From e70c9d5e61c6cb2272c866fc1303e62975006752 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 25 Jun 2005 14:54:25 -0700 Subject: [PATCH] I8K: use standard DMI interface I8K: Change to use stock dmi infrastructure instead of homegrown parsing code. The driver now requires box's DMI data to match list of supported models so driver can be safely compiled-in by default without fear of it poking into random SMM BIOS code. DMI checks can be ignored with i8k.ignore_dmi option. Signed-off-by: Dmitry Torokhov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/dmi_scan.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index 6ed7e28f306c..3facd20212bb 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -414,6 +414,7 @@ static void __init dmi_decode(struct dmi_header *dm) dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); dmi_printk(("Serial Number: %s\n", dmi_string(dm, data[7]))); + dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); break; case 2: dmi_printk(("Board Vendor: %s\n", @@ -470,7 +471,6 @@ fail: d++; return count; } - EXPORT_SYMBOL(dmi_check_system); /** @@ -480,8 +480,8 @@ EXPORT_SYMBOL(dmi_check_system); * Returns one DMI data value, can be used to perform * complex DMI data checks. */ -char * dmi_get_system_info(int field) +char *dmi_get_system_info(int field) { return dmi_ident[field]; } - +EXPORT_SYMBOL(dmi_get_system_info); -- cgit v1.2.2 From aea00143a8db8c0b31dca85bff3c325444d93f0f Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Sat, 25 Jun 2005 14:54:42 -0700 Subject: [PATCH] dmi: move ACPI boot quirk This patch moves ACPI boot quirks out of dmi_scan.c Signed-off-by: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/acpi/boot.c | 219 ++++++++++++++++++++++++++++++++++++++++++- arch/i386/kernel/dmi_scan.c | 163 -------------------------------- 2 files changed, 217 insertions(+), 165 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 848bb97af7ca..0771596c5496 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -815,6 +816,218 @@ acpi_process_madt(void) return; } +extern int acpi_force; + +#ifdef __i386__ + +#ifdef CONFIG_ACPI_PCI +static int __init disable_acpi_irq(struct dmi_system_id *d) +{ + if (!acpi_force) { + printk(KERN_NOTICE "%s detected: force use of acpi=noirq\n", + d->ident); + acpi_noirq_set(); + } + return 0; +} + +static int __init disable_acpi_pci(struct dmi_system_id *d) +{ + if (!acpi_force) { + printk(KERN_NOTICE "%s detected: force use of pci=noacpi\n", + d->ident); + acpi_disable_pci(); + } + return 0; +} +#endif + +static int __init dmi_disable_acpi(struct dmi_system_id *d) +{ + if (!acpi_force) { + printk(KERN_NOTICE "%s detected: acpi off\n",d->ident); + disable_acpi(); + } else { + printk(KERN_NOTICE + "Warning: DMI blacklist says broken, but acpi forced\n"); + } + return 0; +} + +/* + * Limit ACPI to CPU enumeration for HT + */ +static int __init force_acpi_ht(struct dmi_system_id *d) +{ + if (!acpi_force) { + printk(KERN_NOTICE "%s detected: force use of acpi=ht\n", d->ident); + disable_acpi(); + acpi_ht = 1; + } else { + printk(KERN_NOTICE + "Warning: acpi=force overrules DMI blacklist: acpi=ht\n"); + } + return 0; +} + +/* + * If your system is blacklisted here, but you find that acpi=force + * works for you, please contact acpi-devel@sourceforge.net + */ +static struct dmi_system_id __initdata acpi_dmi_table[] = { + /* + * Boxes that need ACPI disabled + */ + { + .callback = dmi_disable_acpi, + .ident = "IBM Thinkpad", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_BOARD_NAME, "2629H1G"), + }, + }, + + /* + * Boxes that need acpi=ht + */ + { + .callback = force_acpi_ht, + .ident = "FSC Primergy T850", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "PRIMERGY T850"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "DELL GX240", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "OptiPlex GX240"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "HP VISUALIZE NT Workstation", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP VISUALIZE NT Workstation"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "Compaq Workstation W8000", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "Workstation W8000"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "ASUS P4B266", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P4B266"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "ASUS P2B-DS", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "ASUS CUR-DLS", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "CUR-DLS"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "ABIT i440BX-W83977", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ABIT "), + DMI_MATCH(DMI_BOARD_NAME, "i440BX-W83977 (BP6)"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "IBM Bladecenter", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_BOARD_NAME, "IBM eServer BladeCenter HS20"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "IBM eServer xSeries 360", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_BOARD_NAME, "eServer xSeries 360"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "IBM eserver xSeries 330", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_BOARD_NAME, "eserver xSeries 330"), + }, + }, + { + .callback = force_acpi_ht, + .ident = "IBM eserver xSeries 440", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "eserver xSeries 440"), + }, + }, + +#ifdef CONFIG_ACPI_PCI + /* + * Boxes that need ACPI PCI IRQ routing disabled + */ + { + .callback = disable_acpi_irq, + .ident = "ASUS A7V", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC"), + DMI_MATCH(DMI_BOARD_NAME, ""), + /* newer BIOS, Revision 1011, does work */ + DMI_MATCH(DMI_BIOS_VERSION, "ASUS A7V ACPI BIOS Revision 1007"), + }, + }, + + /* + * Boxes that need ACPI PCI IRQ routing and PCI scan disabled + */ + { /* _BBN 0 bug */ + .callback = disable_acpi_pci, + .ident = "ASUS PR-DLS", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "PR-DLS"), + DMI_MATCH(DMI_BIOS_VERSION, "ASUS PR-DLS ACPI BIOS Revision 1010"), + DMI_MATCH(DMI_BIOS_DATE, "03/21/2003") + }, + }, + { + .callback = disable_acpi_pci, + .ident = "Acer TravelMate 36x Laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), + }, + }, +#endif +}; + +#endif /* __i386__ */ + /* * acpi_boot_table_init() and acpi_boot_init() * called from setup_arch(), always. @@ -843,6 +1056,10 @@ acpi_boot_table_init(void) { int error; +#ifdef __i386__ + dmi_check_system(acpi_dmi_table); +#endif + /* * If acpi_disabled, bail out * One exception: acpi=ht continues far enough to enumerate LAPICs @@ -870,8 +1087,6 @@ acpi_boot_table_init(void) */ error = acpi_blacklisted(); if (error) { - extern int acpi_force; - if (acpi_force) { printk(KERN_WARNING PREFIX "acpi=force override\n"); } else { diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index 3facd20212bb..b4bae60f5065 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -188,59 +188,6 @@ static __init int reset_videomode_after_s3(struct dmi_blacklist *d) #endif -#ifdef CONFIG_ACPI_BOOT -extern int acpi_force; - -static __init __attribute__((unused)) int dmi_disable_acpi(struct dmi_blacklist *d) -{ - if (!acpi_force) { - printk(KERN_NOTICE "%s detected: acpi off\n",d->ident); - disable_acpi(); - } else { - printk(KERN_NOTICE - "Warning: DMI blacklist says broken, but acpi forced\n"); - } - return 0; -} - -/* - * Limit ACPI to CPU enumeration for HT - */ -static __init __attribute__((unused)) int force_acpi_ht(struct dmi_blacklist *d) -{ - if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of acpi=ht\n", d->ident); - disable_acpi(); - acpi_ht = 1; - } else { - printk(KERN_NOTICE - "Warning: acpi=force overrules DMI blacklist: acpi=ht\n"); - } - return 0; -} -#endif - -#ifdef CONFIG_ACPI_PCI -static __init int disable_acpi_irq(struct dmi_blacklist *d) -{ - if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of acpi=noirq\n", - d->ident); - acpi_noirq_set(); - } - return 0; -} -static __init int disable_acpi_pci(struct dmi_blacklist *d) -{ - if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of pci=noacpi\n", - d->ident); - acpi_disable_pci(); - } - return 0; -} -#endif - /* * Process the DMI blacklists */ @@ -264,116 +211,6 @@ static __initdata struct dmi_blacklist dmi_blacklist[]={ } }, #endif -#ifdef CONFIG_ACPI_BOOT - /* - * If your system is blacklisted here, but you find that acpi=force - * works for you, please contact acpi-devel@sourceforge.net - */ - - /* - * Boxes that need ACPI disabled - */ - - { dmi_disable_acpi, "IBM Thinkpad", { - MATCH(DMI_BOARD_VENDOR, "IBM"), - MATCH(DMI_BOARD_NAME, "2629H1G"), - NO_MATCH, NO_MATCH }}, - - /* - * Boxes that need acpi=ht - */ - - { force_acpi_ht, "FSC Primergy T850", { - MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - MATCH(DMI_PRODUCT_NAME, "PRIMERGY T850"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "DELL GX240", { - MATCH(DMI_BOARD_VENDOR, "Dell Computer Corporation"), - MATCH(DMI_BOARD_NAME, "OptiPlex GX240"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "HP VISUALIZE NT Workstation", { - MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - MATCH(DMI_PRODUCT_NAME, "HP VISUALIZE NT Workstation"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "Compaq Workstation W8000", { - MATCH(DMI_SYS_VENDOR, "Compaq"), - MATCH(DMI_PRODUCT_NAME, "Workstation W8000"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "ASUS P4B266", { - MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - MATCH(DMI_BOARD_NAME, "P4B266"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "ASUS P2B-DS", { - MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - MATCH(DMI_BOARD_NAME, "P2B-DS"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "ASUS CUR-DLS", { - MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - MATCH(DMI_BOARD_NAME, "CUR-DLS"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "ABIT i440BX-W83977", { - MATCH(DMI_BOARD_VENDOR, "ABIT "), - MATCH(DMI_BOARD_NAME, "i440BX-W83977 (BP6)"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "IBM Bladecenter", { - MATCH(DMI_BOARD_VENDOR, "IBM"), - MATCH(DMI_BOARD_NAME, "IBM eServer BladeCenter HS20"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "IBM