Q: Can I suspend-to-disk using a swap partition under LVM?
-A: No. You can suspend successfully, but you'll not be able to
-resume. uswsusp should be able to work with LVM. See suspend.sf.net.
+A: Yes and No. You can suspend successfully, but the kernel will not be able
+to resume on its own. You need an initramfs that can recognize the resume
+situation, activate the logical volume containing the swap volume (but not
+touch any filesystems!), and eventually call
+
+echo -n "$major:$minor" > /sys/power/resume
+
+where $major and $minor are the respective major and minor device numbers of
+the swap volume.
+
+uswsusp works with LVM, too. See http://suspend.sourceforge.net/
Q: I upgraded the kernel from 2.6.15 to 2.6.16. Both kernels were
compiled with the similar configuration files. Anyway I found that
F: arch/powerpc/oprofile/*cell*
F: arch/powerpc/platforms/cell/
-CEPH DISTRIBUTED FILE SYSTEM CLIENT
+CEPH COMMON CODE (LIBCEPH)
+M: Ilya Dryomov <idryomov@gmail.com>
M: "Yan, Zheng" <zyan@redhat.com>
M: Sage Weil <sage@redhat.com>
L: ceph-devel@vger.kernel.org
W: http://ceph.com/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T: git git://github.com/ceph/ceph-client.git
S: Supported
-F: Documentation/filesystems/ceph.txt
-F: fs/ceph/
F: net/ceph/
F: include/linux/ceph/
F: include/linux/crush/
+CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
+M: "Yan, Zheng" <zyan@redhat.com>
+M: Sage Weil <sage@redhat.com>
+M: Ilya Dryomov <idryomov@gmail.com>
+L: ceph-devel@vger.kernel.org
+W: http://ceph.com/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T: git git://github.com/ceph/ceph-client.git
+S: Supported
+F: Documentation/filesystems/ceph.txt
+F: fs/ceph/
+
CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
L: linux-usb@vger.kernel.org
S: Orphan
W: http://www.penguinppc.org/
L: linuxppc-dev@lists.ozlabs.org
Q: http://patchwork.ozlabs.org/project/linuxppc-dev/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
S: Supported
F: Documentation/powerpc/
F: arch/powerpc/
M: Ilya Dryomov <idryomov@gmail.com>
M: Sage Weil <sage@redhat.com>
M: Alex Elder <elder@kernel.org>
-M: ceph-devel@vger.kernel.org
+L: ceph-devel@vger.kernel.org
W: http://ceph.com/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T: git git://github.com/ceph/ceph-client.git
S: Supported
+F: Documentation/ABI/testing/sysfs-bus-rbd
F: drivers/block/rbd.c
F: drivers/block/rbd_types.h
config HIGHPTE
bool "Allocate 2nd-level pagetables from highmem"
depends on HIGHMEM
+ help
+ The VM uses one page of physical memory for each page table.
+ For systems with a lot of processes, this can use a lot of
+ precious low memory, eventually leading to low memory being
+ consumed by page tables. Setting this option will allow
+ user-space 2nd level page tables to reside in high memory.
config HW_PERF_EVENTS
bool "Enable hardware performance counter support for perf events"
config DEBUG_SET_MODULE_RONX
bool "Set loadable kernel module data as NX and text as RO"
- depends on MODULES
+ depends on MODULES && MMU
---help---
This option helps catch unintended modifications to loadable
kernel module's text and read-only data. It also prevents execution
* The _caller variety takes a __builtin_return_address(0) value for
* /proc/vmalloc to use - and should only be used in non-inline functions.
*/
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
- size_t, unsigned int, void *);
extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
void *);
-
extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
unsigned int, void *);
static inline void memset_io(volatile void __iomem *dst, unsigned c,
size_t count)
{
- memset((void __force *)dst, c, count);
+ extern void mmioset(void *, unsigned int, size_t);
+ mmioset((void __force *)dst, c, count);
}
#define memset_io(dst,c,count) memset_io(dst,c,count)
static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
size_t count)
{
- memcpy(to, (const void __force *)from, count);
+ extern void mmiocpy(void *, const void *, size_t);
+ mmiocpy(to, (const void __force *)from, count);
}
#define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
static inline void memcpy_toio(volatile void __iomem *to, const void *from,
size_t count)
{
- memcpy((void __force *)to, from, count);
+ extern void mmiocpy(void *, const void *, size_t);
+ mmiocpy((void __force *)to, from, count);
}
#define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
#endif /* readl */
/*
- * ioremap and friends.
+ * ioremap() and friends.
+ *
+ * ioremap() takes a resource address, and size. Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
+ *
+ * Function Memory type Cacheability Cache hint
+ * ioremap() Device n/a n/a
+ * ioremap_nocache() Device n/a n/a
+ * ioremap_cache() Normal Writeback Read allocate
+ * ioremap_wc() Normal Non-cacheable n/a
+ * ioremap_wt() Normal Non-cacheable n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
*
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different. This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
*
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ * instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
*/
-#define ioremap(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define ioremap_wt(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
-#define iounmap __arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
/*
* io{read,write}{16,32}be() macros
*/
#define __pa(x) __virt_to_phys((unsigned long)(x))
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn) __va((phys_addr_t)(pfn) << PAGE_SHIFT)
extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
/*
* These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type Pre-ARMv6 ARMv6+ type / cacheable status
+ * UNCACHED Uncached Strongly ordered
+ * BUFFERABLE Bufferable Normal memory / non-cacheable
+ * WRITETHROUGH Writethrough Normal memory / write through
+ * WRITEBACK Writeback Normal memory / write back, read alloc
+ * MINICACHE Minicache N/A
+ * WRITEALLOC Writeback Normal memory / write back, write alloc
+ * DEV_SHARED Uncached Device memory (shared)
+ * DEV_NONSHARED Uncached Device memory (non-shared)
+ * DEV_WC Bufferable Normal memory / non-cacheable
+ * DEV_CACHED Writeback Normal memory / write back, read alloc
+ * VECTORS Variable Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
*/
#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */
#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */
extern void fpundefinstr(void);
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
/* platform dependent support */
EXPORT_SYMBOL(arm_delay_ops);
EXPORT_SYMBOL(memchr);
EXPORT_SYMBOL(__memzero);
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
#ifdef CONFIG_MMU
EXPORT_SYMBOL(copy_page);
zero_fp
.if \trace
-#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_off
#endif
ct_user_exit save = 0
struct pt_regs *old_regs = set_irq_regs(regs);
if ((unsigned)ipinr < NR_IPI) {
- trace_ipi_entry(ipi_types[ipinr]);
+ trace_ipi_entry_rcuidle(ipi_types[ipinr]);
__inc_irq_stat(cpu, ipi_irqs[ipinr]);
}
}
if ((unsigned)ipinr < NR_IPI)
- trace_ipi_exit(ipi_types[ipinr]);
+ trace_ipi_exit_rcuidle(ipi_types[ipinr]);
set_irq_regs(old_regs);
}
/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
+ENTRY(mmiocpy)
ENTRY(memcpy)
#include "copy_template.S"
ENDPROC(memcpy)
+ENDPROC(mmiocpy)
.text
.align 5
+ENTRY(mmioset)
ENTRY(memset)
UNWIND( .fnstart )
ands r3, r0, #3 @ 1 unaligned?
