From b02aae9cf52956dfe1bec73f77f81a3d05d3902b Mon Sep 17 00:00:00 2001 From: Rene Herman Date: Wed, 30 Jan 2008 13:30:05 +0100 Subject: [PATCH] x86: provide a DMI based port 0x80 I/O delay override. x86: provide a DMI based port 0x80 I/O delay override. Certain (HP) laptops experience trouble from our port 0x80 I/O delay writes. This patch provides for a DMI based switch to the "alternate diagnostic port" 0xed (as used by some BIOSes as well) for these. David P. Reed confirmed that port 0xed works for him and provides a proper delay. The symptoms of _not_ working are a hanging machine, with "hwclock" use being a direct trigger. Earlier versions of this attempted to simply use udelay(2), with the 2 being a value tested to be a nicely conservative upper-bound with help from many on the linux-kernel mailinglist but that approach has two problems. First, pre-loops_per_jiffy calibration (which is post PIT init while some implementations of the PIT are actually one of the historically problematic devices that need the delay) udelay() isn't particularly well-defined. We could initialise loops_per_jiffy conservatively (and based on CPU family so as to not unduly delay old machines) which would sort of work, but... Second, delaying isn't the only effect that a write to port 0x80 has. It's also a PCI posting barrier which some devices may be explicitly or implicitly relying on. Alan Cox did a survey and found evidence that additionally some drivers may be racy on SMP without the bus locking outb. Switching to an inb() makes the timing too unpredictable and as such, this DMI based switch should be the safest approach for now. Any more invasive changes should get more rigid testing first. It's moreover only very few machines with the problem and a DMI based hack seems to fit that situation. This also introduces a command-line parameter "io_delay" to override the DMI based choice again: io_delay= where "standard" means using the standard port 0x80 and "alternate" port 0xed. This retains the udelay method as a config (CONFIG_UDELAY_IO_DELAY) and command-line ("io_delay=udelay") choice for testing purposes as well. This does not change the io_delay() in the boot code which is using the same port 0x80 I/O delay but those do not appear to be a problem as David P. Reed reported the problem was already gone after using the udelay version. He moreover reported that booting with "acpi=off" also fixed things and seeing as how ACPI isn't touched until after this DMI based I/O port switch I believe it's safe to leave the ones in the boot code be. The DMI strings from David's HP Pavilion dv9000z are in there already and we need to get/verify the DMI info from other machines with the problem, notably the HP Pavilion dv6000z. This patch is partly based on earlier patches from Pavel Machek and David P. Reed. Signed-off-by: Rene Herman Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- Documentation/kernel-parameters.txt | 8 +++ arch/x86/Kconfig.debug | 9 +++ arch/x86/boot/compressed/misc_32.c | 8 +-- arch/x86/boot/compressed/misc_64.c | 8 +-- arch/x86/kernel/Makefile_32 | 2 +- arch/x86/kernel/Makefile_64 | 2 +- arch/x86/kernel/io_delay.c | 106 ++++++++++++++++++++++++++++ arch/x86/kernel/setup_32.c | 2 + arch/x86/kernel/setup_64.c | 2 + include/asm-x86/io_32.h | 8 ++- include/asm-x86/io_64.h | 33 ++++++--- 11 files changed, 165 insertions(+), 23 deletions(-) create mode 100644 arch/x86/kernel/io_delay.c diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 880f882160e..9e605605842 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -794,6 +794,14 @@ and is between 256 and 4096 characters. It is defined in the file for translation below 32 bit and if not available then look in the higher range. + io_delay= [X86-32,X86-64] I/O delay method + standard + Standard port 0x80 delay + alternate + Alternate port 0xed delay + udelay + Simple two microsecond delay + io7= [HW] IO7 for Marvel based alpha systems See comment before marvel_specify_io7 in arch/alpha/kernel/core_marvel.c. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 761ca7b5f12..40aba670fb3 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -112,4 +112,13 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. +config UDELAY_IO_DELAY + bool "Delay I/O through udelay instead of outb" + depends on DEBUG_KERNEL + help + Make inb_p/outb_p use udelay() based delays by default. Please note + that udelay() does not have the same bus-level side-effects that + the normal outb based delay does meaning this could cause drivers + to change behaviour and/or bugs to surface. + endmenu diff --git a/arch/x86/boot/compressed/misc_32.c b/arch/x86/boot/compressed/misc_32.c index b74d60d1b2f..288e16283ef 100644 --- a/arch/x86/boot/compressed/misc_32.c +++ b/arch/x86/boot/compressed/misc_32.c @@ -276,10 +276,10 @@ static void putstr(const char *s) RM_SCREEN_INFO.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ - outb_p(14, vidport); - outb_p(0xff & (pos >> 9), vidport+1); - outb_p(15, vidport); - outb_p(0xff & (pos >> 1), vidport+1); + outb(14, vidport); + outb(0xff & (pos >> 9), vidport+1); + outb(15, vidport); + outb(0xff & (pos >> 1), vidport+1); } static void* memset(void* s, int c, unsigned n) diff --git a/arch/x86/boot/compressed/misc_64.c b/arch/x86/boot/compressed/misc_64.c index 6ea015aa65e..43e5fcc37be 100644 --- a/arch/x86/boot/compressed/misc_64.c +++ b/arch/x86/boot/compressed/misc_64.c @@ -269,10 +269,10 @@ static void putstr(const char *s) RM_SCREEN_INFO.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ - outb_p(14, vidport); - outb_p(0xff & (pos >> 9), vidport+1); - outb_p(15, vidport); - outb_p(0xff & (pos >> 1), vidport+1); + outb(14, vidport); + outb(0xff & (pos >> 9), vidport+1); + outb(15, vidport); + outb(0xff & (pos >> 1), vidport+1); } static void* memset(void* s, int c, unsigned n) diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32 index a7bc93c2766..0cc1981d1e3 100644 --- a/arch/x86/kernel/Makefile_32 +++ b/arch/x86/kernel/Makefile_32 @@ -8,7 +8,7 @@ CPPFLAGS_vmlinux.lds += -Ui386 obj-y := process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \ ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \ pci-dma_32.o i386_ksyms_32.o i387_32.o bootflag.o e820_32.o\ - quirks.o i8237.o topology.o alternative.o i8253.o tsc_32.o + quirks.o i8237.o topology.o alternative.o i8253.o tsc_32.o io_delay.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += cpu/ diff --git a/arch/x86/kernel/Makefile_64 b/arch/x86/kernel/Makefile_64 index 5a88890d8ee..08a68f0d8fd 100644 --- a/arch/x86/kernel/Makefile_64 +++ b/arch/x86/kernel/Makefile_64 @@ -11,7 +11,7 @@ obj-y := process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \ x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \ setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \ pci-dma_64.o pci-nommu_64.o alternative.o hpet.o tsc_64.o bugs_64.o \ - i8253.o + i8253.o io_delay.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += cpu/ diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c new file mode 100644 index 00000000000..4d955e74b97 --- /dev/null +++ b/arch/x86/kernel/io_delay.c @@ -0,0 +1,106 @@ +/* + * I/O delay strategies for inb_p/outb_p + */ +#include +#include +#include +#include +#include +#include + +/* + * Allow for a DMI based override of port 0x80 needed for certain HP laptops + */ +#define IO_DELAY_PORT_STD 0x80 +#define IO_DELAY_PORT_ALT 0xed + +static void standard_io_delay(void) +{ + asm volatile ("outb %%al, %0" : : "N" (IO_DELAY_PORT_STD)); +} + +static void alternate_io_delay(void) +{ + asm volatile ("outb %%al, %0" : : "N" (IO_DELAY_PORT_ALT)); +} + +/* + * 2 usecs is an upper-bound for the outb delay but note that udelay doesn't + * have the bus-level side-effects that outb does + */ +#define IO_DELAY_USECS 2 + +/* + * High on a hill was a lonely goatherd + */ +static void udelay_io_delay(void) +{ + udelay(IO_DELAY_USECS); +} + +#ifndef CONFIG_UDELAY_IO_DELAY +static void (*io_delay)(void) = standard_io_delay; +#else +static void (*io_delay)(void) = udelay_io_delay; +#endif + +/* + * Paravirt wants native_io_delay to be a constant. + */ +void native_io_delay(void) +{ + io_delay(); +} +EXPORT_SYMBOL(native_io_delay); + +#ifndef