eServer xSeries 360", { - MATCH(DMI_BOARD_VENDOR, "IBM"), - MATCH(DMI_BOARD_NAME, "eServer xSeries 360"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "IBM eserver xSeries 330", { - MATCH(DMI_BOARD_VENDOR, "IBM"), - MATCH(DMI_BOARD_NAME, "eserver xSeries 330"), - NO_MATCH, NO_MATCH }}, - - { force_acpi_ht, "IBM eserver xSeries 440", { - MATCH(DMI_BOARD_VENDOR, "IBM"), - MATCH(DMI_PRODUCT_NAME, "eserver xSeries 440"), - NO_MATCH, NO_MATCH }}, - -#endif // CONFIG_ACPI_BOOT - -#ifdef CONFIG_ACPI_PCI - /* - * Boxes that need ACPI PCI IRQ routing disabled - */ - - { disable_acpi_irq, "ASUS A7V", { - MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC"), - MATCH(DMI_BOARD_NAME, ""), - /* newer BIOS, Revision 1011, does work */ - MATCH(DMI_BIOS_VERSION, "ASUS A7V ACPI BIOS Revision 1007"), - NO_MATCH }}, - - /* - * Boxes that need ACPI PCI IRQ routing and PCI scan disabled - */ - { disable_acpi_pci, "ASUS PR-DLS", { /* _BBN 0 bug */ - MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - MATCH(DMI_BOARD_NAME, "PR-DLS"), - MATCH(DMI_BIOS_VERSION, "ASUS PR-DLS ACPI BIOS Revision 1010"), - MATCH(DMI_BIOS_DATE, "03/21/2003") }}, - - { disable_acpi_pci, "Acer TravelMate 36x Laptop", { - MATCH(DMI_SYS_VENDOR, "Acer"), - MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), - NO_MATCH, NO_MATCH - } }, - -#endif - { NULL, } }; -- cgit v1.2.2 From 0f8133a8db81ff824a4abbe5bb0f15bf034d31c3 Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Sat, 25 Jun 2005 14:54:45 -0700 Subject: [PATCH] dmi: move ACPI sleep quirk This patch moves ACPI sleep quirk out of dmi_scan.c Signed-off-by: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/acpi/boot.c | 1 + arch/i386/kernel/acpi/sleep.c | 27 +++++++++++++++++++++++++++ arch/i386/kernel/dmi_scan.c | 16 ---------------- 3 files changed, 28 insertions(+), 16 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 0771596c5496..9f63ae0f404b 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -1024,6 +1024,7 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, }, #endif + { } }; #endif /* __i386__ */ diff --git a/arch/i386/kernel/acpi/sleep.c b/arch/i386/kernel/acpi/sleep.c index 28bb0514bb6e..c1af93032ff3 100644 --- a/arch/i386/kernel/acpi/sleep.c +++ b/arch/i386/kernel/acpi/sleep.c @@ -7,6 +7,7 @@ #include #include +#include #include #include @@ -91,3 +92,29 @@ static int __init acpi_sleep_setup(char *str) __setup("acpi_sleep=", acpi_sleep_setup); + + +static __init int reset_videomode_after_s3(struct dmi_system_id *d) +{ + acpi_video_flags |= 2; + return 0; +} + +static __initdata struct dmi_system_id acpisleep_dmi_table[] = { + { /* Reset video mode after returning from ACPI S3 sleep */ + .callback = reset_videomode_after_s3, + .ident = "Toshiba Satellite 4030cdt", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "S4030CDT/4.3"), + }, + }, + { } +}; + +static int __init acpisleep_dmi_init(void) +{ + dmi_check_system(acpisleep_dmi_table); + return 0; +} + +core_initcall(acpisleep_dmi_init); diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index b4bae60f5065..065c30a73c13 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -177,16 +177,6 @@ static __init int broken_toshiba_keyboard(struct dmi_blacklist *d) } -#ifdef CONFIG_ACPI_SLEEP -static __init int reset_videomode_after_s3(struct dmi_blacklist *d) -{ - /* See acpi_wakeup.S */ - extern long acpi_video_flags; - acpi_video_flags |= 2; - return 0; -} -#endif - /* * Process the DMI blacklists @@ -204,12 +194,6 @@ static __initdata struct dmi_blacklist dmi_blacklist[]={ MATCH(DMI_PRODUCT_NAME, "S4030CDT/4.3"), NO_MATCH, NO_MATCH, NO_MATCH } }, -#ifdef CONFIG_ACPI_SLEEP - { reset_videomode_after_s3, "Toshiba Satellite 4030cdt", { /* Reset video mode after returning from ACPI S3 sleep */ - MATCH(DMI_PRODUCT_NAME, "S4030CDT/4.3"), - NO_MATCH, NO_MATCH, NO_MATCH - } }, -#endif { NULL, } }; -- cgit v1.2.2 From b625883f24d018c989173aeb727f6de954fb154d Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Sat, 25 Jun 2005 14:54:46 -0700 Subject: [PATCH] dmi: remove central blacklist Since last dmi quirk looks useless (it just prints 404 compliant url) we can finally remove central dmi blacklist. Signed-off-by: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/dmi_scan.c | 45 +-------------------------------------------- 1 file changed, 1 insertion(+), 44 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index 065c30a73c13..ad4b369a5837 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -159,51 +159,11 @@ static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) printk(KERN_ERR "dmi_save_ident: out of memory.\n"); } -/* - * Ugly compatibility crap. - */ -#define dmi_blacklist dmi_system_id -#define NO_MATCH { DMI_NONE, NULL} -#define MATCH DMI_MATCH - -/* - * Toshiba keyboard likes to repeat keys when they are not repeated. - */ - -static __init int broken_toshiba_keyboard(struct dmi_blacklist *d) -{ - printk(KERN_WARNING "Toshiba with broken keyboard detected. If your keyboard sometimes generates 3 keypresses instead of one, see http://davyd.ucc.asn.au/projects/toshiba/README\n"); - return 0; -} - - - -/* - * Process the DMI blacklists - */ - - -/* - * This will be expanded over time to force things like the APM - * interrupt mask settings according to the laptop - */ - -static __initdata struct dmi_blacklist dmi_blacklist[]={ - - { broken_toshiba_keyboard, "Toshiba Satellite 4030cdt", { /* Keyboard generates spurious repeats */ - MATCH(DMI_PRODUCT_NAME, "S4030CDT/4.3"), - NO_MATCH, NO_MATCH, NO_MATCH - } }, - - { NULL, } -}; - /* * Process a DMI table entry. Right now all we care about are the BIOS * and machine entries. For 2.5 we should pull the smbus controller info * out of here. */ - static void __init dmi_decode(struct dmi_header *dm) { #ifdef DMI_DEBUG @@ -253,10 +213,7 @@ static void __init dmi_decode(struct dmi_header *dm) void __init dmi_scan_machine(void) { - int err = dmi_iterate(dmi_decode); - if(err == 0) - dmi_check_system(dmi_blacklist); - else + if (dmi_iterate(dmi_decode)) printk(KERN_INFO "DMI not present.\n"); } -- cgit v1.2.2 From 1249c5138f573890eae0c01f13d627094edcd55c Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Sat, 25 Jun 2005 14:54:47 -0700 Subject: [PATCH] dmi: spring cleanup Whitespace and CodingStyle cleanup. No functionality changes. Signed-off-by: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/dmi_scan.c | 163 +++++++++++++++++++------------------------- 1 file changed, 70 insertions(+), 93 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index ad4b369a5837..a3cdf894302b 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -1,22 +1,15 @@ #include -#include #include #include #include -#include -#include -#include -#include -#include #include #include -struct dmi_header -{ - u8 type; - u8 length; - u16 handle; +struct dmi_header { + u8 type; + u8 length; + u16 handle; }; #undef DMI_DEBUG @@ -29,15 +22,13 @@ struct dmi_header static char * __init dmi_string(struct dmi_header *dm, u8 s) { - u8 *bp=(u8 *)dm; - bp+=dm->length; - if(!s) + u8 *bp = ((u8 *) dm) + dm->length; + + if (!s) return ""; s--; - while(s>0 && *bp) - { - bp+=strlen(bp); - bp++; + while (s > 0 && *bp) { + bp += strlen(bp) + 1; s--; } return bp; @@ -47,16 +38,14 @@ static char * __init dmi_string(struct dmi_header *dm, u8 s) * We have to be cautious here. We have seen BIOSes with DMI pointers * pointing to completely the wrong place for example */ - -static int __init dmi_table(u32 base, int len, int num, void (*decode)(struct dmi_header *)) +static int __init dmi_table(u32 base, int len, int num, + void (*decode)(struct dmi_header *)) { - u8 *buf; - struct dmi_header *dm; - u8 *data; - int i=0; + u8 *buf, *data; + int i = 0; buf = bt_ioremap(base, len); - if(buf==NULL) + if (buf == NULL) return -1; data = buf; @@ -65,36 +54,34 @@ static int __init dmi_table(u32 base, int len, int num, void (*decode)(struct dm * Stop when we see all the items the table claimed to have * OR we run off the end of the table (also happens) */ - - while(ilength; - while(data-buflength; + while ((data - buf < len - 1) && (data[0] || data[1])) data++; - if(data-buf>4, buf[14]&0x0F); + buf[14] >> 4, buf[14] & 0xF); else printk(KERN_INFO "DMI present.\n"); + dmi_printk((KERN_INFO "%d structures occupying %d bytes.\n", num, len)); - dmi_printk((KERN_INFO "DMI table at 0x%08X.\n", - base)); - if(dmi_table(base,len, num, decode)==0) + dmi_printk((KERN_INFO "DMI table at 0x%08X.\n", base)); + + if (dmi_table(base,len, num, decode) == 0) return 0; } } @@ -143,16 +132,17 @@ static char *dmi_ident[DMI_STRING_MAX]; /* * Save a DMI string */ - static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) { char *d = (char*)dm; char *p = dmi_string(dm, d[string]); - if(p==NULL || *p == 0) + + if (p == NULL || *p == 0) return; if (dmi_ident[slot]) return; - dmi_ident[slot] = alloc_bootmem(strlen(p)+1); + + dmi_ident[slot] = alloc_bootmem(strlen(p) + 1); if(dmi_ident[slot]) strcpy(dmi_ident[slot], p); else @@ -166,48 +156,35 @@ static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) */ static void __init dmi_decode(struct dmi_header *dm) { -#ifdef DMI_DEBUG - u8 *data = (u8 *)dm; -#endif + u8 *data __attribute__((__unused__)) = (u8 *)dm; - switch(dm->type) - { - case 0: - dmi_printk(("BIOS Vendor: %s\n", - dmi_string(dm, data[4]))); - dmi_save_ident(dm, DMI_BIOS_VENDOR, 4); - dmi_printk(("BIOS Version: %s\n", - dmi_string(dm, data[5]))); - dmi_save_ident(dm, DMI_BIOS_VERSION, 5); - dmi_printk(("BIOS Release: %s\n", - dmi_string(dm, data[8]))); - dmi_save_ident(dm, DMI_BIOS_DATE, 8); - break; - case 1: - dmi_printk(("System Vendor: %s\n", - dmi_string(dm, data[4]))); - dmi_save_ident(dm, DMI_SYS_VENDOR, 4); - dmi_printk(("Product Name: %s\n", - dmi_string(dm, data[5]))); - dmi_save_ident(dm, DMI_PRODUCT_NAME, 5); - dmi_printk(("Version: %s\n", - dmi_string(dm, data[6]))); - dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); - dmi_printk(("Serial Number: %s\n", - dmi_string(dm, data[7]))); - dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); - break; - case 2: - dmi_printk(("Board Vendor: %s\n", - dmi_string(dm, data[4]))); - dmi_save_ident(dm, DMI_BOARD_VENDOR, 4); - dmi_printk(("Board Name: %s\n", - dmi_string(dm, data[5]))); - dmi_save_ident(dm, DMI_BOARD_NAME, 5); - dmi_printk(("Board Version: %s\n", - dmi_string(dm, data[6]))); - dmi_save_ident(dm, DMI_BOARD_VERSION, 6); - break; + switch(dm->type) { + case 0: + dmi_printk(("BIOS Vendor: %s\n", dmi_string(dm, data[4]))); + dmi_save_ident(dm, DMI_BIOS_VENDOR, 4); + dmi_printk(("BIOS Version: %s\n", dmi_string(dm, data[5]))); + dmi_save_ident(dm, DMI_BIOS_VERSION, 5); + dmi_printk(("BIOS Release: %s\n", dmi_string(dm, data[8]))); + dmi_save_ident(dm, DMI_BIOS_DATE, 8); + break; + case 1: + dmi_printk(("System Vendor: %s\n", dmi_string(dm, data[4]))); + dmi_save_ident(dm, DMI_SYS_VENDOR, 4); + dmi_printk(("Product Name: %s\n", dmi_string(dm, data[5]))); + dmi_save_ident(dm, DMI_PRODUCT_NAME, 5); + dmi_printk(("Version: %s\n", dmi_string(dm, data[6]))); + dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); + dmi_printk(("Serial Number: %s\n", dmi_string(dm, data[7]))); + dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); + break; + case 2: + dmi_printk(("Board Vendor: %s\n", dmi_string(dm, data[4]))); + dmi_save_ident(dm, DMI_BOARD_VENDOR, 4); + dmi_printk(("Board Name: %s\n", dmi_string(dm, data[5]))); + dmi_save_ident(dm, DMI_BOARD_NAME, 5); + dmi_printk(("Board Version: %s\n", dmi_string(dm, data[6]))); + dmi_save_ident(dm, DMI_BOARD_VERSION, 6); + break; } } -- cgit v1.2.2 From a13db56624c2a9d6c0dae0a693b25b0e58de9ea3 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Sat, 25 Jun 2005 14:54:48 -0700 Subject: [PATCH] CPU hotplug: fix hpet sectioning With hpet enabled, cpu hotplug uses some routines marked with __init. Signed-off-by: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/time_hpet.c | 2 +- arch/i386/kernel/timers/common.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/time_hpet.c b/arch/i386/kernel/time_hpet.c index 10a0cbb88e75..658c0629ba6a 100644 --- a/arch/i386/kernel/time_hpet.c +++ b/arch/i386/kernel/time_hpet.c @@ -50,7 +50,7 @@ static void hpet_writel(unsigned long d, unsigned long a) * comparator value and continue. Next tick can be caught by checking * for a change in the comparator value. Used in apic.c. */ -static void __init wait_hpet_tick(void) +static void __devinit wait_hpet_tick(void) { unsigned int start_cmp_val, end_cmp_val; diff --git a/arch/i386/kernel/timers/common.c b/arch/i386/kernel/timers/common.c index 37353bd31803..8163fe0cf1f0 100644 --- a/arch/i386/kernel/timers/common.c +++ b/arch/i386/kernel/timers/common.c @@ -86,7 +86,7 @@ bad_ctc: #define CALIBRATE_CNT_HPET (5 * hpet_tick) #define CALIBRATE_TIME_HPET (5 * KERNEL_TICK_USEC) -unsigned long __init calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr) +unsigned long __devinit calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr) { unsigned long tsc_startlow, tsc_starthigh; unsigned long tsc_endlow, tsc_endhigh; -- cgit v1.2.2 From d92de65cab5980c16d4a1c326c1ef9a591892883 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Sat, 25 Jun 2005 14:54:49 -0700 Subject: [PATCH] variable overflow after hundreds round of hotplug CPU I'm doing the cpu hotplug stress test and found a variable ('ready') is overflow after several hundreds rounds of cpu hotplug. Here is a fix. Signed-off-by: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/head.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S index e966fc8c44c4..4477bb107098 100644 --- a/arch/i386/kernel/head.S +++ b/arch/i386/kernel/head.S @@ -299,7 +299,6 @@ is386: movl $2,%ecx # set MP movl %eax,%cr0 call check_x87 - incb ready lgdt cpu_gdt_descr lidt idt_descr ljmp $(__KERNEL_CS),$1f @@ -316,8 +315,9 @@ is386: movl $2,%ecx # set MP lldt %ax cld # gcc2 wants the direction flag cleared at all times #ifdef CONFIG_SMP - movb ready, %cl - cmpb $1,%cl + movb ready, %cl + movb $1, ready + cmpb $0,%cl je 1f # the first CPU calls start_kernel # all other CPUs call initialize_secondary call initialize_secondary -- cgit v1.2.2 From f370513640492641b4046bfd9a6e4714f6ae530d Mon Sep 17 00:00:00 2001 From: Zwane Mwaikambo Date: Sat, 25 Jun 2005 14:54:50 -0700 Subject: [PATCH] i386 CPU hotplug (The i386 CPU hotplug patch provides infrastructure for some work which Pavel is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua is doing) The following provides i386 architecture support for safely unregistering and registering processors during runtime, updated for the current -mm tree. In order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The difference being that on cpu offline, fixup_irqs() is called before we clear the cpu from cpu_online_map and a long delay in order to ensure that we never have any queued external interrupts on the APICs. There are additional changes to s390 and ppc64 to account for this change. 1) Add CONFIG_HOTPLUG_CPU 2) disable local APIC timer on dead cpus. 3) Disable preempt around irq balancing to prevent CPUs going down. 4) Print irq stats for all possible cpus. 5) Debugging check for interrupts on offline cpus. 6) Hacky fixup_irqs() to redirect irqs when cpus go off/online. 7) play_dead() for offline cpus to spin inside. 8) Handle offline cpus set in flush_tlb_others(). 9) Grab lock earlier in smp_call_function() to prevent CPUs going down. 10) Implement __cpu_disable() and __cpu_die(). 11) Enable local interrupts in cpu_enable() after fixup_irqs() 12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus. 13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline. Signed-off-by: Zwane Mwaikambo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/Kconfig | 9 +++++ arch/i386/kernel/apic.c | 3 +- arch/i386/kernel/io_apic.c | 2 + arch/i386/kernel/irq.c | 67 +++++++++++++++++++++++++------ arch/i386/kernel/process.c | 39 +++++++++++++++++- arch/i386/kernel/smp.c | 24 +++++++----- arch/i386/kernel/smpboot.c | 98 +++++++++++++++++++++++++++++++++++++++++++--- arch/i386/kernel/traps.c | 8 ++++ 8 files changed, 221 insertions(+), 29 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index d4ae5f9ceae6..b4cd11e58451 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -1250,6 +1250,15 @@ config SCx200 This support is also available as a module. If compiled as a module, it will be called scx200. +config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs (EXPERIMENTAL)" + depends on SMP && HOTPLUG && EXPERIMENTAL + ---help--- + Say Y here to experiment with turning CPUs off and on. CPUs + can be controlled through /sys/devices/system/cpu. + + Say N. + source "drivers/pcmcia/Kconfig" source "drivers/pci/hotplug/Kconfig" diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 8d993fa71754..a28a088f3e75 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -1048,7 +1049,7 @@ void __init setup_secondary_APIC_clock(void) setup_APIC_timer(calibration_result); } -void __init disable_APIC_timer(void) +void __devinit disable_APIC_timer(void) { if (using_apic_timer) { unsigned long v; diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 08540bc4ba3e..3c2b3bdfc807 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -576,9 +576,11 @@ static int balanced_irq(void *unused) try_to_freeze(PF_FREEZE); if (time_after(jiffies, prev_balance_time+balanced_irq_interval)) { + preempt_disable(); do_irq_balance(); prev_balance_time = jiffies; time_remaining = balanced_irq_interval; + preempt_enable(); } } return 0; diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c index 73945a3c53c4..af115004aec5 100644 --- a/arch/i386/kernel/irq.c +++ b/arch/i386/kernel/irq.c @@ -15,6 +15,9 @@ #include #include #include +#include +#include +#include DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp; EXPORT_PER_CPU_SYMBOL(irq_stat); @@ -210,9 +213,8 @@ int show_interrupts(struct seq_file *p, void *v) if (i == 0) { seq_printf(p, " "); - for (j=0; jtypename); seq_printf(p, " %s", action->name); @@ -240,16 +241,14 @@ skip: spin_unlock_irqrestore(&irq_desc[i].lock, flags); } else if (i == NR_IRQS) { seq_printf(p, "NMI: "); - for (j = 0; j < NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", nmi_count(j)); + for_each_cpu(j) + seq_printf(p, "%10u ", nmi_count(j)); seq_putc(p, '\n'); #ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "LOC: "); - for (j = 0; j < NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", - per_cpu(irq_stat,j).apic_timer_irqs); + for_each_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).apic_timer_irqs); seq_putc(p, '\n'); #endif seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); @@ -259,3 +258,45 @@ skip: } return 0; } + +#ifdef CONFIG_HOTPLUG_CPU +#include + +void fixup_irqs(cpumask_t map) +{ + unsigned int irq; + static int warned; + + for (irq = 0; irq < NR_IRQS; irq++) { + cpumask_t mask; + if (irq == 2) + continue; + + cpus_and(mask, irq_affinity[irq], map); + if (any_online_cpu(mask) == NR_CPUS) { + printk("Breaking affinity for irq %i\n", irq); + mask = map; + } + if (irq_desc[irq].handler->set_affinity) + irq_desc[irq].handler->set_affinity(irq, mask); + else if (irq_desc[irq].action && !