b 1b
UNWIND( .fnend )
ENDPROC(memset)
+ENDPROC(mmioset)
}
#endif
-void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
unsigned long offset, size_t size, unsigned int mtype, void *caller)
{
const struct mem_type *type;
unsigned int mtype)
{
return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
- __builtin_return_address(0));
+ __builtin_return_address(0));
}
EXPORT_SYMBOL(__arm_ioremap_pfn);
unsigned int, void *) =
__arm_ioremap_caller;
-void __iomem *
-__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
+{
+ return arch_ioremap_caller(res_cookie, size, MT_DEVICE,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+ return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
{
- return arch_ioremap_caller(phys_addr, size, mtype,
- __builtin_return_address(0));
+ return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+ __builtin_return_address(0));
}
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap_wc);
/*
* Remap an arbitrary physical address space into the kernel virtual
void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
-void __arm_iounmap(volatile void __iomem *io_addr)
+void iounmap(volatile void __iomem *cookie)
{
- arch_iounmap(io_addr);
+ arch_iounmap(cookie);
}
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
#ifdef CONFIG_PCI
static int pci_ioremap_mem_type = MT_DEVICE;
int highmem = 0;
phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
struct memblock_region *reg;
+ bool should_use_highmem = false;
for_each_memblock(memory, reg) {
phys_addr_t block_start = reg->base;
pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
&block_start, &block_end);
memblock_remove(reg->base, reg->size);
+ should_use_highmem = true;
continue;
}
&block_start, &block_end, &vmalloc_limit);
memblock_remove(vmalloc_limit, overlap_size);
block_end = vmalloc_limit;
+ should_use_highmem = true;
}
}
}
}
+ if (should_use_highmem)
+ pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
high_memory = __va(arm_lowmem_limit - 1) + 1;
/*
build_mem_type_table();
prepare_page_table();
map_lowmem();
+ memblock_set_current_limit(arm_lowmem_limit);
dma_contiguous_remap();
devicemaps_init(mdesc);
kmap_init();
}
EXPORT_SYMBOL(__arm_ioremap_pfn);
-void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
- size_t size, unsigned int mtype, void *caller)
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
+ unsigned int mtype, void *caller)
{
- return __arm_ioremap_pfn(pfn, offset, size, mtype);
+ return (void __iomem *)phys_addr;
}
-void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
- unsigned int mtype)
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
{
- return (void __iomem *)phys_addr;
+ return __arm_ioremap_caller(res_cookie, size, MT_DEVICE,
+ __builtin_return_address(0));
}
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap);
-void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+ return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
-void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
- unsigned int mtype, void *caller)
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+ return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iounmap(volatile void __iomem *addr)
{
- return __arm_ioremap(phys_addr, size, mtype);
}
+EXPORT_SYMBOL(__iounmap);
void (*arch_iounmap)(volatile void __iomem *);
-void __arm_iounmap(volatile void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
{
}
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
* it does.
*/
-#define _GNU_SOURCE
-
#include <byteswap.h>
#include <elf.h>
#include <errno.h>
-#include <error.h>
#include <fcntl.h>
+#include <stdarg.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#define EF_ARM_ABI_FLOAT_HARD 0x400
#endif
+static int failed;
+static const char *argv0;
static const char *outfile;
+static void fail(const char *fmt, ...)
+{
+ va_list ap;
+
+ failed = 1;
+ fprintf(stderr, "%s: ", argv0);
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+ exit(EXIT_FAILURE);
+}
+
static void cleanup(void)
{
- if (error_message_count > 0 && outfile != NULL)
+ if (failed && outfile != NULL)
unlink(outfile);
}
int infd;
atexit(cleanup);
+ argv0 = argv[0];
if (argc != 3)
- error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]);
+ fail("Usage: %s [infile] [outfile]\n", argv[0]);
infile = argv[1];
outfile = argv[2];
infd = open(infile, O_RDONLY);
if (infd < 0)
- error(EXIT_FAILURE, errno, "Cannot open %s", infile);
+ fail("Cannot open %s: %s\n", infile, strerror(errno));
if (fstat(infd, &stat) != 0)
- error(EXIT_FAILURE, errno, "Failed stat for %s", infile);
+ fail("Failed stat for %s: %s\n", infile, strerror(errno));
inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0);
if (inbuf == MAP_FAILED)
- error(EXIT_FAILURE, errno, "Failed to map %s", infile);
+ fail("Failed to map %s: %s\n", infile, strerror(errno));
close(infd);
inhdr = inbuf;
if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0)
- error(EXIT_FAILURE, 0, "Not an ELF file");
+ fail("Not an ELF file\n");
if (inhdr->e_ident[EI_CLASS] != ELFCLASS32)
- error(EXIT_FAILURE, 0, "Unsupported ELF class");
+ fail("Unsupported ELF class\n");
swap = inhdr->e_ident[EI_DATA] != HOST_ORDER;
if (read_elf_half(inhdr->e_type, swap) != ET_DYN)
- error(EXIT_FAILURE, 0, "Not a shared object");
+ fail("Not a shared object\n");
- if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) {
- error(EXIT_FAILURE, 0, "Unsupported architecture %#x",
- inhdr->e_machine);
- }
+ if (read_elf_half(inhdr->e_machine, swap) != EM_ARM)
+ fail("Unsupported architecture %#x\n", inhdr->e_machine);
e_flags = read_elf_word(inhdr->e_flags, swap);
if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) {
- error(EXIT_FAILURE, 0, "Unsupported EABI version %#x",
- EF_ARM_EABI_VERSION(e_flags));
+ fail("Unsupported EABI version %#x\n",
+ EF_ARM_EABI_VERSION(e_flags));
}
if (e_flags & EF_ARM_ABI_FLOAT_HARD)
- error(EXIT_FAILURE, 0,
- "Unexpected hard-float flag set in e_flags");
+ fail("Unexpected hard-float flag set in e_flags\n");
clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT);
outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
if (outfd < 0)
- error(EXIT_FAILURE, errno, "Cannot open %s", outfile);
+ fail("Cannot open %s: %s\n", outfile, strerror(errno));
if (ftruncate(outfd, stat.st_size) != 0)
- error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile);
