). pci_update_resource() uses pcibios_resource_to_bus() to convert a resource to a device BAR - the transformation should be exactly the same as the transformation used for the PCI bridges. pci_update_resource "knows" about 64-bit BARs, but doesn't attempt to set the high 32-bits to anything non-zero - currently no architecture attempts to do something different. If anyone cares, please fix; I'm going to reflect current behaviour for the time being. Ivan pointed out the following architectures need to examine their pcibios_update_resource() implementation - they should make sure that this new implementation does the right thing. #warning's have been added where appropriate. ia64 mips mips64 This cset also includes a fix for the problem reported by AKPM where 64-bit arch compilers complain about the resource mask being placed in a u32. <-- snip --> This patch removes the unused pcibios_update_resource() functions the kernel gained since, from FRV, m68k, mips & sh architectures. Signed-off-by: Adrian Bunk Acked-by: David Howells Acked-by: Greg Ungerer Acked-by: Paul Mundt Acked-by: Ralf Baechle Signed-off-by: Jesse Barnes --- arch/frv/mb93090-mb00/pci-frv.c | 30 ------------------------------ arch/m68knommu/kernel/comempci.c | 9 --------- arch/mips/pmc-sierra/yosemite/ht.c | 36 ------------------------------------ arch/sh/drivers/pci/pci.c | 32 -------------------------------- 4 files changed, 107 deletions(-) (limited to 'arch') diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c index 4f165c93be42..edae117fcc2b 100644 --- a/arch/frv/mb93090-mb00/pci-frv.c +++ b/arch/frv/mb93090-mb00/pci-frv.c @@ -19,36 +19,6 @@ #include "pci-frv.h" -#if 0 -void -pcibios_update_resource(struct pci_dev *dev, struct resource *root, - struct resource *res, int resource) -{ - u32 new, check; - int reg; - - new = res->start | (res->flags & PCI_REGION_FLAG_MASK); - if (resource < 6) { - reg = PCI_BASE_ADDRESS_0 + 4*resource; - } else if (resource == PCI_ROM_RESOURCE) { - res->flags |= IORESOURCE_ROM_ENABLE; - new |= PCI_ROM_ADDRESS_ENABLE; - reg = dev->rom_base_reg; - } else { - /* Somebody might have asked allocation of a non-standard resource */ - return; - } - - pci_write_config_dword(dev, reg, new); - pci_read_config_dword(dev, reg, &check); - if ((new ^ check) & ((new & PCI_BASE_ADDRESS_SPACE_IO) ? PCI_BASE_ADDRESS_IO_MASK : PCI_BASE_ADDRESS_MEM_MASK)) { - printk(KERN_ERR "PCI: Error while updating region " - "%s/%d (%08x != %08x)\n", pci_name(dev), resource, - new, check); - } -} -#endif - /* * We need to avoid collisions with `mirrored' VGA ports * and other strange ISA hardware, so we always want the diff --git a/arch/m68knommu/kernel/comempci.c b/arch/m68knommu/kernel/comempci.c index 6ee00effbad2..0a68b5a85f86 100644 --- a/arch/m68knommu/kernel/comempci.c +++ b/arch/m68knommu/kernel/comempci.c @@ -373,15 +373,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return(0); } -/*****************************************************************************/ - -void pcibios_update_resource(struct pci_dev *dev, struct resource *root, struct resource *r, int resource) -{ - printk(KERN_WARNING "%s(%d): no support for changing PCI resources...\n", - __FILE__, __LINE__); -} - - /*****************************************************************************/ /* diff --git a/arch/mips/pmc-sierra/yosemite/ht.c b/arch/mips/pmc-sierra/yosemite/ht.c index 6380662bbf3c..678388fd34b1 100644 --- a/arch/mips/pmc-sierra/yosemite/ht.c +++ b/arch/mips/pmc-sierra/yosemite/ht.c @@ -345,42 +345,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return pcibios_enable_resources(dev); } - - -void pcibios_update_resource(struct pci_dev *dev, struct resource *root, - struct resource *res, int resource) -{ - u32 new, check; - int reg; - - return; - - new = res->start | (res->flags & PCI_REGION_FLAG_MASK); - if (resource < 6) { - reg = PCI_BASE_ADDRESS_0 + 4 * resource; - } else if (resource == PCI_ROM_RESOURCE) { - res->flags |= IORESOURCE_ROM_ENABLE; - reg = dev->rom_base_reg; - } else { - /* - * Somebody might have asked allocation of a non-standard - * resource - */ - return; - } - - pci_write_config_dword(dev, reg, new); - pci_read_config_dword(dev, reg, &check); - if ((new ^ check) & - ((new & PCI_BASE_ADDRESS_SPACE_IO) ? PCI_BASE_ADDRESS_IO_MASK : - PCI_BASE_ADDRESS_MEM_MASK)) { - printk(KERN_ERR "PCI: Error while updating region " - "%s/%d (%08x != %08x)\n", pci_name(dev), resource, - new, check); - } -} - - void pcibios_align_resource(void *data, struct resource *res, resource_size_t size, resource_size_t align) { diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index 08d2e7325252..f57095a2617c 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -76,38 +76,6 @@ void __devinit __weak pcibios_fixup_bus(struct pci_bus *bus) pci_read_bridge_bases(bus); } -void -pcibios_update_resource(struct pci_dev *dev, struct resource *root, - struct resource *res, int resource) -{ - u32 new, check; - int reg; - - new = res->start | (res->flags & PCI_REGION_FLAG_MASK); - if (resource < 6) { - reg = PCI_BASE_ADDRESS_0 + 4*resource; - } else if (resource == PCI_ROM_RESOURCE) { - res->flags |= IORESOURCE_ROM_ENABLE; - new |= PCI_ROM_ADDRESS_ENABLE; - reg = dev->rom_base_reg; - } else { - /* - * Somebody might have asked allocation of a non-standard - * resource - */ - return; - } - - pci_write_config_dword(dev, reg, new); - pci_read_config_dword(dev, reg, &check); - if ((new ^ check) & ((new & PCI_BASE_ADDRESS_SPACE_IO) ? - PCI_BASE_ADDRESS_IO_MASK : PCI_BASE_ADDRESS_MEM_MASK)) { - printk(KERN_ERR "PCI: Error while updating region " - "%s/%d (%08x != %08x)\n", pci_name(dev), resource, - new, check); - } -} - void pcibios_align_resource(void *data, struct resource *res, resource_size_t size, resource_size_t align) __attribute__ ((weak)); -- cgit v1.2.3 From c6c4f070a61b2b6e5cd317a5fbf25255878688a2 Mon Sep 17 00:00:00 2001 From: Greg KH Date: Thu, 3 Jul 2008 09:49:39 -0700 Subject: PCI: make pci_name use dev_name Also fixes up the sparc code that was assuming this is not a constant. Acked-by: David S. Miller Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman Signed-off-by: Jesse Barnes --- arch/sparc64/kernel/pci.c | 2 +- include/linux/pci.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc64/kernel/pci.c index 112b09f16f36..d00a3656c287 100644 --- a/arch/sparc64/kernel/pci.c +++ b/arch/sparc64/kernel/pci.c @@ -408,7 +408,7 @@ struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->class = class >> 8; dev->revision = class & 0xff; - sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), + sprintf(dev->dev.bus_id, "%04x:%02x:%02x.%d", pci_domain_nr(bus), dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); if (ofpci_verbose) diff --git a/include/linux/pci.h b/include/linux/pci.h index 96ebaa8d80e3..4c80dc3f2990 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -996,9 +996,9 @@ static inline void pci_set_drvdata(struct pci_dev *pdev, void *data) /* If you want to know what to call your pci_dev, ask this function. * Again, it's a wrapper around the generic device. */ -static inline char *pci_name(struct pci_dev *pdev) +static inline const char *pci_name(struct pci_dev *pdev) { - return pdev->dev.bus_id; + return dev_name(&pdev->dev); } -- cgit v1.2.3 From beef3129b3afb74817acff72fda4a9d951e3973e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 11 Jul 2008 15:21:17 -0600 Subject: x86/PCI: Fix PCI config space for domains > 0 John Keller reports that PCI config space access is broken on machines with more than one domain. conf1 accesses only work for domain 0, so make sure we check the domain number in the raw routines before trying conf1. Reported-by: John