(warned++)) + printk("Cannot set affinity for irq %i\n", irq); + } + +#if 0 + barrier(); + /* Ingo Molnar says: "after the IO-APIC masks have been redirected + [note the nop - the interrupt-enable boundary on x86 is two + instructions from sti] - to flush out pending hardirqs and + IPIs. After this point nothing is supposed to reach this CPU." */ + __asm__ __volatile__("sti; nop; cli"); + barrier(); +#else + /* That doesn't seem sufficient. Give it 1ms. */ + local_irq_enable(); + mdelay(1); + local_irq_disable(); +#endif +} +#endif + diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index aea2ce1145df..c1b11e8df60b 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -13,6 +13,7 @@ #include +#include #include #include #include @@ -55,6 +56,9 @@ #include #include +#include +#include + asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); static int hlt_counter; @@ -143,14 +147,44 @@ static void poll_idle (void) } } +#ifdef CONFIG_HOTPLUG_CPU +#include +/* We don't actually take CPU down, just spin without interrupts. */ +static inline void play_dead(void) +{ + /* Ack it */ + __get_cpu_var(cpu_state) = CPU_DEAD; + + /* We shouldn't have to disable interrupts while dead, but + * some interrupts just don't seem to go away, and this makes + * it "work" for testing purposes. */ + /* Death loop */ + while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) + cpu_relax(); + + local_irq_disable(); + __flush_tlb_all(); + cpu_set(smp_processor_id(), cpu_online_map); + enable_APIC_timer(); + local_irq_enable(); +} +#else +static inline void play_dead(void) +{ + BUG(); +} +#endif /* CONFIG_HOTPLUG_CPU */ + /* * The idle thread. There's no useful work to be * done, so just try to conserve power and have a * low exit latency (ie sit in a loop waiting for * somebody to say that they'd like to reschedule) */ -void cpu_idle (void) +void cpu_idle(void) { + int cpu = raw_smp_processor_id(); + /* endless idle loop with no priority at all */ while (1) { while (!need_resched()) { @@ -165,6 +199,9 @@ void cpu_idle (void) if (!idle) idle = default_idle; + if (cpu_is_offline(cpu)) + play_dead(); + __get_cpu_var(irq_stat).idle_timestamp = jiffies; idle(); } diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c index 68be7d0c7238..35f521612b20 100644 --- a/arch/i386/kernel/smp.c +++ b/arch/i386/kernel/smp.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -164,7 +165,7 @@ void send_IPI_mask_bitmask(cpumask_t cpumask, int vector) unsigned long flags; local_irq_save(flags); - + WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]); /* * Wait for idle. */ @@ -346,21 +347,21 @@ out: static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, unsigned long va) { - cpumask_t tmp; /* * A couple of (to be removed) sanity checks: * - * - we do not send IPIs to not-yet booted CPUs. * - current CPU must not be in mask * - mask must exist :) */ BUG_ON(cpus_empty(cpumask)); - - cpus_and(tmp, cpumask, cpu_online_map); - BUG_ON(!cpus_equal(cpumask, tmp)); BUG_ON(cpu_isset(smp_processor_id(), cpumask)); BUG_ON(!mm); + /* If a CPU which we ran on has gone down, OK. */ + cpus_and(cpumask, cpumask, cpu_online_map); + if (cpus_empty(cpumask)) + return; + /* * i'm not happy about this global shared spinlock in the * MM hot path, but we'll see how contended it is. @@ -476,6 +477,7 @@ void flush_tlb_all(void) */ void smp_send_reschedule(int cpu) { + WARN_ON(cpu_is_offline(cpu)); send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); } @@ -516,10 +518,15 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic, */ { struct call_data_struct data; - int cpus = num_online_cpus()-1; + int cpus; - if (!cpus) + /* Holding any lock stops cpus from going down. */ + spin_lock(&call_lock); + cpus = num_online_cpus() - 1; + if (!cpus) { + spin_unlock(&call_lock); return 0; + } /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); @@ -531,7 +538,6 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic, if (wait) atomic_set(&data.finished, 0); - spin_lock(&call_lock); call_data = &data; mb(); diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index c20d96d5c15c..ad74a46e9ef0 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -44,6 +44,9 @@ #include #include #include +#include +#include +#include #include #include @@ -96,6 +99,9 @@ static int trampoline_exec; static void map_cpu_to_logical_apicid(void); +/* State of each CPU. */ +DEFINE_PER_CPU(int, cpu_state) = { 0 }; + /* * Currently trivial. Write the real->protected mode * bootstrap into the page concerned. The caller @@ -1119,6 +1125,9 @@ static void __init smp_boot_cpus(unsigned int max_cpus) who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */ void __init smp_prepare_cpus(unsigned int max_cpus) { + smp_commenced_mask = cpumask_of_cpu(0); + cpu_callin_map = cpumask_of_cpu(0); + mb(); smp_boot_cpus(max_cpus); } @@ -1128,20 +1137,99 @@ void __devinit smp_prepare_boot_cpu(void) cpu_set(smp_processor_id(), cpu_callout_map); } -int __devinit __cpu_up(unsigned int cpu) +#ifdef CONFIG_HOTPLUG_CPU + +/* must be called with the cpucontrol mutex held */ +static int __devinit cpu_enable(unsigned int cpu) { - /* This only works at boot for x86. See "rewrite" above. */ - if (cpu_isset(cpu, smp_commenced_mask)) { - local_irq_enable(); - return -ENOSYS; + /* get the target out of its holding state */ + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + wmb(); + + /* wait for the processor to ack it. timeout? */ + while (!cpu_online(cpu)) + cpu_relax(); + + fixup_irqs(cpu_online_map); + /* counter the disable in fixup_irqs() */ + local_irq_enable(); + return 0; +} + +int __cpu_disable(void) +{ + cpumask_t map = cpu_online_map; + int cpu = smp_processor_id(); + + /* + * Perhaps use cpufreq to drop frequency, but that could go + * into generic code. + * + * We won't take down the boot processor on i386 due to some + * interrupts only being able to be serviced by the BSP. + * Especially so if we're not using an IOAPIC -zwane + */ + if (cpu == 0) + return -EBUSY; + + /* We enable the timer again on the exit path of the death loop */ + disable_APIC_timer(); + /* Allow any queued timer interrupts to get serviced */ + local_irq_enable(); + mdelay(1); + local_irq_disable(); + + cpu_clear(cpu, map); + fixup_irqs(map); + /* It's now safe to remove this processor from the online map */ + cpu_clear(cpu, cpu_online_map); + return 0; +} + +void __cpu_die(unsigned int cpu) +{ + /* We don't do anything here: idle task is faking death itself. */ + unsigned int i; + + for (i = 0; i < 10; i++) { + /* They ack this in play_dead by setting CPU_DEAD */ + if (per_cpu(cpu_state, cpu) == CPU_DEAD) + return; + current->state = TASK_UNINTERRUPTIBLE; + schedule_timeout(HZ/10); } + printk(KERN_ERR "CPU %u didn't die...\n", cpu); +} +#else /* ... !CONFIG_HOTPLUG_CPU */ +int __cpu_disable(void) +{ + return -ENOSYS; +} +void __cpu_die(unsigned int cpu) +{ + /* We said "no" in __cpu_disable */ + BUG(); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +int __devinit __cpu_up(unsigned int cpu) +{ /* In case one didn't come up */ if (!cpu_isset(cpu, cpu_callin_map)) { + printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu); local_irq_enable(); return -EIO; } +#ifdef CONFIG_HOTPLUG_CPU + /* Already up, and in cpu_quiescent now? */ + if (cpu_isset(cpu, smp_commenced_mask)) { + cpu_enable(cpu); + return 0; + } +#endif + local_irq_enable(); /* Unleash the CPU! */ cpu_set(cpu, smp_commenced_mask); diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index e4d4e2162c7a..207ea8ba7169 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -625,6 +625,14 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code) nmi_enter(); cpu = smp_processor_id(); + +#ifdef CONFIG_HOTPLUG_CPU + if (!cpu_online(cpu)) { + nmi_exit(); + return; + } +#endif + ++nmi_count(cpu); if (!nmi_callback(regs, cpu)) -- cgit v1.2.2 From 67664c8f7e74def5adf66298a1245d82af72db2c Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Sat, 25 Jun 2005 14:54:52 -0700 Subject: [PATCH] i386: Dont use IPI broadcast when using cpu hotplug. This patch introduces a startup parameter no_broadcast. When we enable CONFIG_HOTPLUG_CPU, we dont want to use broadcast shortcut as it has ill effects on a offline cpu. If we issue broadcast, the IPI is also delivered to offline cpus, or partially up cpu causing stale IPI's to be handled, which is a problem and can cause undesirable effects. Introduces a new startup cmdline option no_ipi_broadcast, that can be switched at cmdline if necessary. Signed-off-by: Ashok Raj Acked-by: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/mach-default/setup.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'arch/i386') diff --git a/arch/i386/mach-default/setup.c b/arch/i386/mach-default/setup.c index 0aa08eaa8932..e5a1a83d09ef 100644 --- a/arch/i386/mach-default/setup.c +++ b/arch/i386/mach-default/setup.c @@ -10,6 +10,14 @@ #include #include +#ifdef CONFIG_HOTPLUG_CPU +#define DEFAULT_SEND_IPI (1) +#else +#define DEFAULT_SEND_IPI (0) +#endif + +int no_broadcast=DEFAULT_SEND_IPI; + /** * pre_intr_init_hook - initialisation prior to setting up interrupt vectors * @@ -104,3 +112,22 @@ void __init mca_nmi_hook(void) printk("NMI generated from unknown source!\n"); } #endif + +static __init int no_ipi_broadcast(char *str) +{ + get_option(&str, &no_broadcast); + printk ("Using %s mode\n", no_broadcast ? "No IPI Broadcast" : + "IPI Broadcast"); + return 1; +} + +__setup("no_ipi_broadcast", no_ipi_broadcast); + +static int __init print_ipi_mode(void) +{ + printk ("Using IPI %s mode\n", no_broadcast ? "No-Shortcut" : + "Shortcut"); + return 0; +} + +late_initcall(print_ipi_mode); -- cgit v1.2.2 From 6fe940d6c300886de4ff1454d8ffd363172af433 Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:54:53 -0700 Subject: [PATCH] sep initializing rework Make SEP init per-cpu, so it is hotplug safe. Signed-off-by: Li Shaohua Signed-off-by: Ashok Raj Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/cpu/common.c | 3 +++ arch/i386/kernel/smp.c | 10 ++++++++++ arch/i386/kernel/smpboot.c | 11 +++++++++++ arch/i386/kernel/sysenter.c | 12 +++++++----- arch/i386/power/cpu.c | 6 +++--- 5 files changed, 34 insertions(+), 8 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index b9954248d0aa..d58e169fbdbb 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -432,6 +432,9 @@ void __init identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_MCE mcheck_init(c); #endif + if (c == &boot_cpu_data) + sysenter_setup(); + enable_sep_cpu(); } #ifdef CONFIG_X86_HT diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c index 35f521612b20..cec4bde67161 100644 --- a/arch/i386/kernel/smp.c +++ b/arch/i386/kernel/smp.c @@ -495,6 +495,16 @@ struct call_data_struct { int wait; }; +void lock_ipi_call_lock(void) +{ + spin_lock_irq(&call_lock); +} + +void unlock_ipi_call_lock(void) +{ + spin_unlock_irq(&call_lock); +} + static struct call_data_struct * call_data; /* diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index ad74a46e9ef0..c5517f332309 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -449,7 +449,18 @@ static void __init start_secondary(void *unused) * the local TLBs too. */ local_flush_tlb(); + + /* + * We need to hold call_lock, so there