+ fail("Cannot truncate %s: %s\n", outfile, strerror(errno));
outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED,
outfd, 0);
if (outbuf == MAP_FAILED)
- error(EXIT_FAILURE, errno, "Failed to map %s", outfile);
+ fail("Failed to map %s: %s\n", outfile, strerror(errno));
close(outfd);
}
if (msync(outbuf, stat.st_size, MS_SYNC) != 0)
- error(EXIT_FAILURE, errno, "Failed to sync %s", outfile);
+ fail("Failed to sync %s: %s\n", outfile, strerror(errno));
return EXIT_SUCCESS;
}
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select COMMON_CLK
- select EDAC_SUPPORT
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS
+ select EDAC_SUPPORT
select GENERIC_ALLOCATOR
select GENERIC_CLOCKEVENTS
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
CONFIG_ATA=y
CONFIG_SATA_AHCI=y
CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_CEVA=y
CONFIG_AHCI_XGENE=y
CONFIG_PATA_PLATFORM=y
CONFIG_PATA_OF_PLATFORM=y
#include <asm/psci.h>
#include <asm/smp_plat.h>
+/* Macros for consistency checks of the GICC subtable of MADT */
+#define ACPI_MADT_GICC_LENGTH \
+ (acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
+
+#define BAD_MADT_GICC_ENTRY(entry, end) \
+ (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \
+ (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+
/* Basic configuration for ACPI */
#ifdef CONFIG_ACPI
/* ACPI table mapping after acpi_gbl_permanent_mmap is set */
// TODO: add support for undefined instructions in kernel mode
enable_dbg
mov x0, sp
+ mov x2, x1
mov x1, #BAD_SYNC
- mrs x2, esr_el1
b bad_mode
ENDPROC(el1_sync)
ct_user_exit
mov x0, sp
mov x1, #BAD_SYNC
- mrs x2, esr_el1
+ mov x2, x25
bl bad_mode
b ret_to_user
ENDPROC(el0_sync)
ENTRY(compat_sys_sigreturn_wrapper)
mov x0, sp
- mov x27, #0 // prevent syscall restart handling (why)
b compat_sys_sigreturn
ENDPROC(compat_sys_sigreturn_wrapper)
ENTRY(compat_sys_rt_sigreturn_wrapper)
mov x0, sp
- mov x27, #0 // prevent syscall restart handling (why)
b compat_sys_rt_sigreturn
ENDPROC(compat_sys_rt_sigreturn_wrapper)
struct acpi_madt_generic_interrupt *processor;
processor = (struct acpi_madt_generic_interrupt *)header;
- if (BAD_MADT_ENTRY(processor, end))
+ if (BAD_MADT_GICC_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(header);
context.o proc.o pageattr.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_ARM64_PTDUMP) += dump.o
-
-CFLAGS_mmu.o := -I$(srctree)/scripts/dtc/libfdt/
#include <asm/processor.h>
#include <asm/cache.h>
-extern spinlock_t pa_dbit_lock;
+extern spinlock_t pa_tlb_lock;
/*
* kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
*/
#define kern_addr_valid(addr) (1)
+/* Purge data and instruction TLB entries. Must be called holding
+ * the pa_tlb_lock. The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+
+static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+ mtsp(mm->context, 1);
+ pdtlb(addr);
+ if (unlikely(split_tlb))
+ pitlb(addr);
+}
+
/* Certain architectures need to do special things when PTEs
* within a page table are directly modified. Thus, the following
* hook is made available.
*(pteptr) = (pteval); \
} while(0)
-extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+#define pte_inserted(x) \
+ ((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED)) \
+ == (_PAGE_PRESENT|_PAGE_ACCESSED))
-#define set_pte_at(mm, addr, ptep, pteval) \
- do { \
+#define set_pte_at(mm, addr, ptep, pteval) \
+ do { \
+ pte_t old_pte; \
unsigned long flags; \
- spin_lock_irqsave(&pa_dbit_lock, flags); \
- set_pte(ptep, pteval); \
- purge_tlb_entries(mm, addr); \
- spin_unlock_irqrestore(&pa_dbit_lock, flags); \
+ spin_lock_irqsave(&pa_tlb_lock, flags); \
+ old_pte = *ptep; \
+ set_pte(ptep, pteval); \
+ if (pte_inserted(old_pte)) \
+ purge_tlb_entries(mm, addr); \
+ spin_unlock_irqrestore(&pa_tlb_lock, flags); \
} while (0)
#endif /* !__ASSEMBLY__ */
#define pte_none(x) (pte_val(x) == 0)
#define pte_present(x) (pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp) do { pte_val(*(xp)) = 0; } while (0)
+#define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0))
#define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK)
#define pmd_address(x) ((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
if (!pte_young(*ptep))
return 0;
- spin_lock_irqsave(&pa_dbit_lock, flags);
+ spin_lock_irqsave(&pa_tlb_lock, flags);
pte = *ptep;
if (!pte_young(pte)) {
- spin_unlock_irqrestore(&pa_dbit_lock, flags);
+ spin_unlock_irqrestore(&pa_tlb_lock, flags);
return 0;
}
set_pte(ptep, pte_mkold(pte));
purge_tlb_entries(vma->vm_mm, addr);
- spin_unlock_irqrestore(&pa_dbit_lock, flags);
+ spin_unlock_irqrestore(&pa_tlb_lock, flags);
return 1;
}
pte_t old_pte;
unsigned long flags;
- spin_lock_irqsave(&pa_dbit_lock, flags);
+ spin_lock_irqsave(&pa_tlb_lock, flags);
old_pte = *ptep;
- pte_clear(mm,addr,ptep);
- purge_tlb_entries(mm, addr);
- spin_unlock_irqrestore(&pa_dbit_lock, flags);
+ set_pte(ptep, __pte(0));
+ if (pte_inserted(old_pte))
+ purge_tlb_entries(mm, addr);
+ spin_unlock_irqrestore(&pa_tlb_lock, flags);
return old_pte;
}
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
unsigned long flags;
- spin_lock_irqsave(&pa_dbit_lock, flags);
+ spin_lock_irqsave(&pa_tlb_lock, flags);
set_pte(ptep, pte_wrprotect(*ptep));
purge_tlb_entries(mm, addr);
- spin_unlock_irqrestore(&pa_dbit_lock, flags);
+ spin_unlock_irqrestore(&pa_tlb_lock, flags);
}
#define pte_same(A,B) (pte_val(A) == pte_val(B))
* active at any one time on the Merced bus. This tlb purge
* synchronisation is fairly lightweight and harmless so we activate
* it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
*/
extern spinlock_t pa_tlb_lock;
#define smp_flush_tlb_all() flush_tlb_all()
+int __flush_tlb_range(unsigned long sid,
+ unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+ __flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+ __flush_tlb_range(0, start, end)
+
/*
* flush_tlb_mm()
*
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's. Thus, we have to preserve the
+ * space and just flush the entire tlb. However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
*/
static inline void flush_tlb_mm(struct mm_struct *mm)
BUG_ON(mm == &init_mm); /* Should never happen */
#if 1 || defined(CONFIG_SMP)
+ /* Except for very small threads, flushing the whole TLB is
+ * faster than using __flush_tlb_range. The pdtlb and pitlb
+ * instructions are very slow because of the TLB broadcast.
