OpenCloudOS-Kernel/arch/x86/pci/pcbios.c

456 lines
11 KiB
C
Raw Normal View History

/*
* BIOS32 and PCI BIOS handling.
*/
#include <linux/pci.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <asm/pci_x86.h>
#include <asm/pci-functions.h>
x86: Add NX protection for kernel data This patch expands functionality of CONFIG_DEBUG_RODATA to set main (static) kernel data area as NX. The following steps are taken to achieve this: 1. Linker script is adjusted so .text always starts and ends on a page bound 2. Linker script is adjusted so .rodata always start and end on a page boundary 3. NX is set for all pages from _etext through _end in mark_rodata_ro. 4. free_init_pages() sets released memory NX in arch/x86/mm/init.c 5. bios rom is set to x when pcibios is used. The results of patch application may be observed in the diff of kernel page table dumps: pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc00a0000 640K RW GLB NX pte +0xc00a0000-0xc0100000 384K RW GLB x pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte No pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc0100000 1M RW GLB NX pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte The patch has been originally developed for Linux 2.6.34-rc2 x86 by Siarhei Liakh <sliakh.lkml@gmail.com> and Xuxian Jiang <jiang@cs.ncsu.edu>. -v1: initial patch for 2.6.30 -v2: patch for 2.6.31-rc7 -v3: moved all code into arch/x86, adjusted credits -v4: fixed ifdef, removed credits from CREDITS -v5: fixed an address calculation bug in mark_nxdata_nx() -v6: added acked-by and PT dump diff to commit log -v7: minor adjustments for -tip -v8: rework with the merge of "Set first MB as RW+NX" Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Signed-off-by: Matthieu CASTET <castet.matthieu@free.fr> Cc: Arjan van de Ven <arjan@infradead.org> Cc: James Morris <jmorris@namei.org> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F82E.60601@free.fr> [ minor cleanliness edits ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:31:26 +08:00
#include <asm/cacheflush.h>
/* BIOS32 signature: "_32_" */
#define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
/* PCI signature: "PCI " */
#define PCI_SIGNATURE (('P' << 0) + ('C' << 8) + ('I' << 16) + (' ' << 24))
/* PCI service signature: "$PCI" */
#define PCI_SERVICE (('$' << 0) + ('P' << 8) + ('C' << 16) + ('I' << 24))
/* PCI BIOS hardware mechanism flags */
#define PCIBIOS_HW_TYPE1 0x01
#define PCIBIOS_HW_TYPE2 0x02
#define PCIBIOS_HW_TYPE1_SPEC 0x10
#define PCIBIOS_HW_TYPE2_SPEC 0x20
x86: Add NX protection for kernel data This patch expands functionality of CONFIG_DEBUG_RODATA to set main (static) kernel data area as NX. The following steps are taken to achieve this: 1. Linker script is adjusted so .text always starts and ends on a page bound 2. Linker script is adjusted so .rodata always start and end on a page boundary 3. NX is set for all pages from _etext through _end in mark_rodata_ro. 4. free_init_pages() sets released memory NX in arch/x86/mm/init.c 5. bios rom is set to x when pcibios is used. The results of patch application may be observed in the diff of kernel page table dumps: pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc00a0000 640K RW GLB NX pte +0xc00a0000-0xc0100000 384K RW GLB x pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte No pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc0100000 1M RW GLB NX pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte The patch has been originally developed for Linux 2.6.34-rc2 x86 by Siarhei Liakh <sliakh.lkml@gmail.com> and Xuxian Jiang <jiang@cs.ncsu.edu>. -v1: initial patch for 2.6.30 -v2: patch for 2.6.31-rc7 -v3: moved all code into arch/x86, adjusted credits -v4: fixed ifdef, removed credits from CREDITS -v5: fixed an address calculation bug in mark_nxdata_nx() -v6: added acked-by and PT dump diff to commit log -v7: minor adjustments for -tip -v8: rework with the merge of "Set first MB as RW+NX" Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Signed-off-by: Matthieu CASTET <castet.matthieu@free.fr> Cc: Arjan van de Ven <arjan@infradead.org> Cc: James Morris <jmorris@namei.org> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F82E.60601@free.fr> [ minor cleanliness edits ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:31:26 +08:00
int pcibios_enabled;
/* According to the BIOS specification at:
* http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
* restrict the x zone to some pages and make it ro. But this may be
* broken on some bios, complex to handle with static_protections.