is no inconsistency + * between the time smp_call_function() determines number of + * IPI receipients, and the time when the determination is made + * for which cpus receive the IPI. Holding this + * lock helps us to not include this cpu in a currently in progress + * smp_call_function(). + */ + lock_ipi_call_lock(); cpu_set(smp_processor_id(), cpu_online_map); + unlock_ipi_call_lock(); /* We can take interrupts now: we're officially "up". */ local_irq_enable(); diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c index 960d8bd137d0..0bada1870bdf 100644 --- a/arch/i386/kernel/sysenter.c +++ b/arch/i386/kernel/sysenter.c @@ -21,11 +21,16 @@ extern asmlinkage void sysenter_entry(void); -void enable_sep_cpu(void *info) +void enable_sep_cpu(void) { int cpu = get_cpu(); struct tss_struct *tss = &per_cpu(init_tss, cpu); + if (!boot_cpu_has(X86_FEATURE_SEP)) { + put_cpu(); + return; + } + tss->ss1 = __KERNEL_CS; tss->esp1 = sizeof(struct tss_struct) + (unsigned long) tss; wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); @@ -41,7 +46,7 @@ void enable_sep_cpu(void *info) extern const char vsyscall_int80_start, vsyscall_int80_end; extern const char vsyscall_sysenter_start, vsyscall_sysenter_end; -static int __init sysenter_setup(void) +int __init sysenter_setup(void) { void *page = (void *)get_zeroed_page(GFP_ATOMIC); @@ -58,8 +63,5 @@ static int __init sysenter_setup(void) &vsyscall_sysenter_start, &vsyscall_sysenter_end - &vsyscall_sysenter_start); - on_each_cpu(enable_sep_cpu, NULL, 1, 1); return 0; } - -__initcall(sysenter_setup); diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c index 6f521cf19a13..d099d01461f4 100644 --- a/arch/i386/power/cpu.c +++ b/arch/i386/power/cpu.c @@ -22,9 +22,11 @@ #include #include #include + #include #include #include +#include static struct saved_context saved_context; @@ -33,8 +35,6 @@ unsigned long saved_context_esp, saved_context_ebp; unsigned long saved_context_esi, saved_context_edi; unsigned long saved_context_eflags; -extern void enable_sep_cpu(void *); - void __save_processor_state(struct saved_context *ctxt) { kernel_fpu_begin(); @@ -136,7 +136,7 @@ void __restore_processor_state(struct saved_context *ctxt) * sysenter MSRs */ if (boot_cpu_has(X86_FEATURE_SEP)) - enable_sep_cpu(NULL); + enable_sep_cpu(); fix_processor_context(); do_fpu_end(); -- cgit v1.2.2 From d720803a9365d360b3e5ea02033f0c11b5b1226a Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:54:54 -0700 Subject: [PATCH] sibling map initializing rework Make sibling map init per-cpu. Hotplug CPU may change the map at runtime. Signed-off-by: Li Shaohua Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/smpboot.c | 97 ++++++++++++++++++++++++---------------------- 1 file changed, 50 insertions(+), 47 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index c5517f332309..09b4ceb832b2 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -66,11 +66,21 @@ int smp_num_siblings = 1; #ifdef CONFIG_X86_HT EXPORT_SYMBOL(smp_num_siblings); #endif -int phys_proc_id[NR_CPUS]; /* Package ID of each logical CPU */ + +/* Package ID of each logical CPU */ +int phys_proc_id[NR_CPUS] = {[0 ... NR_CPUS-1] = BAD_APICID}; EXPORT_SYMBOL(phys_proc_id); -int cpu_core_id[NR_CPUS]; /* Core ID of each logical CPU */ + +/* Core ID of each logical CPU */ +int cpu_core_id[NR_CPUS] = {[0 ... NR_CPUS-1] = BAD_APICID}; EXPORT_SYMBOL(cpu_core_id); +cpumask_t cpu_sibling_map[NR_CPUS]; +EXPORT_SYMBOL(cpu_sibling_map); + +cpumask_t cpu_core_map[NR_CPUS]; +EXPORT_SYMBOL(cpu_core_map); + /* bitmap of online cpus */ cpumask_t cpu_online_map; EXPORT_SYMBOL(cpu_online_map); @@ -423,6 +433,38 @@ static void __init smp_callin(void) static int cpucount; +static inline void +set_cpu_sibling_map(int cpu) +{ + int i; + + if (smp_num_siblings > 1) { + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_isset(i, cpu_callout_map)) + continue; + if (cpu_core_id[cpu] == cpu_core_id[i]) { + cpu_set(i, cpu_sibling_map[cpu]); + cpu_set(cpu, cpu_sibling_map[i]); + } + } + } else { + cpu_set(cpu, cpu_sibling_map[cpu]); + } + + if (current_cpu_data.x86_num_cores > 1) { + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_isset(i, cpu_callout_map)) + continue; + if (phys_proc_id[cpu] == phys_proc_id[i]) { + cpu_set(i, cpu_core_map[cpu]); + cpu_set(cpu, cpu_core_map[i]); + } + } + } else { + cpu_core_map[cpu] = cpu_sibling_map[cpu]; + } +} + /* * Activate a secondary processor. */ @@ -450,6 +492,10 @@ static void __init start_secondary(void *unused) */ local_flush_tlb(); + /* This must be done before setting cpu_online_map */ + set_cpu_sibling_map(raw_smp_processor_id()); + wmb(); + /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of @@ -912,13 +958,6 @@ void *xquad_portio; EXPORT_SYMBOL(xquad_portio); #endif -cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned; -#ifdef CONFIG_X86_HT -EXPORT_SYMBOL(cpu_sibling_map); -#endif -cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned; -EXPORT_SYMBOL(cpu_core_map); - static void __init smp_boot_cpus(unsigned int max_cpus) { int apicid, cpu, bit, kicked; @@ -1082,44 +1121,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus) cpus_clear(cpu_core_map[cpu]); } - for (cpu = 0; cpu < NR_CPUS; cpu++) { - struct cpuinfo_x86 *c = cpu_data + cpu; - int siblings = 0; - int i; - if (!cpu_isset(cpu, cpu_callout_map)) - continue; - - if (smp_num_siblings > 1) { - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_isset(i, cpu_callout_map)) - continue; - if (cpu_core_id[cpu] == cpu_core_id[i]) { - siblings++; - cpu_set(i, cpu_sibling_map[cpu]); - } - } - } else { - siblings++; - cpu_set(cpu, cpu_sibling_map[cpu]); - } - - if (siblings != smp_num_siblings) { - printk(KERN_WARNING "WARNING: %d siblings found for CPU%d, should be %d\n", siblings, cpu, smp_num_siblings); - smp_num_siblings = siblings; - } - - if (c->x86_num_cores > 1) { - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_isset(i, cpu_callout_map)) - continue; - if (phys_proc_id[cpu] == phys_proc_id[i]) { - cpu_set(i, cpu_core_map[cpu]); - } - } - } else { - cpu_core_map[cpu] = cpu_sibling_map[cpu]; - } - } + cpu_set(0, cpu_sibling_map[0]); + cpu_set(0, cpu_core_map[0]); smpboot_setup_io_apic(); -- cgit v1.2.2 From 0bb3184df537002a742bafddf3f4fb482b7fe610 Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:54:55 -0700 Subject: [PATCH] init call cleanup Trival patch for CPU hotplug. In CPU identify part, only did cleaup for intel CPUs. Need do for other CPUs if they support S3 SMP. Signed-off-by: Li Shaohua Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/apic.c | 14 +++++++------- arch/i386/kernel/cpu/common.c | 30 +++++++++++++++--------------- arch/i386/kernel/cpu/intel.c | 12 ++++++------ arch/i386/kernel/cpu/intel_cacheinfo.c | 4 ++-- arch/i386/kernel/cpu/mcheck/mce.c | 2 +- arch/i386/kernel/cpu/mcheck/p5.c | 2 +- arch/i386/kernel/process.c | 2 +- arch/i386/kernel/setup.c | 2 +- arch/i386/kernel/smpboot.c | 18 +++++++++--------- arch/i386/kernel/timers/timer_tsc.c | 2 +- 10 files changed, 44 insertions(+), 44 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index a28a088f3e75..b905d7bb9a0d 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -364,7 +364,7 @@ void __init init_bsp_APIC(void) apic_write_around(APIC_LVT1, value); } -void __init setup_local_APIC (void) +void __devinit setup_local_APIC(void) { unsigned long oldvalue, value, ver, maxlvt; @@ -635,7 +635,7 @@ static struct sys_device device_lapic = { .cls = &lapic_sysclass, }; -static void __init apic_pm_activate(void) +static void __devinit apic_pm_activate(void) { apic_pm_state.active = 1; } @@ -856,7 +856,7 @@ fake_ioapic_page: * but we do not accept timer interrupts yet. We only allow the BP * to calibrate. */ -static unsigned int __init get_8254_timer_count(void) +static unsigned int __devinit get_8254_timer_count(void) { extern spinlock_t i8253_lock; unsigned long flags; @@ -875,7 +875,7 @@ static unsigned int __init get_8254_timer_count(void) } /* next tick in 8254 can be caught by catching timer wraparound */ -static void __init wait_8254_wraparound(void) +static void __devinit wait_8254_wraparound(void) { unsigned int curr_count, prev_count; @@ -895,7 +895,7 @@ static void __init wait_8254_wraparound(void) * Default initialization for 8254 timers. If we use other timers like HPET, * we override this later */ -void (*wait_timer_tick)(void) __initdata = wait_8254_wraparound; +void (*wait_timer_tick)(void) __devinitdata = wait_8254_wraparound; /* * This function sets up the local APIC timer, with a timeout of @@ -931,7 +931,7 @@ static void __setup_APIC_LVTT(unsigned int clocks) apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR); } -static void __init setup_APIC_timer(unsigned int clocks) +static void __devinit setup_APIC_timer(unsigned int clocks) { unsigned long flags; @@ -1044,7 +1044,7 @@ void __init setup_boot_APIC_clock(void) local_irq_enable(); } -void __init setup_secondary_APIC_clock(void) +void __devinit setup_secondary_APIC_clock(void) { setup_APIC_timer(calibration_result); } diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index d58e169fbdbb..aac74758caf4 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -24,9 +24,9 @@ EXPORT_PER_CPU_SYMBOL(cpu_gdt_table); DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack); -static int cachesize_override __initdata = -1; -static int disable_x86_fxsr __initdata = 0; -static int disable_x86_serial_nr __initdata = 1; +static int cachesize_override __devinitdata = -1; +static int disable_x86_fxsr __devinitdata = 0; +static int disable_x86_serial_nr __devinitdata = 1; struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; @@ -59,7 +59,7 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -int __init get_model_name(struct cpuinfo_x86 *c) +int __devinit get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; char *p, *q; @@ -89,7 +89,7 @@ int __init get_model_name(struct cpuinfo_x86 *c) } -void __init display_cacheinfo(struct cpuinfo_x86 *c) +void __devinit display_cacheinfo(struct cpuinfo_x86 *c) { unsigned int n, dummy, ecx, edx, l2size; @@ -130,7 +130,7 @@ void __init display_cacheinfo(struct