+ * It might be faster to do local range flushes on all CPUs
+ * on PA 2.0 systems.
+ */
flush_tlb_all();
#else
/* FIXME: currently broken, causing space id and protection ids
- * to go out of sync, resulting in faults on userspace accesses.
+ * to go out of sync, resulting in faults on userspace accesses.
+ * This approach needs further investigation since running many
+ * small applications (e.g., GCC testsuite) is faster on HP-UX.
*/
if (mm) {
if (mm->context != 0)
{
unsigned long flags, sid;
- /* For one page, it's not worth testing the split_tlb variable */
-
- mb();
sid = vma->vm_mm->context;
purge_tlb_start(flags);
mtsp(sid, 1);
pdtlb(addr);
- pitlb(addr);
+ if (unlikely(split_tlb))
+ pitlb(addr);
purge_tlb_end(flags);
}
-
-void __flush_tlb_range(unsigned long sid,
- unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
#endif
EXPORT_SYMBOL(flush_kernel_icache_range_asm);
#define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
-int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+
+#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
void __init parisc_setup_cache_timing(void)
{
unsigned long rangetime, alltime;
- unsigned long size;
+ unsigned long size, start;
alltime = mfctl(16);
flush_data_cache();
/* Racy, but if we see an intermediate value, it's ok too... */
parisc_cache_flush_threshold = size * alltime / rangetime;
- parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1);
+ parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
if (!parisc_cache_flush_threshold)
parisc_cache_flush_threshold = FLUSH_THRESHOLD;
if (parisc_cache_flush_threshold > cache_info.dc_size)
parisc_cache_flush_threshold = cache_info.dc_size;
- printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
+ printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+ parisc_cache_flush_threshold/1024);
+
+ /* calculate TLB flush threshold */
+
+ alltime = mfctl(16);
+ flush_tlb_all();
+ alltime = mfctl(16) - alltime;
+
+ size = PAGE_SIZE;
+ start = (unsigned long) _text;
+ rangetime = mfctl(16);
+ while (start < (unsigned long) _end) {
+ flush_tlb_kernel_range(start, start + PAGE_SIZE);
+ start += PAGE_SIZE;
+ size += PAGE_SIZE;
+ }
+ rangetime = mfctl(16) - rangetime;
+
+ printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+ alltime, size, rangetime);
+
+ parisc_tlb_flush_threshold = size * alltime / rangetime;
+ parisc_tlb_flush_threshold *= num_online_cpus();
+ parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
+ if (!parisc_tlb_flush_threshold)
+ parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+
+ printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+ parisc_tlb_flush_threshold/1024);
}
extern void purge_kernel_dcache_page_asm(unsigned long);
}
EXPORT_SYMBOL(copy_user_page);
-void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
-{
- unsigned long flags;
-
- /* Note: purge_tlb_entries can be called at startup with
- no context. */
-
- purge_tlb_start(flags);
- mtsp(mm->context, 1);
- pdtlb(addr);
- pitlb(addr);
- purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(purge_tlb_entries);
-
-void __flush_tlb_range(unsigned long sid, unsigned long start,
- unsigned long end)
+/* __flush_tlb_range()
+ *
+ * returns 1 if all TLBs were flushed.
+ */
+int __flush_tlb_range(unsigned long sid, unsigned long start,
+ unsigned long end)
{
- unsigned long npages;
+ unsigned long flags, size;
- npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
- if (npages >= 512) /* 2MB of space: arbitrary, should be tuned */
+ size = (end - start);
+ if (size >= parisc_tlb_flush_threshold) {
flush_tlb_all();
- else {
- unsigned long flags;
+ return 1;
+ }
+ /* Purge TLB entries for small ranges using the pdtlb and
+ pitlb instructions. These instructions execute locally
+ but cause a purge request to be broadcast to other TLBs. */
+ if (likely(!split_tlb)) {
+ while (start < end) {
+ purge_tlb_start(flags);
+ mtsp(sid, 1);
+ pdtlb(start);
+ purge_tlb_end(flags);
+ start += PAGE_SIZE;
+ }
+ return 0;
+ }
+
+ /* split TLB case */
+ while (start < end) {
purge_tlb_start(flags);
mtsp(sid, 1);
- if (split_tlb) {
- while (npages--) {
- pdtlb(start);
- pitlb(start);
- start += PAGE_SIZE;
- }
- } else {
- while (npages--) {
- pdtlb(start);
- start += PAGE_SIZE;
- }
- }
+ pdtlb(start);
+ pitlb(start);
purge_tlb_end(flags);
+ start += PAGE_SIZE;
}
+ return 0;
}
static void cacheflush_h_tmp_function(void *dummy)
.level 2.0
#endif
- .import pa_dbit_lock,data
+ .import pa_tlb_lock,data
/* space_to_prot macro creates a prot id from a space id */
SHLREG %r9,PxD_VALUE_SHIFT,\pmd
extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */
- shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd
- LDREG %r0(\pmd),\pte /* pmd is now pte */
+ shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
+ LDREG %r0(\pmd),\pte
bb,>=,n \pte,_PAGE_PRESENT_BIT,\fault
.endm
L2_ptep \pgd,\pte,\index,\va,\fault
.endm
- /* Acquire pa_dbit_lock lock. */
- .macro dbit_lock spc,tmp,tmp1
+ /* Acquire pa_tlb_lock lock and recheck page is still present. */
+ .macro tlb_lock spc,ptp,pte,tmp,tmp1,fault
#ifdef CONFIG_SMP
cmpib,COND(=),n 0,\spc,2f
- load32 PA(pa_dbit_lock),\tmp
+ load32 PA(pa_tlb_lock),\tmp
1: LDCW 0(\tmp),\tmp1
cmpib,COND(=) 0,\tmp1,1b
nop
+ LDREG 0(\ptp),\pte
+ bb,<,n \pte,_PAGE_PRESENT_BIT,2f
+ b \fault
+ stw \spc,0(\tmp)
2:
#endif
.endm
- /* Release pa_dbit_lock lock without reloading lock address. */
- .macro dbit_unlock0 spc,tmp
+ /* Release pa_tlb_lock lock without reloading lock address. */
+ .macro tlb_unlock0 spc,tmp
#ifdef CONFIG_SMP
or,COND(=) %r0,\spc,%r0
stw \spc,0(\tmp)
#endif
.endm
- /* Release pa_dbit_lock lock. */
- .macro dbit_unlock1 spc,tmp