* We could make the 0xe0000-0x100000 range rox, but this can break
* some ISA mapping.
*
* So we let's an rw and x hole when pcibios is used. This shouldn't
* happen for modern system with mmconfig, and if you don't want it
* you could disable pcibios...
*/
static inline void set_bios_x(void)
{
pcibios_enabled = 1;
set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT);
if (__supported_pte_mask & _PAGE_NX)
printk(KERN_INFO "PCI : PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n");
x86: Add NX protection for kernel data This patch expands functionality of CONFIG_DEBUG_RODATA to set main (static) kernel data area as NX. The following steps are taken to achieve this: 1. Linker script is adjusted so .text always starts and ends on a page bound 2. Linker script is adjusted so .rodata always start and end on a page boundary 3. NX is set for all pages from _etext through _end in mark_rodata_ro. 4. free_init_pages() sets released memory NX in arch/x86/mm/init.c 5. bios rom is set to x when pcibios is used. The results of patch application may be observed in the diff of kernel page table dumps: pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc00a0000 640K RW GLB NX pte +0xc00a0000-0xc0100000 384K RW GLB x pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte No pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc0100000 1M RW GLB NX pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte The patch has been originally developed for Linux 2.6.34-rc2 x86 by Siarhei Liakh <sliakh.lkml@gmail.com> and Xuxian Jiang <jiang@cs.ncsu.edu>. -v1: initial patch for 2.6.30 -v2: patch for 2.6.31-rc7 -v3: moved all code into arch/x86, adjusted credits -v4: fixed ifdef, removed credits from CREDITS -v5: fixed an address calculation bug in mark_nxdata_nx() -v6: added acked-by and PT dump diff to commit log -v7: minor adjustments for -tip -v8: rework with the merge of "Set first MB as RW+NX" Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Signed-off-by: Matthieu CASTET <castet.matthieu@free.fr> Cc: Arjan van de Ven <arjan@infradead.org> Cc: James Morris <jmorris@namei.org> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F82E.60601@free.fr> [ minor cleanliness edits ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:31:26 +08:00
}
/*
* This is the standard structure used to identify the entry point
* to the BIOS32 Service Directory, as documented in
* Standard BIOS 32-bit Service Directory Proposal
* Revision 0.4 May 24, 1993
* Phoenix Technologies Ltd.
* Norwood, MA
* and the PCI BIOS specification.
*/
union bios32 {
struct {
unsigned long signature; /* _32_ */
unsigned long entry; /* 32 bit physical address */
unsigned char revision; /* Revision level, 0 */
unsigned char length; /* Length in paragraphs should be 01 */
unsigned char checksum; /* All bytes must add up to zero */
unsigned char reserved[5]; /* Must be zero */
} fields;
char chars[16];
};
/*
* Physical address of the service directory. I don't know if we're
* allowed to have more than one of these or not, so just in case
* we'll make pcibios_present() take a memory start parameter and store
* the array there.