cpuinfo_x86 *c) /* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */ /* Look up CPU names by table lookup. */ -static char __init *table_lookup_model(struct cpuinfo_x86 *c) +static char __devinit *table_lookup_model(struct cpuinfo_x86 *c) { struct cpu_model_info *info; @@ -151,7 +151,7 @@ static char __init *table_lookup_model(struct cpuinfo_x86 *c) } -void __init get_cpu_vendor(struct cpuinfo_x86 *c, int early) +void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) { char *v = c->x86_vendor_id; int i; @@ -202,7 +202,7 @@ static inline int flag_is_changeable_p(u32 flag) /* Probe for the CPUID instruction */ -static int __init have_cpuid_p(void) +static int __devinit have_cpuid_p(void) { return flag_is_changeable_p(X86_EFLAGS_ID); } @@ -249,7 +249,7 @@ static void __init early_cpu_detect(void) #endif } -void __init generic_identify(struct cpuinfo_x86 * c) +void __devinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; int junk; @@ -296,7 +296,7 @@ void __init generic_identify(struct cpuinfo_x86 * c) } } -static void __init squash_the_stupid_serial_number(struct cpuinfo_x86 *c) +static void __devinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) { /* Disable processor serial number */ @@ -324,7 +324,7 @@ __setup("serialnumber", x86_serial_nr_setup); /* * This does the hard work of actually picking apart the CPU stuff... */ -void __init identify_cpu(struct cpuinfo_x86 *c) +void __devinit identify_cpu(struct cpuinfo_x86 *c) { int i; @@ -438,7 +438,7 @@ void __init identify_cpu(struct cpuinfo_x86 *c) } #ifdef CONFIG_X86_HT -void __init detect_ht(struct cpuinfo_x86 *c) +void __devinit detect_ht(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; int index_msb, tmp; @@ -493,7 +493,7 @@ void __init detect_ht(struct cpuinfo_x86 *c) } #endif -void __init print_cpu_info(struct cpuinfo_x86 *c) +void __devinit print_cpu_info(struct cpuinfo_x86 *c) { char *vendor = NULL; @@ -516,7 +516,7 @@ void __init print_cpu_info(struct cpuinfo_x86 *c) printk("\n"); } -cpumask_t cpu_initialized __initdata = CPU_MASK_NONE; +cpumask_t cpu_initialized __devinitdata = CPU_MASK_NONE; /* This is hacky. :) * We're emulating future behavior. @@ -563,7 +563,7 @@ void __init early_cpu_init(void) * and IDT. We reload them nevertheless, this function acts as a * 'CPU state barrier', nothing should get across. */ -void __init cpu_init (void) +void __devinit cpu_init(void) { int cpu = smp_processor_id(); struct tss_struct * t = &per_cpu(init_tss, cpu); diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c index 121aa2176e69..96a75d045835 100644 --- a/arch/i386/kernel/cpu/intel.c +++ b/arch/i386/kernel/cpu/intel.c @@ -28,7 +28,7 @@ extern int trap_init_f00f_bug(void); struct movsl_mask movsl_mask; #endif -void __init early_intel_workaround(struct cpuinfo_x86 *c) +void __devinit early_intel_workaround(struct cpuinfo_x86 *c) { if (c->x86_vendor != X86_VENDOR_INTEL) return; @@ -43,7 +43,7 @@ void __init early_intel_workaround(struct cpuinfo_x86 *c) * This is called before we do cpu ident work */ -int __init ppro_with_ram_bug(void) +int __devinit ppro_with_ram_bug(void) { /* Uses data from early_cpu_detect now */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && @@ -61,7 +61,7 @@ int __init ppro_with_ram_bug(void) * P4 Xeon errata 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ -static void __init Intel_errata_workarounds(struct cpuinfo_x86 *c) +static void __devinit Intel_errata_workarounds(struct cpuinfo_x86 *c) { unsigned long lo, hi; @@ -80,7 +80,7 @@ static void __init Intel_errata_workarounds(struct cpuinfo_x86 *c) /* * find out the number of processor cores on the die */ -static int __init num_cpu_cores(struct cpuinfo_x86 *c) +static int __devinit num_cpu_cores(struct cpuinfo_x86 *c) { unsigned int eax; @@ -98,7 +98,7 @@ static int __init num_cpu_cores(struct cpuinfo_x86 *c) return 1; } -static void __init init_intel(struct cpuinfo_x86 *c) +static void __devinit init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; char *p = NULL; @@ -204,7 +204,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 * c, unsigned int size) return size; } -static struct cpu_dev intel_cpu_dev __initdata = { +static struct cpu_dev intel_cpu_dev __devinitdata = { .c_vendor = "Intel", .c_ident = { "GenuineIntel" }, .c_models = { diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index a710dc4eb20e..1d768b263269 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -28,7 +28,7 @@ struct _cache_table }; /* all the cache descriptor types we care about (no TLB or trace cache entries) */ -static struct _cache_table cache_table[] __initdata = +static struct _cache_table cache_table[] __devinitdata = { { 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */ { 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */ @@ -160,7 +160,7 @@ static int __init find_num_cache_leaves(void) return retval; } -unsigned int __init init_intel_cacheinfo(struct cpuinfo_x86 *c) +unsigned int __devinit init_intel_cacheinfo(struct cpuinfo_x86 *c) { unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */ unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c index bf6d1aefafc0..7218a7341fbc 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.c +++ b/arch/i386/kernel/cpu/mcheck/mce.c @@ -31,7 +31,7 @@ static fastcall void unexpected_machine_check(struct pt_regs * regs, long error_ void fastcall (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; /* This has to be run for each processor */ -void __init mcheck_init(struct cpuinfo_x86 *c) +void __devinit mcheck_init(struct cpuinfo_x86 *c) { if (mce_disabled==1) return; diff --git a/arch/i386/kernel/cpu/mcheck/p5.c b/arch/i386/kernel/cpu/mcheck/p5.c index c45a1b485c80..ec0614cd2925 100644 --- a/arch/i386/kernel/cpu/mcheck/p5.c +++ b/arch/i386/kernel/cpu/mcheck/p5.c @@ -29,7 +29,7 @@ static fastcall void pentium_machine_check(struct pt_regs * regs, long error_cod } /* Set up machine check reporting for processors with Intel style MCE */ -void __init intel_p5_mcheck_init(struct cpuinfo_x86 *c) +void __devinit intel_p5_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index c1b11e8df60b..e06f2dc7123d 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -260,7 +260,7 @@ static void mwait_idle(void) } } -void __init select_idle_routine(const struct cpuinfo_x86 *c) +void __devinit select_idle_routine(const struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_MWAIT)) { printk("monitor/mwait feature present.\n"); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 30406fd0b64c..cba67e4ba0af 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -60,7 +60,7 @@ address, and must not be in the .bss segment! */ unsigned long init_pg_tables_end __initdata = ~0UL; -int disable_pse __initdata = 0; +int disable_pse __devinitdata = 0; /* * Machine setup.. diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 09b4ceb832b2..fb0b200d1d85 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -59,7 +59,7 @@ #include /* Set if we find a B stepping CPU */ -static int __initdata smp_b_stepping; +static int __devinitdata smp_b_stepping; /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -118,7 +118,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 }; * has made sure it's suitably aligned. */ -static unsigned long __init setup_trampoline(void) +static unsigned long __devinit setup_trampoline(void) { memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data); return virt_to_phys(trampoline_base); @@ -148,7 +148,7 @@ void __init smp_alloc_memory(void) * a given CPU */ -static void __init smp_store_cpu_info(int id) +static void __devinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = cpu_data + id; @@ -342,7 +342,7 @@ extern void calibrate_delay(void); static atomic_t init_deasserted; -static void __init smp_callin(void) +static void __devinit smp_callin(void) { int cpuid, phys_id; unsigned long timeout; @@ -468,7 +468,7 @@ set_cpu_sibling_map(int cpu) /* * Activate a secondary processor. */ -static void __init start_secondary(void *unused) +static void __devinit start_secondary(void *unused) { /* * Dont put anything before smp_callin(), SMP @@ -521,7 +521,7 @@ static void __init start_secondary(void *unused) * from the task structure * This function must not return. */ -void __init initialize_secondary(void) +void __devinit initialize_secondary(void) { /* * We don't actually need to load the full TSS, @@ -635,7 +635,7 @@ static inline void __inquire_remote_apic(int apicid) * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. */ -static int __init +static int __devinit wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) { unsigned long send_status = 0, accept_status = 0; @@ -681,7 +681,7 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) #endif /* WAKE_SECONDARY_VIA_NMI */ #ifdef WAKE_SECONDARY_VIA_INIT -static int __init +static int __devinit wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) { unsigned long send_status = 0, accept_status = 0; @@ -817,7 +817,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) extern cpumask_t cpu_initialized; -static int __init do_boot_cpu(int apicid) +static int __devinit do_boot_cpu(int apicid) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c index 54c36b182021..f46e625bab67 100644 --- a/arch/i386/kernel/timers/timer_tsc.c +++ b/arch/i386/kernel/timers/timer_tsc.c @@ -33,7 +33,7 @@ static struct timer_opts timer_tsc; static inline void cpufreq_delayed_get(void); -int tsc_disable __initdata = 0; +int tsc_disable __devinitdata = 0; extern spinlock_t i8253_lock; -- cgit v1.2.2 From e1367daf3eed5cd619ee88c9907e1e6ddaa58406 Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:54:56 -0700 Subject: [PATCH] cpu state clean after hot remove Clean CPU states in order to reuse smp boot code for CPU hotplug. Signed-off-by: Li Shaohua Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/cpu/common.c | 12 +++ arch/i386/kernel/irq.c | 5 ++ arch/i386/kernel/process.c | 20 +++-- arch/i386/kernel/smpboot.c | 175 ++++++++++++++++++++++++++++++++++-------- 4 files changed, 170 insertions(+), 42 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index aac74758caf4..2203a9d20212 