+ /* Release pa_tlb_lock lock. */
+ .macro tlb_unlock1 spc,tmp
#ifdef CONFIG_SMP
- load32 PA(pa_dbit_lock),\tmp
- dbit_unlock0 \spc,\tmp
+ load32 PA(pa_tlb_lock),\tmp
+ tlb_unlock0 \spc,\tmp
#endif
.endm
/* Set the _PAGE_ACCESSED bit of the PTE. Be clever and
* don't needlessly dirty the cache line if it was already set */
- .macro update_ptep spc,ptep,pte,tmp,tmp1
-#ifdef CONFIG_SMP
- or,COND(=) %r0,\spc,%r0
- LDREG 0(\ptep),\pte
-#endif
+ .macro update_accessed ptp,pte,tmp,tmp1
ldi _PAGE_ACCESSED,\tmp1
or \tmp1,\pte,\tmp
and,COND(<>) \tmp1,\pte,%r0
- STREG \tmp,0(\ptep)
+ STREG \tmp,0(\ptp)
.endm
/* Set the dirty bit (and accessed bit). No need to be
* clever, this is only used from the dirty fault */
- .macro update_dirty spc,ptep,pte,tmp
-#ifdef CONFIG_SMP
- or,COND(=) %r0,\spc,%r0
- LDREG 0(\ptep),\pte
-#endif
+ .macro update_dirty ptp,pte,tmp
ldi _PAGE_ACCESSED|_PAGE_DIRTY,\tmp
or \tmp,\pte,\pte
- STREG \pte,0(\ptep)
+ STREG \pte,0(\ptp)
.endm
/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
L3_ptep ptp,pte,t0,va,dtlb_check_alias_20w
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
idtlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L3_ptep ptp,pte,t0,va,nadtlb_check_alias_20w
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
idtlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,dtlb_check_alias_11
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_11
+ update_accessed ptp,pte,t0,t1
make_insert_tlb_11 spc,pte,prot
- mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */
+ mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */
mtsp spc,%sr1
idtlba pte,(%sr1,va)
idtlbp prot,(%sr1,va)
- mtsp t0, %sr1 /* Restore sr1 */
- dbit_unlock1 spc,t0
+ mtsp t1, %sr1 /* Restore sr1 */
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,nadtlb_check_alias_11
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+ update_accessed ptp,pte,t0,t1
make_insert_tlb_11 spc,pte,prot
-
- mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */
+ mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */
mtsp spc,%sr1
idtlba pte,(%sr1,va)
idtlbp prot,(%sr1,va)
- mtsp t0, %sr1 /* Restore sr1 */
- dbit_unlock1 spc,t0
+ mtsp t1, %sr1 /* Restore sr1 */
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,dtlb_check_alias_20
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
- f_extend pte,t0
+ f_extend pte,t1
idtlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,nadtlb_check_alias_20
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
- f_extend pte,t0
+ f_extend pte,t1
- idtlbt pte,prot
- dbit_unlock1 spc,t0
+ idtlbt pte,prot
+ tlb_unlock1 spc,t0
rfir
nop
L3_ptep ptp,pte,t0,va,itlb_fault
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,itlb_fault
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
iitlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L3_ptep ptp,pte,t0,va,naitlb_check_alias_20w
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
iitlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,itlb_fault
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,itlb_fault
+ update_accessed ptp,pte,t0,t1
make_insert_tlb_11 spc,pte,prot
- mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */
+ mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */
mtsp spc,%sr1
iitlba pte,(%sr1,va)
iitlbp prot,(%sr1,va)
- mtsp t0, %sr1 /* Restore sr1 */
- dbit_unlock1 spc,t0
+ mtsp t1, %sr1 /* Restore sr1 */
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,naitlb_check_alias_11
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_11
+ update_accessed ptp,pte,t0,t1
make_insert_tlb_11 spc,pte,prot
- mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */
+ mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */
mtsp spc,%sr1
iitlba pte,(%sr1,va)
iitlbp prot,(%sr1,va)
- mtsp t0, %sr1 /* Restore sr1 */
- dbit_unlock1 spc,t0
+ mtsp t1, %sr1 /* Restore sr1 */
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,itlb_fault
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,itlb_fault
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
- f_extend pte,t0
+ f_extend pte,t1
iitlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,naitlb_check_alias_20
- dbit_lock spc,t0,t1
- update_ptep spc,ptp,pte,t0,t1
+ tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20
+ update_accessed ptp,pte,t0,t1
make_insert_tlb spc,pte,prot
- f_extend pte,t0
+ f_extend pte,t1
iitlbt pte,prot
- dbit_unlock1 spc,t0
+ tlb_unlock1 spc,t0
rfir
nop
L3_ptep ptp,pte,t0,va,dbit_fault
- dbit_lock spc,t0,t1
- update_dirty spc,ptp,pte,t1
+ tlb_lock spc,ptp,pte,t0,t1,dbit_fault
+ update_dirty ptp,pte,t1
make_insert_tlb spc,pte,prot
idtlbt pte,prot
- dbit_unlock0 spc,t0
+ tlb_unlock0 spc,t0
rfir
nop
#else
L2_ptep ptp,pte,t0,va,dbit_fault
- dbit_lock spc,t0,t1
- update_dirty spc,ptp,pte,t1
+ tlb_lock spc,ptp,pte,t0,t1,dbit_fault
+ update_dirty ptp,pte,t1
make_insert_tlb_11 spc,pte,prot
idtlbp prot,(%sr1,va)
mtsp t1, %sr1 /* Restore sr1 */
- dbit_unlock0 spc,t0
+ tlb_unlock0 spc,t0
rfir
nop
L2_ptep ptp,pte,t0,va,dbit_fault
- dbit_lock spc,t0,t1
- update_dirty spc,ptp,pte,t1
+ tlb_lock spc,ptp,pte,t0,t1,dbit_fault
+ update_dirty ptp,pte,t1
make_insert_tlb spc,pte,prot
f_extend pte,t1
- idtlbt pte,prot
- dbit_unlock0 spc,t0
+ idtlbt pte,prot
+ tlb_unlock0 spc,t0
rfir
nop
#endif
#include "../math-emu/math-emu.h" /* for handle_fpe() */
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-DEFINE_SPINLOCK(pa_dbit_lock);
-#endif
-
static void parisc_show_stack(struct task_struct *task, unsigned long *sp,
struct pt_regs *regs);
.text
/*
+ * Used by threads when the lock bit of core_idle_state is set.
+ * Threads will spin in HMT_LOW until the lock bit is cleared.