*/
static struct {
unsigned long address;
unsigned short segment;
} bios32_indirect = { 0, __KERNEL_CS };
/*
* Returns the entry point for the given service, NULL on error
*/
static unsigned long bios32_service(unsigned long service)
{
unsigned char return_code; /* %al */
unsigned long address; /* %ebx */
unsigned long length; /* %ecx */
unsigned long entry; /* %edx */
unsigned long flags;
local_irq_save(flags);
__asm__("lcall *(%%edi); cld"
: "=a" (return_code),
"=b" (address),
"=c" (length),
"=d" (entry)
: "0" (service),
"1" (0),
"D" (&bios32_indirect));
local_irq_restore(flags);
switch (return_code) {
case 0:
return address + entry;
case 0x80: /* Not present */
printk(KERN_WARNING "bios32_service(0x%lx): not present\n", service);
return 0;
default: /* Shouldn't happen */
printk(KERN_WARNING "bios32_service(0x%lx): returned 0x%x -- BIOS bug!\n",
service, return_code);
return 0;
}
}
static struct {
unsigned long address;
unsigned short segment;
} pci_indirect = { 0, __KERNEL_CS };
static int pci_bios_present;
static int check_pcibios(void)
{
u32 signature, eax, ebx, ecx;
u8 status, major_ver, minor_ver, hw_mech;
unsigned long flags, pcibios_entry;
if ((pcibios_entry = bios32_service(PCI_SERVICE))) {
pci_indirect.address = pcibios_entry + PAGE_OFFSET;
local_irq_save(flags);
__asm__(
"lcall *(%%edi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=d" (signature),
"=a" (eax),
"=b" (ebx),
"=c" (ecx)
: "1" (PCIBIOS_PCI_BIOS_PRESENT),
"D" (&pci_indirect)
: "memory");
local_irq_restore(flags);
status = (eax >> 8) & 0xff;
hw_mech = eax & 0xff;
major_ver = (ebx >> 8) & 0xff;
minor_ver = ebx & 0xff;
if (pcibios_last_bus < 0)
pcibios_last_bus = ecx & 0xff;
DBG("PCI: BIOS probe returned s=%02x hw=%02x ver=%02x.%02x l=%02x\n",
status, hw_mech, major_ver, minor_ver, pcibios_last_bus);
if (status || signature != PCI_SIGNATURE) {
printk (KERN_ERR "PCI: BIOS BUG #%x[%08x] found\n",
status, signature);
return 0;
}
printk(KERN_INFO "PCI: PCI BIOS revision %x.%02x entry at 0x%lx, last bus=%d\n",
major_ver, minor_ver, pcibios_entry, pcibios_last_bus);
#ifdef CONFIG_PCI_DIRECT
if (!(hw_mech & PCIBIOS_HW_TYPE1))
pci_probe &= ~PCI_PROBE_CONF1;
if (!(hw_mech & PCIBIOS_HW_TYPE2))
pci_probe &= ~PCI_PROBE_CONF2;
#endif
return 1;
}
return 0;
}
static int pci_bios_read(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 *value)
{
unsigned long result = 0;
unsigned long flags;
unsigned long bx = (bus << 8) | devfn;
WARN_ON(seg);
if (!value || (bus > 255) || (devfn > 255) || (reg > 255))
return -EINVAL;
raw_spin_lock_irqsave(&pci_config_lock, flags);
switch (len) {
case 1:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=c" (*value),
"=a" (result)
: "1" (PCIBIOS_READ_CONFIG_BYTE),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
fix BIOS PCI config cycle buglet causing ACPI boot regression I figured out another ACPI related regression today. randconfig testing triggered an early boot-time hang on a laptop of mine (32-bit x86, config attached) - the screen was scrolling ACPI AML exceptions [with no serial port and no early debugging available]. v2.6.24 works fine on that laptop with the same .config, so after a few hours of bisection (had to restart it 3 times - other regressions interacted), it honed in on this commit: | 10270d4838bdc493781f5a1cf2e90e9c34c9142f is first bad commit | | Author: Linus Torvalds <torvalds@woody.linux-foundation.org> | Date: Wed Feb 13 09:56:14 2008 -0800 | | acpi: fix acpi_os_read_pci_configuration() misuse of raw_pci_read() reverting this commit ontop of -rc5 gave a correctly booting kernel. But this commit fixes a real bug so the real question is, why did it break the bootup? After quite some head-scratching, the following change stood out: - pci_id->bus = tu8; + pci_id->bus = val; pci_id->bus is defined as u16: struct acpi_pci_id { u16 segment; u16 bus; ... and 'tu8' changed from u8 to u32. So previously we'd unconditionally mask the return value of acpi_os_read_pci_configuration() (raw_pci_read()) to 8 bits, but now we just trust whatever comes back from the PCI access routines and only crop it to 16 bits. But if the high 8 bits of that result contains any noise then we'll write that into ACPI's PCI ID descriptor and confuse the heck out of the rest of ACPI. So lets check the PCI-BIOS code on that theory. We have this codepath for 8-bit accesses (arch/x86/pci/pcbios.c:pci_bios_read()): switch (len) { case 1: __asm__("lcall *(%%esi); cld\n\t" "jc 1f\n\t" "xor %%ah, %%ah\n" "1:" : "=c" (*value), "=a" (result) : "1" (PCIBIOS_READ_CONFIG_BYTE), "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); Aha! The "=a" output constraint puts the full 32 bits of EAX into *value. But if the BIOS's routines set any of the high bits to nonzero, we'll return a value with more set in it than intended. The other, more common PCI access methods (v1 and v2 PCI reads) clear out the high bits already, for example pci_conf1_read() does: switch (len) { case 1: *value = inb(0xCFC + (reg & 3)); which explicitly converts the return byte up to 32 bits and zero-extends it. So zero-extending the result in the PCI-BIOS read routine fixes the regression on my laptop. ( It might fix some other long-standing issues we had with PCI-BIOS during the past decade ... ) Both 8-bit and 16-bit accesses were buggy. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-03-11 01:04:34 +08:00
/*
* Zero-extend the result beyond 8 bits, do not trust the
* BIOS having done it:
*/
*value &= 0xff;
break;
case 2:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=c" (*value),
"=a" (result)
: "1" (PCIBIOS_READ_CONFIG_WORD),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
fix BIOS PCI config cycle buglet causing ACPI boot regression I figured out another ACPI related regression today. randconfig testing triggered an early boot-time hang on a laptop of mine (32-bit x86, config attached) - the screen was scrolling ACPI AML exceptions [with no serial port and no early debugging available]. v2.6.24 works fine on that laptop with the same .config, so after a few hours of bisection (had to restart it 3 times - other regressions interacted), it honed in on this commit: | 10270d4838bdc493781f5a1cf2e90e9c34c9142f is first bad commit | | Author: Linus Torvalds <torvalds@woody.linux-foundation.org> | Date: Wed Feb 13 09:56:14 2008 -0800 | | acpi: fix acpi_os_read_pci_configuration() misuse of raw_pci_read() reverting this commit ontop of -rc5 gave a correctly booting kernel. But this commit fixes a real bug so the real question is, why did it break the bootup? After quite some head-scratching, the following change stood out: - pci_id->bus = tu8; + pci_id->bus = val; pci_id->bus is defined as u16: struct acpi_pci_id { u16 segment; u16 bus; ... and 'tu8' changed from u8 to u32. So previously we'd unconditionally mask the return value of acpi_os_read_pci_configuration() (raw_pci_read()) to 8 bits, but now we just trust whatever comes back from the PCI access routines and only crop it to 16 bits. But if the high 8 bits of that result contains any noise then we'll write that into ACPI's PCI ID descriptor and confuse the heck out of the rest of ACPI. So lets check the PCI-BIOS code on that theory. We have this codepath for 8-bit accesses (arch/x86/pci/pcbios.c:pci_bios_read()): switch (len) { case 1: __asm__("lcall *(%%esi); cld\n\t" "jc 1f\n\t" "xor %%ah, %%ah\n" "1:" : "=c" (*value), "=a" (result) : "1" (PCIBIOS_READ_CONFIG_BYTE), "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); Aha! The "=a" output constraint puts the full 32 bits of EAX into *value. But if the BIOS's routines set any