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -651,3 +651,15 @@ void __devinit cpu_init(void) clear_used_math(); mxcsr_feature_mask_init(); } + +#ifdef CONFIG_HOTPLUG_CPU +void __devinit cpu_uninit(void) +{ + int cpu = raw_smp_processor_id(); + cpu_clear(cpu, cpu_initialized); + + /* lazy TLB state */ + per_cpu(cpu_tlbstate, cpu).state = 0; + per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm; +} +#endif diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c index af115004aec5..ce66dcc26d90 100644 --- a/arch/i386/kernel/irq.c +++ b/arch/i386/kernel/irq.c @@ -156,6 +156,11 @@ void irq_ctx_init(int cpu) cpu,hardirq_ctx[cpu],softirq_ctx[cpu]); } +void irq_ctx_exit(int cpu) +{ + hardirq_ctx[cpu] = NULL; +} + extern asmlinkage void __do_softirq(void); asmlinkage void do_softirq(void) diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index e06f2dc7123d..5f8cfa6b7940 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -152,21 +152,19 @@ static void poll_idle (void) /* We don't actually take CPU down, just spin without interrupts. */ static inline void play_dead(void) { + /* This must be done before dead CPU ack */ + cpu_exit_clear(); + wbinvd(); + mb(); /* Ack it */ __get_cpu_var(cpu_state) = CPU_DEAD; - /* We shouldn't have to disable interrupts while dead, but - * some interrupts just don't seem to go away, and this makes - * it "work" for testing purposes. */ - /* Death loop */ - while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) - cpu_relax(); - + /* + * With physical CPU hotplug, we should halt the cpu + */ local_irq_disable(); - __flush_tlb_all(); - cpu_set(smp_processor_id(), cpu_online_map); - enable_APIC_timer(); - local_irq_enable(); + while (1) + __asm__ __volatile__("hlt":::"memory"); } #else static inline void play_dead(void) diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index fb0b200d1d85..d66bf489a2e9 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -90,6 +90,12 @@ cpumask_t cpu_callout_map; EXPORT_SYMBOL(cpu_callout_map); static cpumask_t smp_commenced_mask; +/* TSC's upper 32 bits can't be written in eariler CPU (before prescott), there + * is no way to resync one AP against BP. TBD: for prescott and above, we + * should use IA64's algorithm + */ +static int __devinitdata tsc_sync_disabled; + /* Per CPU bogomips and other parameters */ struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; EXPORT_SYMBOL(cpu_data); @@ -427,7 +433,7 @@ static void __devinit smp_callin(void) /* * Synchronize the TSC with the BP */ - if (cpu_has_tsc && cpu_khz) + if (cpu_has_tsc && cpu_khz && !tsc_sync_disabled) synchronize_tsc_ap(); } @@ -507,6 +513,7 @@ static void __devinit start_secondary(void *unused) lock_ipi_call_lock(); cpu_set(smp_processor_id(), cpu_online_map); unlock_ipi_call_lock(); + per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; /* We can take interrupts now: we're officially "up". */ local_irq_enable(); @@ -816,8 +823,43 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) #endif /* WAKE_SECONDARY_VIA_INIT */ extern cpumask_t cpu_initialized; +static inline int alloc_cpu_id(void) +{ + cpumask_t tmp_map; + int cpu; + cpus_complement(tmp_map, cpu_present_map); + cpu = first_cpu(tmp_map); + if (cpu >= NR_CPUS) + return -ENODEV; + return cpu; +} + +#ifdef CONFIG_HOTPLUG_CPU +static struct task_struct * __devinitdata cpu_idle_tasks[NR_CPUS]; +static inline struct task_struct * alloc_idle_task(int cpu) +{ + struct task_struct *idle; + + if ((idle = cpu_idle_tasks[cpu]) != NULL) { + /* initialize thread_struct. we really want to avoid destroy + * idle tread + */ + idle->thread.esp = (unsigned long)(((struct pt_regs *) + (THREAD_SIZE + (unsigned long) idle->thread_info)) - 1); + init_idle(idle, cpu); + return idle; + } + idle = fork_idle(cpu); + + if (!IS_ERR(idle)) + cpu_idle_tasks[cpu] = idle; + return idle; +} +#else +#define alloc_idle_task(cpu) fork_idle(cpu) +#endif -static int __devinit do_boot_cpu(int apicid) +static int __devinit do_boot_cpu(int apicid, int cpu) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -826,16 +868,17 @@ static int __devinit do_boot_cpu(int apicid) { struct task_struct *idle; unsigned long boot_error; - int timeout, cpu; + int timeout; unsigned long start_eip; unsigned short nmi_high = 0, nmi_low = 0; - cpu = ++cpucount; + ++cpucount; + /* * We can't use kernel_thread since we must avoid to * reschedule the child. */ - idle = fork_idle(cpu); + idle = alloc_idle_task(cpu); if (IS_ERR(idle)) panic("failed fork for CPU %d", cpu); idle->thread.eip = (unsigned long) start_secondary; @@ -902,13 +945,16 @@ static int __devinit do_boot_cpu(int apicid) inquire_remote_apic(apicid); } } - x86_cpu_to_apicid[cpu] = apicid; + if (boot_error) { /* Try to put things back the way they were before ... */ unmap_cpu_to_logical_apicid(cpu); cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ cpucount--; + } else { + x86_cpu_to_apicid[cpu] = apicid; + cpu_set(cpu, cpu_present_map); } /* mark "stuck" area as not stuck */ @@ -917,6 +963,75 @@ static int __devinit do_boot_cpu(int apicid) return boot_error; } +#ifdef CONFIG_HOTPLUG_CPU +void cpu_exit_clear(void) +{ + int cpu = raw_smp_processor_id(); + + idle_task_exit(); + + cpucount --; + cpu_uninit(); + irq_ctx_exit(cpu); + + cpu_clear(cpu, cpu_callout_map); + cpu_clear(cpu, cpu_callin_map); + cpu_clear(cpu, cpu_present_map); + + cpu_clear(cpu, smp_commenced_mask); + unmap_cpu_to_logical_apicid(cpu); +} + +struct warm_boot_cpu_info { + struct completion *complete; + int apicid; + int cpu; +}; + +static void __devinit do_warm_boot_cpu(void *p) +{ + struct warm_boot_cpu_info *info = p; + do_boot_cpu(info->apicid, info->cpu); + complete(info->complete); +} + +int __devinit smp_prepare_cpu(int cpu) +{ + DECLARE_COMPLETION(done); + struct warm_boot_cpu_info info; + struct work_struct task; + int apicid, ret; + + lock_cpu_hotplug(); + apicid = x86_cpu_to_apicid[cpu]; + if (apicid == BAD_APICID) { + ret = -ENODEV; + goto exit; + } + + info.complete = &done; + info.apicid = apicid; + info.cpu = cpu; + INIT_WORK(&task, do_warm_boot_cpu, &info); + + tsc_sync_disabled = 1; + + /* init low mem mapping */ + memcpy(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, + sizeof(swapper_pg_dir[0]) * KERNEL_PGD_PTRS); + flush_tlb_all(); + schedule_work(&task); + wait_for_completion(&done); + + tsc_sync_disabled = 0; + zap_low_mappings(); + ret = 0; +exit: + unlock_cpu_hotplug(); + return ret; +} +#endif + static void smp_tune_scheduling (void) { unsigned long cachesize; /* kB */ @@ -1069,7 +1184,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus) if (max_cpus <= cpucount+1) continue; - if (do_boot_cpu(apicid)) + if (((cpu = alloc_cpu_id()) <= 0) || do_boot_cpu(apicid, cpu)) printk("CPU #%d not responding - cannot use it.\n", apicid); else @@ -1149,25 +1264,24 @@ void __devinit smp_prepare_boot_cpu(void) { cpu_set(smp_processor_id(), cpu_online_map); cpu_set(smp_processor_id(), cpu_callout_map); + cpu_set(smp_processor_id(), cpu_present_map); + per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; } #ifdef CONFIG_HOTPLUG_CPU - -/* must be called with the cpucontrol mutex held */ -static int __devinit cpu_enable(unsigned int cpu) +static void +remove_siblinginfo(int cpu) { - /* get the target out of its holding state */ - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; - wmb(); - - /* wait for the processor to ack it. timeout? */ - while (!cpu_online(cpu)) - cpu_relax(); - - fixup_irqs(cpu_online_map); - /* counter the disable in fixup_irqs() */ - local_irq_enable(); - return 0; + int sibling; + + for_each_cpu_mask(sibling, cpu_sibling_map[cpu]) + cpu_clear(cpu, cpu_sibling_map[sibling]); + for_each_cpu_mask(sibling, cpu_core_map[cpu]) + cpu_clear(cpu, cpu_core_map[sibling]); + cpus_clear(cpu_sibling_map[cpu]); + cpus_clear(cpu_core_map[cpu]); + phys_proc_id[cpu] = BAD_APICID; + cpu_core_id[cpu] = BAD_APICID; } int __cpu_disable(void) @@ -1193,6 +1307,8 @@ int __cpu_disable(void) mdelay(1); local_irq_disable(); + remove_siblinginfo(cpu); + cpu_clear(cpu, map); fixup_irqs(map); /* It's now safe to remove this processor from the online map */ @@ -1207,8 +1323,10 @@ void __cpu_die(unsigned int cpu) for (i = 0; i < 10; i++) { /* They ack this in play_dead by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) + if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + printk ("CPU %d is now offline\n", cpu); return; + } current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(HZ/10); } @@ -1236,15 +1354,8 @@ int __devinit __cpu_up(unsigned int cpu) return -EIO; } -#ifdef CONFIG_HOTPLUG_CPU - /* Already up, and in cpu_quiescent now? */ - if (cpu_isset(cpu, smp_commenced_mask)) { - cpu_enable(cpu); - return 0; - } -#endif - local_irq_enable(); + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; /* Unleash the CPU! */ cpu_set(cpu, smp_commenced_mask); while (!cpu_isset(cpu, cpu_online_map)) @@ -1258,10 +1369,12 @@ void __init smp_cpus_done(unsigned int max_cpus) setup_ioapic_dest(); #endif zap_low_mappings(); +#ifndef CONFIG_HOTPLUG_CPU /* * Disable executability of the SMP trampoline: */ set_kernel_exec((unsigned long)trampoline_base, trampoline_exec); +#endif } void __init smp_intr_init(void) -- cgit v1.2.2 From 76e4f660d9f4c6d1bb473f72be2988c35eaca948 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Sat, 25 Jun 2005 14:55:00 -0700 Subject: [PATCH] x86_64: CPU hotplug support Experimental CPU hotplug patch for x86_64 ----------------------------------------- This supports logical CPU online and offline. - Test with maxcpus=1, and then kick other cpu's off to test if init code is all cleaned up. CONFIG_SCHED_SMT works as well. - idle threads are forked on demand from keventd threads for clean startup TBD: 1. Not tested on a real NUMA machine (tested with numa=fake=2) 2. Handle ACPI pieces for physical hotplug support. Signed-off-by: Ashok Raj Acked-by: Andi Kleen Acked-by: Zwane Mwaikambo Signed-off-by: Shaohua.li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/mach-default/topology.