+ * r14 - pointer to core_idle_state
+ * r15 - used to load contents of core_idle_state
+ */
+
+core_idle_lock_held:
+ HMT_LOW
+3: lwz r15,0(r14)
+ andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ bne 3b
+ HMT_MEDIUM
+ lwarx r15,0,r14
+ blr
+
+/*
* Pass requested state in r3:
* r3 - PNV_THREAD_NAP/SLEEP/WINKLE
*
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
lwarx_loop1:
lwarx r15,0,r14
+
+ andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ bnel core_idle_lock_held
+
andc r15,r15,r7 /* Clear thread bit */
andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
* workaround undo code or resyncing timebase or restoring context
* In either case loop until the lock bit is cleared.
*/
- bne core_idle_lock_held
+ bnel core_idle_lock_held
cmpwi cr2,r15,0
lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
isync
b common_exit
-core_idle_lock_held:
- HMT_LOW
-core_idle_lock_loop:
- lwz r15,0(14)
- andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
- bne core_idle_lock_loop
- HMT_MEDIUM
- b lwarx_loop2
-
first_thread_in_subcore:
/* First thread in subcore to wakeup */
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
__this_cpu_inc(irq_stat.mce_exceptions);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
handled = cur_cpu_spec->machine_check_early(regs);
return handled;
printk(KERN_ALERT "Unable to handle kernel paging request for "
"instruction fetch\n");
break;
+ case 0x600:
+ printk(KERN_ALERT "Unable to handle kernel paging request for "
+ "unaligned access at address 0x%08lx\n", regs->dar);
+ break;
default:
printk(KERN_ALERT "Unable to handle kernel paging request for "
"unknown fault\n");
if (!attr)
return NULL;
+ sysfs_attr_init(&attr->attr.attr);
+
attr->var = str;
attr->attr.attr.name = name;
attr->attr.attr.mode = 0444;
return elog;
}
-static void elog_work_fn(struct work_struct *work)
+static irqreturn_t elog_event(int irq, void *data)
{
__be64 size;
__be64 id;
rc = opal_get_elog_size(&id, &size, &type);
if (rc != OPAL_SUCCESS) {
pr_err("ELOG: OPAL log info read failed\n");
- return;
+ return IRQ_HANDLED;
}
elog_size = be64_to_cpu(size);
* entries.
*/
if (kset_find_obj(elog_kset, name))
- return;
+ return IRQ_HANDLED;
create_elog_obj(log_id, elog_size, elog_type);
-}
-
-static DECLARE_WORK(elog_work, elog_work_fn);
-static irqreturn_t elog_event(int irq, void *data)
-{
- schedule_work(&elog_work);
return IRQ_HANDLED;
}
return irq;
}
- rc = request_irq(irq, elog_event,
- IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
+ rc = request_threaded_irq(irq, NULL, elog_event,
+ IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "opal-elog", NULL);
if (rc) {
pr_err("%s: Can't request OPAL event irq (%d)\n",
__func__, rc);
static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
{
size_t addr, size;
+ pgprot_t page_prot;
int rc;
pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
if (!opal_prd_range_is_valid(addr, size))
return -EINVAL;
- vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
- vma->vm_pgoff,
- size, vma->vm_page_prot))
- | _PAGE_SPECIAL);
+ page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
+ size, vma->vm_page_prot);
rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
- vma->vm_page_prot);
+ page_prot);
return rc;
}
#include <linux/pci.h>
#include <linux/semaphore.h>
#include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
struct ppc4xx_hsta_msi {
struct device *dev;
#define _ST(p, inst, v) \
({ \
asm("1: " #inst " %0, %1;" \
- ".pushsection .coldtext.memcpy,\"ax\";" \
+ ".pushsection .coldtext,\"ax\";" \
"2: { move r0, %2; jrp lr };" \
".section __ex_table,\"a\";" \
".align 8;" \
({ \
unsigned long __v; \
asm("1: " #inst " %0, %1;" \
- ".pushsection .coldtext.memcpy,\"ax\";" \
+ ".pushsection .coldtext,\"ax\";" \
"2: { move r0, %2; jrp lr };" \
".section __ex_table,\"a\";" \
".align 8;" \
unsigned long ret;
if (__range_not_ok(from, n, TASK_SIZE))
- return 0;
+ return n;
/*
* Even though this function is typically called from NMI/IRQ context
pdata->mmio_size = resource_size(rentry->res);
pdata->mmio_base = ioremap(rentry->res->start,
pdata->mmio_size);
- if (!pdata->mmio_base)
- goto err_out;
break;
}
acpi_dev_free_resource_list(&resource_list);
+ if (!pdata->mmio_base) {
+ ret = -ENOMEM;
+ goto err_out;
+ }
+
pdata->dev_desc = dev_desc;
if (dev_desc->setup)
if (!addr || !length)
return;
- acpi_reserve_region(addr, length, gas->space_id, 0, desc);
+ /* Resources are never freed */
+ if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+ request_region(addr, length, desc);
+ else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+ request_mem_region(addr, length, desc);
}
-static void __init acpi_reserve_resources(void)
+static int __init acpi_reserve_resources(void)
{
acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
"ACPI PM1a_EVT_BLK");
if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
+
+ return 0;
}
+fs_initcall_sync(acpi_reserve_resources);
void acpi_os_printf(const char *fmt, ...)
{
acpi_status __init acpi_os_initialize1(void)
{
- acpi_reserve_resources();
kacpid_wq = alloc_workqueue("kacpid", 0, 1);
kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
#include <linux/device.h>
#include <linux/export.h>
#include <linux/ioport.h>
-#include <linux/list.h>
#include <linux/slab.h>
#ifdef CONFIG_X86
return (type & types) ? 0 : 1;
}
EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
-
-struct reserved_region {
- struct list_head node;
- u64 start;
- u64 end;
-};
-
-static LIST_HEAD(reserved_io_regions);
-static LIST_HEAD(reserved_mem_regions);
-
-static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags,
- char *desc)
-{
- unsigned int length = end - start + 1;
- struct resource *res;
-
- res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ?
- request_region(start, length, desc) :
- request_mem_region(start, length, desc);
- if (!res)
- return -EIO;
-
- res->flags &= ~flags;
- return 0;
-}
-
-static int add_region_before(u64 start, u64 end, u8 space_id,
- unsigned long flags, char *desc,
- struct list_head *head)
-{
- struct reserved_region *reg;
- int error;
-
- reg = kmalloc(sizeof(*reg), GFP_KERNEL);
- if (!reg)
- return -ENOMEM;
-
- error = request_range(start, end, space_id, flags, desc);
- if (error) {
- kfree(reg);
- return error;
- }
-
- reg->start = start;
- reg->end = end;
- list_add_tail(®->node, head);
- return 0;
-}
-
-/**
- * acpi_reserve_region - Reserve an I/O or memory region as a system resource.
- * @start: Starting address of the region.
- * @length: Length of the region.
- * @space_id: Identifier of address space to reserve the region from.
- * @flags: Resource flags to clear for the region after requesting it.
- * @desc: Region description (for messages).