CONFIG_UDELAY_IO_DELAY +static int __init dmi_alternate_io_delay_port(const struct dmi_system_id *id) +{ + printk(KERN_NOTICE "%s: using alternate I/O delay port\n", id->ident); + io_delay = alternate_io_delay; + return 0; +} + +static struct dmi_system_id __initdata alternate_io_delay_port_dmi_table[] = { + { + .callback = dmi_alternate_io_delay_port, + .ident = "HP Pavilion dv9000z", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B9") + } + }, + { + } +}; + +static int __initdata io_delay_override; + +void __init io_delay_init(void) +{ + if (!io_delay_override) + dmi_check_system(alternate_io_delay_port_dmi_table); +} +#endif + +static int __init io_delay_param(char *s) +{ + if (!s) + return -EINVAL; + + if (!strcmp(s, "standard")) + io_delay = standard_io_delay; + else if (!strcmp(s, "alternate")) + io_delay = alternate_io_delay; + else if (!strcmp(s, "udelay")) + io_delay = udelay_io_delay; + else + return -EINVAL; + +#ifndef CONFIG_UDELAY_IO_DELAY + io_delay_override = 1; +#endif + return 0; +} + +early_param("io_delay", io_delay_param); diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index 9c24b45b513..51bdc0b1b72 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -648,6 +648,8 @@ void __init setup_arch(char **cmdline_p) dmi_scan_machine(); + io_delay_init();; + #ifdef CONFIG_X86_GENERICARCH generic_apic_probe(); #endif diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 30d94d1d5f5..ec976edf039 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -311,6 +311,8 @@ void __init setup_arch(char **cmdline_p) dmi_scan_machine(); + io_delay_init(); + #ifdef CONFIG_SMP /* setup to use the static apicid table during kernel startup */ x86_cpu_to_apicid_ptr = (void *)&x86_cpu_to_apicid_init; diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h index fe881cd1e6f..a8d25c38b91 100644 --- a/include/asm-x86/io_32.h +++ b/include/asm-x86/io_32.h @@ -250,10 +250,14 @@ static inline void flush_write_buffers(void) #endif /* __KERNEL__ */ -static inline void native_io_delay(void) +#ifndef CONFIG_UDELAY_IO_DELAY +extern void io_delay_init(void); +#else +static inline void io_delay_init(void) { - asm volatile("outb %%al,$0x80" : : : "memory"); } +#endif +extern void native_io_delay(void); #if defined(CONFIG_PARAVIRT) #include diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h index a037b079433..5bebaf96169 100644 --- a/include/asm-x86/io_64.h +++ b/include/asm-x86/io_64.h @@ -35,13 +35,24 @@ * - Arnaldo Carvalho de Melo */ -#define __SLOW_DOWN_IO "\noutb %%al,$0x80" +#ifndef CONFIG_UDELAY_IO_DELAY +extern void io_delay_init(void); +#else +static inline void io_delay_init(void) +{ +} +#endif +extern void native_io_delay(void); +static inline void slow_down_io(void) +{ + native_io_delay(); #ifdef REALLY_SLOW_IO -#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO -#else -#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO + native_io_delay(); + native_io_delay(); + native_io_delay(); #endif +} /* * Talk about misusing macros.. @@ -50,21 +61,21 @@ static inline void out##s(unsigned x value, unsigned short port) { #define __OUT2(s,s1,s2) \ -__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1" +__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1" : : "a" (value), "Nd" (port)) #define __OUT(s,s1,x) \ -__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \ -__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \ +__OUT1(s,x) __OUT2(s,s1,"w"); } \ +__OUT1(s##_p,x) __OUT2(s,s1,"w"); slow_down_io(); } #define __IN1(s) \ static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v; #define __IN2(s,s1,s2) \ -__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0" +__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0" : "=a" (_v) : "Nd" (port)) -#define __IN(s,s1,i...) \ -__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ -__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ +#define __IN(s,s1) \ +__IN1(s) __IN2(s,s1,"w"); return _v; } \ +__IN1(s##_p) __IN2(s,s1,"w"); slow_down_io(); return _v; } #define __INS(s) \ static inline void ins##s(unsigned short port, void * addr, unsigned long count) \ -- 2.41.1