Keller Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- arch/x86/pci/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index d19fd07bafd6..86aff81a0829 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -32,7 +32,7 @@ struct pci_raw_ops *raw_pci_ext_ops; int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) { - if (reg < 256 && raw_pci_ops) + if (domain == 0 && reg < 256 && raw_pci_ops) return raw_pci_ops->read(domain, bus, devfn, reg, len, val); if (raw_pci_ext_ops) return raw_pci_ext_ops->read(domain, bus, devfn, reg, len, val); @@ -42,7 +42,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 val) { - if (reg < 256 && raw_pci_ops) + if (domain == 0 && reg < 256 && raw_pci_ops) return raw_pci_ops->write(domain, bus, devfn, reg, len, val); if (raw_pci_ext_ops) return raw_pci_ext_ops->write(domain, bus, devfn, reg, len, val); -- cgit v1.2.3 From 809d9a8f93bd8504dcc34b16bbfdfd1a8c9bb1ed Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Tue, 15 Jul 2008 11:59:42 -0700 Subject: x86/PCI: ACPI based PCI gap calculation Using ACPI to find free address space allows us to find a gap for the unallocated PCI resources or MMIO resources for hotplug devices within the BIOS allowed PCI regions. It works by evaluating the _CRS object under PCI0 looking for producer resources. Then searches the e820 memory space for a gap within these producer resources. Signed-off-by: Alok N Kataria Cc: Andi Kleen Cc: Len Brown Cc: Ingo Molnar Signed-off-by: Jesse Barnes --- arch/x86/pci/acpi.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'arch') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d95de2f199cd..d1ffb5709174 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "pci.h" struct pci_root_info { @@ -14,6 +15,11 @@ struct pci_root_info { int busnum; }; +struct gap_info { + unsigned long gapstart; + unsigned long gapsize; +}; + static acpi_status resource_to_addr(struct acpi_resource *resource, struct acpi_resource_address64 *addr) @@ -110,6 +116,78 @@ adjust_transparent_bridge_resources(struct pci_bus *bus) } } +static acpi_status search_gap(struct acpi_resource *resource, void *data) +{ + struct acpi_resource_address64 addr; + acpi_status status; + struct gap_info *gap = data; + unsigned long long start_addr, end_addr; + + status = resource_to_addr(resource, &addr); + if (ACPI_SUCCESS(status) && + addr.resource_type == ACPI_MEMORY_RANGE && + addr.address_length > gap->gapsize) { + start_addr = addr.minimum + addr.translation_offset; + /* + * We want space only in the 32bit address range + */ + if (start_addr < UINT_MAX) { + end_addr = start_addr + addr.address_length; + e820_search_gap(&gap->gapstart, &gap->gapsize, + start_addr, end_addr); + } + } + + return AE_OK; +} + +/* + * Search for a hole in the 32 bit address space for PCI to assign MMIO + * resources, for hotplug or unconfigured resources. + * We query the CRS object of the PCI root device to look for possible producer + * resources in the tree and consider these while calulating the start address + * for this hole. + */ +static void pci_setup_gap(acpi_handle *handle) +{ + struct gap_info gap; + acpi_status status; + + gap.gapstart = 0; + gap.gapsize = 0x400000; + + status = acpi_walk_resources(handle, METHOD_NAME__CRS, + search_gap, &gap); + + if (ACPI_SUCCESS(status)) { + unsigned long round; + + if (!gap.gapstart) { + printk(KERN_ERR "ACPI: Warning: Cannot find a gap " + "in the 32bit address range for PCI\n" + "ACPI: PCI devices may collide with " + "hotpluggable memory address range\n"); + } + /* + * Round the gapstart, uses the same logic as in + * e820_gap_setup + */ + round = 0x100000; + while ((gap.gapsize >> 4) > round) + round += round; + /* Fun with two's complement */ + pci_mem_start = (gap.gapstart + round) & -round; + + printk(KERN_INFO "ACPI: PCI resources should " + "start at %lx (gap: %lx:%lx)\n", + pci_mem_start, gap.gapstart, gap.gapsize); + } else { + printk(KERN_ERR "ACPI: Error while searching for gap in " + "the 32bit address range for PCI\n"); + } +} + + static void get_current_resources(struct acpi_device *device, int busnum, int domain, struct pci_bus *bus) @@ -215,6 +293,8 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus && (pci_probe & PCI_USE__CRS)) get_current_resources(device, busnum, domain, bus); + + pci_setup_gap(device->handle); return bus; } -- cgit v1.2.3 From 58b6e5538460be358fdf1286d9a2fbcfcc2cfaba Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Wed, 16 Jul 2008 16:21:47 -0700 Subject: Revert "x86/PCI: ACPI based PCI gap calculation" This reverts commit 809d9a8f93bd8504dcc34b16bbfdfd1a8c9bb1ed. This one isn't quite ready for prime time. It needs more testing and additional feedback from the ACPI guys. --- arch/x86/pci/acpi.c | 80 ----------------------------------------------------- 1 file changed, 80 deletions(-) (limited to 'arch') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d1ffb5709174..d95de2f199cd 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -4,7 +4,6 @@ #include #include #include -#include #include "pci.h" struct pci_root_info { @@ -15,11 +14,6 @@ struct pci_root_info { int busnum; }; -struct gap_info { - unsigned long gapstart; - unsigned long gapsize; -}; - static acpi_status resource_to_addr(struct acpi_resource *resource, struct acpi_resource_address64 *addr) @@ -116,78 +110,6 @@ adjust_transparent_bridge_resources(struct pci_bus *bus) } } -static acpi_status search_gap(struct acpi_resource *resource, void *data) -{ - struct acpi_resource_address64 addr; - acpi_status status; - struct gap_info *gap = data; - unsigned long long start_addr, end_addr; - - status = resource_to_addr(resource, &addr); - if (ACPI_SUCCESS(status) && - addr.resource_type == ACPI_MEMORY_RANGE && - addr.address_length > gap->gapsize) { - start_addr = addr.minimum + addr.translation_offset; - /* - * We want space only in the 32bit address range - */ - if (start_addr < UINT_MAX) { - end_addr = start_addr + addr.address_length; - e820_search_gap(&gap->gapstart, &gap->gapsize, - start_addr, end_addr); - } - } - - return AE_OK; -} - -/* - * Search for a hole in the 32 bit address space for PCI to assign MMIO - * resources, for hotplug or unconfigured resources. - * We query the CRS object of the PCI root device to look for possible producer - * resources in the tree and consider these while calulating the start address - * for this hole. - */ -static void pci_setup_gap(acpi_handle *handle) -{ - struct gap_info gap; - acpi_status status; - - gap.gapstart = 0; - gap.gapsize = 0x400000; - - status = acpi_walk_resources(handle, METHOD_NAME__CRS, - search_gap, &gap); - - if (ACPI_SUCCESS(status)) { - unsigned long round; - - if (!gap.gapstart) { - printk(KERN_ERR "ACPI: Warning: Cannot find a gap " - "in the 32bit address range for PCI\n" - "ACPI: PCI devices may collide with " - "hotpluggable memory address range\n"); - } - /* - * Round the gapstart, uses the same logic as in - * e820_gap_setup - */ - round = 0x100000; - while ((gap.gapsize >> 4) > round) - round += round; - /* Fun with two's complement */ - pci_mem_start = (gap.gapstart + round) & -round; - - printk(KERN_INFO "ACPI: PCI resources should " - "start at %lx (gap: %lx:%lx)\n", - pci_mem_start, gap.gapstart, gap.gapsize); - } else { - printk(KERN_ERR "ACPI: Error while searching for gap in " - "the 32bit address range for PCI\n"); - } -} - - static void get_current_resources(struct acpi_device *device, int busnum, int domain, struct pci_bus *bus) @@ -293,8 +215,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus && (pci_probe & PCI_USE__CRS)) get_current_resources(device, busnum, domain, bus); - - pci_setup_gap(device->handle); return bus; } -- cgit v1.2.3