- *
- * Reserve an I/O or memory region as a system resource to prevent others from
- * using it. If the new region overlaps with one of the regions (in the given
- * address space) already reserved by this routine, only the non-overlapping
- * parts of it will be reserved.
- *
- * Returned is either 0 (success) or a negative error code indicating a resource
- * reservation problem. It is the code of the first encountered error, but the
- * routine doesn't abort until it has attempted to request all of the parts of
- * the new region that don't overlap with other regions reserved previously.
- *
- * The resources requested by this routine are never released.
- */
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
- unsigned long flags, char *desc)
-{
- struct list_head *regions;
- struct reserved_region *reg;
- u64 end = start + length - 1;
- int ret = 0, error = 0;
-
- if (space_id == ACPI_ADR_SPACE_SYSTEM_IO)
- regions = &reserved_io_regions;
- else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
- regions = &reserved_mem_regions;
- else
- return -EINVAL;
-
- if (list_empty(regions))
- return add_region_before(start, end, space_id, flags, desc, regions);
-
- list_for_each_entry(reg, regions, node)
- if (reg->start == end + 1) {
- /* The new region can be prepended to this one. */
- ret = request_range(start, end, space_id, flags, desc);
- if (!ret)
- reg->start = start;
-
- return ret;
- } else if (reg->start > end) {
- /* No overlap. Add the new region here and get out. */
- return add_region_before(start, end, space_id, flags,
- desc, ®->node);
- } else if (reg->end == start - 1) {
- goto combine;
- } else if (reg->end >= start) {
- goto overlap;
- }
-
- /* The new region goes after the last existing one. */
- return add_region_before(start, end, space_id, flags, desc, regions);
-
- overlap:
- /*
- * The new region overlaps an existing one.
- *
- * The head part of the new region immediately preceding the existing
- * overlapping one can be combined with it right away.
- */
- if (reg->start > start) {
- error = request_range(start, reg->start - 1, space_id, flags, desc);
- if (error)
- ret = error;
- else
- reg->start = start;
- }
-
- combine:
- /*
- * The new region is adjacent to an existing one. If it extends beyond
- * that region all the way to the next one, it is possible to combine
- * all three of them.
- */
- while (reg->end < end) {
- struct reserved_region *next = NULL;
- u64 a = reg->end + 1, b = end;
-
- if (!list_is_last(®->node, regions)) {
- next = list_next_entry(reg, node);
- if (next->start <= end)
- b = next->start - 1;
- }
- error = request_range(a, b, space_id, flags, desc);
- if (!error) {
- if (next && next->start == b + 1) {
- reg->end = next->end;
- list_del(&next->node);
- kfree(next);
- } else {
- reg->end = end;
- break;
- }
- } else if (next) {
- if (!ret)
- ret = error;
-
- reg = next;
- } else {
- break;
- }
- }
-
- return ret ? ret : error;
-}
-EXPORT_SYMBOL_GPL(acpi_reserve_region);
return false;
}
+static bool __acpi_match_device_cls(const struct acpi_device_id *id,
+ struct acpi_hardware_id *hwid)
+{
+ int i, msk, byte_shift;
+ char buf[3];
+
+ if (!id->cls)
+ return false;
+
+ /* Apply class-code bitmask, before checking each class-code byte */
+ for (i = 1; i <= 3; i++) {
+ byte_shift = 8 * (3 - i);
+ msk = (id->cls_msk >> byte_shift) & 0xFF;
+ if (!msk)
+ continue;
+
+ sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
+ if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
+ return false;
+ }
+ return true;
+}
+
static const struct acpi_device_id *__acpi_match_device(
struct acpi_device *device,
const struct acpi_device_id *ids,
list_for_each_entry(hwid, &device->pnp.ids, list) {
/* First, check the ACPI/PNP IDs provided by the caller. */
- for (id = ids; id->id[0]; id++)
- if (!strcmp((char *) id->id, hwid->id))
+ for (id = ids; id->id[0] || id->cls; id++) {
+ if (id->id[0] && !strcmp((char *) id->id, hwid->id))
return id;
+ else if (id->cls && __acpi_match_device_cls(id, hwid))
+ return id;
+ }
/*
* Next, check ACPI_DT_NAMESPACE_HID and try to match the
if (info->valid & ACPI_VALID_UID)
pnp->unique_id = kstrdup(info->unique_id.string,
GFP_KERNEL);
+ if (info->valid & ACPI_VALID_CLS)
+ acpi_add_id(pnp, info->class_code.string);
kfree(info);
config ATA_ACPI
bool "ATA ACPI Support"
- depends on ACPI && PCI
+ depends on ACPI
default y
help
This option adds support for ATA-related ACPI objects.
#include <linux/platform_device.h>
#include <linux/libata.h>
#include <linux/ahci_platform.h>
+#include <linux/acpi.h>
+#include <linux/pci_ids.h>
#include "ahci.h"
#define DRV_NAME "ahci"
};
MODULE_DEVICE_TABLE(of, ahci_of_match);
+static const struct acpi_device_id ahci_acpi_match[] = {
+ { ACPI_DEVICE_CLASS(PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff) },
+ {},
+};
+MODULE_DEVICE_TABLE(acpi, ahci_acpi_match);
+
static struct platform_driver ahci_driver = {
.probe = ahci_probe,
.remove = ata_platform_remove_one,
.driver = {
.name = DRV_NAME,
.of_match_table = ahci_of_match,
+ .acpi_match_table = ahci_acpi_match,
.pm = &ahci_pm_ops,
},
};
kfree(fw_priv);
}
-static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
{
- struct firmware_priv *fw_priv = to_firmware_priv(dev);
-
if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
return -ENOMEM;
if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
return 0;
}
+static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct firmware_priv *fw_priv = to_firmware_priv(dev);
+ int err = 0;
+
+ mutex_lock(&fw_lock);
+ if (fw_priv->buf)
+ err = do_firmware_uevent(fw_priv, env);
+ mutex_unlock(&fw_lock);
+ return err;
+}
+
static struct class firmware_class = {
.name = "firmware",
.class_attrs = firmware_class_attrs,
* This file is released under the GPLv2.