of the high bits to nonzero, we'll return a value with more set in it than intended. The other, more common PCI access methods (v1 and v2 PCI reads) clear out the high bits already, for example pci_conf1_read() does: switch (len) { case 1: *value = inb(0xCFC + (reg & 3)); which explicitly converts the return byte up to 32 bits and zero-extends it. So zero-extending the result in the PCI-BIOS read routine fixes the regression on my laptop. ( It might fix some other long-standing issues we had with PCI-BIOS during the past decade ... ) Both 8-bit and 16-bit accesses were buggy. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-03-11 01:04:34 +08:00
/*
* Zero-extend the result beyond 16 bits, do not trust the
* BIOS having done it:
*/
*value &= 0xffff;
break;
case 4:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=c" (*value),
"=a" (result)
: "1" (PCIBIOS_READ_CONFIG_DWORD),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
break;
}
raw_spin_unlock_irqrestore(&pci_config_lock, flags);
return (int)((result & 0xff00) >> 8);
}
static int pci_bios_write(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 value)
{
unsigned long result = 0;
unsigned long flags;
unsigned long bx = (bus << 8) | devfn;
WARN_ON(seg);
if ((bus > 255) || (devfn > 255) || (reg > 255))
return -EINVAL;
raw_spin_lock_irqsave(&pci_config_lock, flags);
switch (len) {
case 1:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=a" (result)
: "0" (PCIBIOS_WRITE_CONFIG_BYTE),
"c" (value),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
break;
case 2:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=a" (result)
: "0" (PCIBIOS_WRITE_CONFIG_WORD),
"c" (value),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
break;
case 4:
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=a" (result)
: "0" (PCIBIOS_WRITE_CONFIG_DWORD),
"c" (value),
"b" (bx),
"D" ((long)reg),
"S" (&pci_indirect));
break;
}
raw_spin_unlock_irqrestore(&pci_config_lock, flags);
return (int)((result & 0xff00) >> 8);
}
/*
* Function table for BIOS32 access
*/
static const struct pci_raw_ops pci_bios_access = {
.read = pci_bios_read,
.write = pci_bios_write
};
/*
* Try to find PCI BIOS.
*/
static const struct pci_raw_ops *pci_find_bios(void)
{
union bios32 *check;
unsigned char sum;
int i, length;
/*
* Follow the standard procedure for locating the BIOS32 Service
* directory by scanning the permissible address range from
* 0xe0000 through 0xfffff for a valid BIOS32 structure.
*/
for (check = (union bios32 *) __va(0xe0000);
check <= (union bios32 *) __va(0xffff0);
++check) {
long sig;
if (probe_kernel_address(&check->fields.signature, sig))
continue;
if (check->fields.signature != BIOS32_SIGNATURE)
continue;
length = check->fields.length * 16;
if (!length)
continue;
sum = 0;
for (i = 0; i < length ; ++i)
sum += check->chars[i];
if (sum != 0)
continue;
if (check->fields.revision != 0) {
printk("PCI: unsupported BIOS32 revision %d at 0x%p\n",
check->fields.revision, check);
continue;
}
DBG("PCI: BIOS32 Service Directory structure at 0x%p\n", check);
if (check->fields.entry >= 0x100000) {
printk("PCI: BIOS32 entry (0x%p) in high memory, "
"cannot use.\n", check);
return NULL;
} else {
unsigned long bios32_entry = check->fields.entry;
DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n",
bios32_entry);
bios32_indirect.address = bios32_entry + PAGE_OFFSET;