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/mach-default/topology.c b/arch/i386/mach-default/topology.c index 5b3e8817dae8..23395fff35d1 100644 --- a/arch/i386/mach-default/topology.c +++ b/arch/i386/mach-default/topology.c @@ -73,12 +73,11 @@ static int __init topology_init(void) { int i; - for (i = 0; i < MAX_NUMNODES; i++) { - if (node_online(i)) - arch_register_node(i); - } - for (i = 0; i < NR_CPUS; i++) - if (cpu_possible(i)) arch_register_cpu(i); + for_each_online_node(i) + arch_register_node(i); + + for_each_cpu(i) + arch_register_cpu(i); return 0; } @@ -88,8 +87,8 @@ static int __init topology_init(void) { int i; - for (i = 0; i < NR_CPUS; i++) - if (cpu_possible(i)) arch_register_cpu(i); + for_each_cpu(i) + arch_register_cpu(i); return 0; } -- cgit v1.2.2 From 5a72e04df5470df0ec646029d31e5528167ab1a7 Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:55:06 -0700 Subject: [PATCH] suspend/resume SMP support Using CPU hotplug to support suspend/resume SMP. Both S3 and S4 use disable/enable_nonboot_cpus API. The S4 part is based on Pavel's original S4 SMP patch. Signed-off-by: Li Shaohua Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/cpu/mcheck/k7.c | 2 +- arch/i386/kernel/cpu/mcheck/mce.c | 2 +- arch/i386/kernel/cpu/mcheck/p4.c | 4 ++-- arch/i386/kernel/cpu/mcheck/p6.c | 2 +- arch/i386/kernel/cpu/mcheck/winchip.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/cpu/mcheck/k7.c b/arch/i386/kernel/cpu/mcheck/k7.c index 8df52e86c4d2..c4abe7657397 100644 --- a/arch/i386/kernel/cpu/mcheck/k7.c +++ b/arch/i386/kernel/cpu/mcheck/k7.c @@ -69,7 +69,7 @@ static fastcall void k7_machine_check(struct pt_regs * regs, long error_code) /* AMD K7 machine check is Intel like */ -void __init amd_mcheck_init(struct cpuinfo_x86 *c) +void __devinit amd_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c index 7218a7341fbc..2cf25d2ba0f1 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.c +++ b/arch/i386/kernel/cpu/mcheck/mce.c @@ -16,7 +16,7 @@ #include "mce.h" -int mce_disabled __initdata = 0; +int mce_disabled __devinitdata = 0; int nr_mce_banks; EXPORT_SYMBOL_GPL(nr_mce_banks); /* non-fatal.o */ diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c index 8b16ceb929b4..0abccb6fdf9e 100644 --- a/arch/i386/kernel/cpu/mcheck/p4.c +++ b/arch/i386/kernel/cpu/mcheck/p4.c @@ -78,7 +78,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs) } /* P4/Xeon Thermal regulation detect and init */ -static void __init intel_init_thermal(struct cpuinfo_x86 *c) +static void __devinit intel_init_thermal(struct cpuinfo_x86 *c) { u32 l, h; unsigned int cpu = smp_processor_id(); @@ -232,7 +232,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) } -void __init intel_p4_mcheck_init(struct cpuinfo_x86 *c) +void __devinit intel_p4_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/p6.c b/arch/i386/kernel/cpu/mcheck/p6.c index 46640f8c2494..f01b73f947e1 100644 --- a/arch/i386/kernel/cpu/mcheck/p6.c +++ b/arch/i386/kernel/cpu/mcheck/p6.c @@ -80,7 +80,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) } /* Set up machine check reporting for processors with Intel style MCE */ -void __init intel_p6_mcheck_init(struct cpuinfo_x86 *c) +void __devinit intel_p6_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/winchip.c b/arch/i386/kernel/cpu/mcheck/winchip.c index 753fa7acb984..7bae68fa168f 100644 --- a/arch/i386/kernel/cpu/mcheck/winchip.c +++ b/arch/i386/kernel/cpu/mcheck/winchip.c @@ -23,7 +23,7 @@ static fastcall void winchip_machine_check(struct pt_regs * regs, long error_cod } /* Set up machine check reporting on the Winchip C6 series */ -void __init winchip_mcheck_init(struct cpuinfo_x86 *c) +void __devinit winchip_mcheck_init(struct cpuinfo_x86 *c) { u32 lo, hi; machine_check_vector = winchip_machine_check; -- cgit v1.2.2 From 648be3188135add682349e86d46d07cc11c8eb57 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Sat, 25 Jun 2005 14:55:09 -0700 Subject: [PATCH] swsusp: kill config_pm_disk CONFIG_PM_DISK is long gone, but it still managed to survived at few places. Signed-off-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/defconfig | 1 - arch/i386/mm/init.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/defconfig b/arch/i386/defconfig index 28e620383799..ca07b95c06b8 100644 --- a/arch/i386/defconfig +++ b/arch/i386/defconfig @@ -126,7 +126,6 @@ CONFIG_HAVE_DEC_LOCK=y # CONFIG_PM=y CONFIG_SOFTWARE_SUSPEND=y -# CONFIG_PM_DISK is not set # # ACPI (Advanced Configuration and Power Interface) Support diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 3672e2ef51ae..12216b52e28b 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -352,7 +352,7 @@ static void __init pagetable_init (void) #endif } -#if defined(CONFIG_PM_DISK) || defined(CONFIG_SOFTWARE_SUSPEND) +#ifdef CONFIG_SOFTWARE_SUSPEND /* * Swap suspend & friends need this for resume because things like the intel-agp * driver might have split up a kernel 4MB mapping. -- cgit v1.2.2 From 8d783b3e02002bce8cf9d4e4a82922ee7e59b1e5 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Sat, 25 Jun 2005 14:55:14 -0700 Subject: [PATCH] swsusp: clean assembly parts This patch fixes register saving so that each register is only saved once, and adds missing saving of %cr8 on x86-64. Some reordering so that save/restore is more logical/safer (segment registers should be restored after gdt). Signed-off-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/power/cpu.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c index d099d01461f4..0e6b45b61251 100644 --- a/arch/i386/power/cpu.c +++ b/arch/i386/power/cpu.c @@ -44,7 +44,6 @@ void __save_processor_state(struct saved_context *ctxt) */ asm volatile ("sgdt %0" : "=m" (ctxt->gdt_limit)); asm volatile ("sidt %0" : "=m" (ctxt->idt_limit)); - asm volatile ("sldt %0" : "=m" (ctxt->ldt)); asm volatile ("str %0" : "=m" (ctxt->tr)); /* @@ -107,7 +106,6 @@ static void fix_processor_context(void) void __restore_processor_state(struct saved_context *ctxt) { - /* * control registers */ @@ -116,6 +114,13 @@ void __restore_processor_state(struct saved_context *ctxt) asm volatile ("movl %0, %%cr2" :: "r" (ctxt->cr2)); asm volatile ("movl %0, %%cr0" :: "r" (ctxt->cr0)); + /* + * now restore the descriptor tables to their proper values + * ltr is done i fix_processor_context(). + */ + asm volatile ("lgdt %0" :: "m" (ctxt->gdt_limit)); + asm volatile ("lidt %0" :: "m" (ctxt->idt_limit)); + /* * segment registers */ @@ -124,14 +129,6 @@ void __restore_processor_state(struct saved_context *ctxt) asm volatile ("movw %0, %%gs" :: "r" (ctxt->gs)); asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss)); - /* - * now restore the descriptor tables to their proper values - * ltr is done i fix_processor_context(). - */ - asm volatile ("lgdt %0" :: "m" (ctxt->gdt_limit)); - asm volatile ("lidt %0" :: "m" (ctxt->idt_limit)); - asm volatile ("lldt %0" :: "m" (ctxt->ldt)); - /* * sysenter MSRs */ -- cgit v1.2.2 From cc19ca86a023fcd552c78e77a7be6ce271f92a28 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 25 Jun 2005 14:57:36 -0700 Subject: [PATCH] consolidate PREEMPT options into kernel/Kconfig.preempt This patch consolidates the CONFIG_PREEMPT and CONFIG_PREEMPT_BKL preemption options into kernel/Kconfig.preempt. This, besides reducing source-code, also enables more centralized tweaking of preemption related options. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/Kconfig | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index b4cd11e58451..961ab20032f5 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -510,28 +510,7 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. -config PREEMPT - bool "Preemptible Kernel" - help - This option reduces the latency of the kernel when reacting to - real-time or interactive events by allowing a low priority process to - be preempted even if it is in kernel mode executing a system call. - This allows applications to run more reliably even when the system is - under load. - - Say Y here if you are building a kernel for a desktop, embedded - or real-time system. Say N if you are unsure. - -config PREEMPT_BKL - bool "Preempt The Big Kernel Lock" - depends on PREEMPT - default y - help - This option reduces the latency of the kernel by making the - big kernel lock preemptible. - - Say Y here if you are building a kernel for a desktop system. - Say N if you are unsure. +source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" -- cgit v1.2.2 From 9635b47d910223745258768418003580ef7dba17 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 25 Jun 2005 14:57:41 -0700 Subject: [PATCH] kexec: x86: local apic fix From: "Maciej W. Rozycki" Fix a kexec problem whcih causes local APIC detection failure. The problem is detect_init_APIC() is called early, before the command line have been processed. Therefore "lapic" (and "nolapic") have not been seen, yet. Signed-off-by: Maciej W. Rozycki Signed-off-by: Eric Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/apic.c | 25 +++++-------------------- arch/i386/kernel/setup.c | 11 +++++++++++ 2 files changed, 16 insertions(+), 20 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index b905d7bb9a0d..cf45bed96d08 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -40,6 +40,11 @@ #include "io_ports.h" +/* + * Knob to control our willingness to enable the local APIC. + */ +int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */ + /* * Debug level */ @@ -666,26 +671,6 @@ static void apic_pm_activate(void) { } * Original code written by Keir Fraser. */ -/* - * Knob to control our willingness to enable the local APIC. - */ -int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */ - -static int __init lapic_disable(char *str) -{ - enable_local_apic = -1; - clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); - return 0; -} -__setup("nolapic", lapic_disable); - -static int __init lapic_enable(char *str) -{ - enable_local_apic = 1; - return 0; -} -__setup("lapic", lapic_enable); - static int __init apic_set_verbosity(char *str) { if (strcmp("debug", str) == 0) diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index cba67e4ba0af..f1ad9fdeaad8 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -44,6 +44,7 @@ #include #include #include