x86: Add NX protection for kernel data This patch expands functionality of CONFIG_DEBUG_RODATA to set main (static) kernel data area as NX. The following steps are taken to achieve this: 1. Linker script is adjusted so .text always starts and ends on a page bound 2. Linker script is adjusted so .rodata always start and end on a page boundary 3. NX is set for all pages from _etext through _end in mark_rodata_ro. 4. free_init_pages() sets released memory NX in arch/x86/mm/init.c 5. bios rom is set to x when pcibios is used. The results of patch application may be observed in the diff of kernel page table dumps: pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc00a0000 640K RW GLB NX pte +0xc00a0000-0xc0100000 384K RW GLB x pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte No pcibios: -- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400 ++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400 0x00000000-0xc0000000 3G pmd ---[ Kernel Mapping ]--- -0xc0000000-0xc0100000 1M RW GLB x pte +0xc0000000-0xc0100000 1M RW GLB NX pte -0xc0100000-0xc03d7000 2908K ro GLB x pte +0xc0100000-0xc0318000 2144K ro GLB x pte +0xc0318000-0xc03d7000 764K ro GLB NX pte -0xc03d7000-0xc0600000 2212K RW GLB x pte +0xc03d7000-0xc0600000 2212K RW GLB NX pte 0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd 0xf7a00000-0xf7bfe000 2040K RW GLB NX pte 0xf7bfe000-0xf7c00000 8K pte The patch has been originally developed for Linux 2.6.34-rc2 x86 by Siarhei Liakh <sliakh.lkml@gmail.com> and Xuxian Jiang <jiang@cs.ncsu.edu>. -v1: initial patch for 2.6.30 -v2: patch for 2.6.31-rc7 -v3: moved all code into arch/x86, adjusted credits -v4: fixed ifdef, removed credits from CREDITS -v5: fixed an address calculation bug in mark_nxdata_nx() -v6: added acked-by and PT dump diff to commit log -v7: minor adjustments for -tip -v8: rework with the merge of "Set first MB as RW+NX" Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Signed-off-by: Matthieu CASTET <castet.matthieu@free.fr> Cc: Arjan van de Ven <arjan@infradead.org> Cc: James Morris <jmorris@namei.org> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F82E.60601@free.fr> [ minor cleanliness edits ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:31:26 +08:00
set_bios_x();
if (check_pcibios())
return &pci_bios_access;
}
break; /* Hopefully more than one BIOS32 cannot happen... */
}
return NULL;
}
/*
* BIOS Functions for IRQ Routing
*/
struct irq_routing_options {
u16 size;
struct irq_info *table;
u16 segment;
} __attribute__((packed));
struct irq_routing_table * pcibios_get_irq_routing_table(void)
{
struct irq_routing_options opt;
struct irq_routing_table *rt = NULL;
int ret, map;
unsigned long page;
if (!pci_bios_present)
return NULL;
page = __get_free_page(GFP_KERNEL);
if (!page)
return NULL;
opt.table = (struct irq_info *) page;
opt.size = PAGE_SIZE;
opt.segment = __KERNEL_DS;
DBG("PCI: Fetching IRQ routing table... ");
__asm__("push %%es\n\t"
"push %%ds\n\t"
"pop %%es\n\t"
"lcall *(%%esi); cld\n\t"
"pop %%es\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=a" (ret),
"=b" (map),
"=m" (opt)
: "0" (PCIBIOS_GET_ROUTING_OPTIONS),
"1" (0),
"D" ((long) &opt),
"S" (&pci_indirect),
"m" (opt)
: "memory");
DBG("OK ret=%d, size=%d, map=%x\n", ret, opt.size, map);
if (ret & 0xff00)
printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff);
else if (opt.size) {
rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL);
if (rt) {
memset(rt, 0, sizeof(struct irq_routing_table));
rt->size = opt.size + sizeof(struct irq_routing_table);
rt->exclusive_irqs = map;
memcpy(rt->slots, (void *) page, opt.size);
printk(KERN_INFO "PCI: Using BIOS Interrupt Routing Table\n");
}
}
free_page(page);
return rt;
}
EXPORT_SYMBOL(pcibios_get_irq_routing_table);
int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
{
int ret;
__asm__("lcall *(%%esi); cld\n\t"
"jc 1f\n\t"
"xor %%ah, %%ah\n"
"1:"
: "=a" (ret)
: "0" (PCIBIOS_SET_PCI_HW_INT),
"b" ((dev->bus->number << 8) | dev->devfn),
"c" ((irq << 8) | (pin + 10)),
"S" (&pci_indirect));
return !(ret & 0xff00);
}
EXPORT_SYMBOL(pcibios_set_irq_routing);
void __init pci_pcbios_init(void)
{
if ((pci_probe & PCI_PROBE_BIOS)
&& ((raw_pci_ops = pci_find_bios()))) {
pci_bios_present = 1;
}
}