*/
+#include <linux/delay.h>
#include <linux/kernel.h>
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/suspend.h>
#include <linux/export.h>
+#define GENPD_RETRY_MAX_MS 250 /* Approximate */
+
#define GENPD_DEV_CALLBACK(genpd, type, callback, dev) \
({ \
type (*__routine)(struct device *__d); \
static void genpd_dev_pm_detach(struct device *dev, bool power_off)
{
struct generic_pm_domain *pd;
+ unsigned int i;
int ret = 0;
pd = pm_genpd_lookup_dev(dev);
dev_dbg(dev, "removing from PM domain %s\n", pd->name);
- while (1) {
+ for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
ret = pm_genpd_remove_device(pd, dev);
if (ret != -EAGAIN)
break;
+
+ mdelay(i);
cond_resched();
}
{
struct of_phandle_args pd_args;
struct generic_pm_domain *pd;
+ unsigned int i;
int ret;
if (!dev->of_node)
dev_dbg(dev, "adding to PM domain %s\n", pd->name);
- while (1) {
+ for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
ret = pm_genpd_add_device(pd, dev);
if (ret != -EAGAIN)
break;
+
+ mdelay(i);
cond_resched();
}
return -EEXIST;
}
- dev->power.wakeirq = wirq;
- spin_unlock_irqrestore(&dev->power.lock, flags);
-
err = device_wakeup_attach_irq(dev, wirq);
- if (err)
- return err;
+ if (!err)
+ dev->power.wakeirq = wirq;
- return 0;
+ spin_unlock_irqrestore(&dev->power.lock, flags);
+ return err;
}
/**
return;
spin_lock_irqsave(&dev->power.lock, flags);
+ device_wakeup_detach_irq(dev);
dev->power.wakeirq = NULL;
spin_unlock_irqrestore(&dev->power.lock, flags);
- device_wakeup_detach_irq(dev);
if (wirq->dedicated_irq)
free_irq(wirq->irq, wirq);
kfree(wirq);
* Attach a device wakeirq to the wakeup source so the device
* wake IRQ can be configured automatically for suspend and
* resume.
+ *
+ * Call under the device's power.lock lock.
*/
int device_wakeup_attach_irq(struct device *dev,
struct wake_irq *wakeirq)
{
struct wakeup_source *ws;
- int ret = 0;
- spin_lock_irq(&dev->power.lock);
ws = dev->power.wakeup;
if (!ws) {
dev_err(dev, "forgot to call call device_init_wakeup?\n");
- ret = -EINVAL;
- goto unlock;
+ return -EINVAL;
}
- if (ws->wakeirq) {
- ret = -EEXIST;
- goto unlock;
- }
+ if (ws->wakeirq)
+ return -EEXIST;
ws->wakeirq = wakeirq;
-
-unlock:
- spin_unlock_irq(&dev->power.lock);
-
- return ret;
+ return 0;
}
/**
* @dev: Device to handle
*
* Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
*/
void device_wakeup_detach_irq(struct device *dev)
{
struct wakeup_source *ws;
- spin_lock_irq(&dev->power.lock);
ws = dev->power.wakeup;
- if (!ws)
- goto unlock;
-
- ws->wakeirq = NULL;
-
-unlock:
- spin_unlock_irq(&dev->power.lock);
+ if (ws)
+ ws->wakeirq = NULL;
}
/**
processor = (struct acpi_madt_generic_interrupt *)header;
- if (BAD_MADT_ENTRY(processor, end))
+ if (BAD_MADT_GICC_ENTRY(processor, end))
return -EINVAL;
/*
afu = cxl_pci_to_afu(dev);
+ get_device(&afu->dev);
ctx = cxl_context_alloc();
if (IS_ERR(ctx))
return ctx;
rc = cxl_context_init(ctx, afu, false, NULL);
if (rc) {
kfree(ctx);
+ put_device(&afu->dev);
return ERR_PTR(-ENOMEM);
}
cxl_assign_psn_space(ctx);
if (ctx->status != CLOSED)
return -EBUSY;
+ put_device(&ctx->afu->dev);
+
cxl_context_free(ctx);
return 0;
}
ctx->status = STARTED;
- get_device(&ctx->afu->dev);
out:
mutex_unlock(&ctx->status_mutex);
return rc;
/* Stop a context. Returns 0 on success, otherwise -Errno */
int cxl_stop_context(struct cxl_context *ctx)
{
- int rc;
-
- rc = __detach_context(ctx);
- if (!rc)
- put_device(&ctx->afu->dev);
- return rc;
+ return __detach_context(ctx);
}
EXPORT_SYMBOL_GPL(cxl_stop_context);
if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
area = ctx->afu->psn_phys;
- if (offset > ctx->afu->adapter->ps_size)
+ if (offset >= ctx->afu->adapter->ps_size)
return VM_FAULT_SIGBUS;
} else {
area = ctx->psn_phys;
- if (offset > ctx->psn_size)
+ if (offset >= ctx->psn_size)
return VM_FAULT_SIGBUS;
}
*/
int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
{
+ u64 start = vma->vm_pgoff << PAGE_SHIFT;
u64 len = vma->vm_end - vma->vm_start;
- len = min(len, ctx->psn_size);
+
+ if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
+ if (start + len > ctx->afu->adapter->ps_size)
+ return -EINVAL;
+ } else {
+ if (start + len > ctx->psn_size)
+ return -EINVAL;
+ }
if (ctx->afu->current_mode != CXL_MODE_DEDICATED) {
/* make sure there is a valid per process space for this AFU */
spin_lock(&adapter->afu_list_lock);
for (slice = 0; slice < adapter->slices; slice++) {
afu = adapter->afu[slice];
- if (!afu->enabled)
+ if (!afu || !afu->enabled)
continue;
rcu_read_lock();
idr_for_each_entry(&afu->contexts_idr, ctx, id)
static void cxl_unmap_slice_regs(struct cxl_afu *afu)
{
- if (afu->p1n_mmio)
+ if (afu->p2n_mmio)
iounmap(afu->p2n_mmio);
if (afu->p1n_mmio)
iounmap(afu->p1n_mmio);
unsigned long addr;
phb = pci_bus_to_host(bus);
- afu = (struct cxl_afu *)phb->private_data;
if (phb == NULL)
return PCIBIOS_DEVICE_NOT_FOUND;
+ afu = (struct cxl_afu *)phb->private_data;
+
if (cxl_pcie_cfg_record(bus->number, devfn) > afu->crs_num)
return PCIBIOS_DEVICE_NOT_FOUND;
if (offset >= (unsigned long)phb->cfg_data)
schedule_work(&device->event_work);
}
-void mei_cl_bus_remove_devices(struct mei_device *dev)
-{
- struct mei_cl *cl, *next;
-
- mutex_lock(&dev->device_lock);
- list_for_each_entry_safe(cl, next, &dev->device_list, device_link) {
- if (cl->device)
- mei_cl_remove_device(cl->device);
-
- list_del(&cl->device_link);
- mei_cl_unlink(cl);
- kfree(cl);
- }
- mutex_unlock(&dev->device_lock);
-}
-
int __init mei_cl_bus_init(void)
{
return bus_register(&mei_cl_bus_type);
mei_nfc_host_exit(dev);
- mei_cl_bus_remove_devices(dev);
-
mutex_lock(&dev->device_lock);
mei_wd_stop(dev);
cldev->priv_data = NULL;
- mutex_lock(&dev->device_lock);
/* Need to remove the device here
* since mei_nfc_free will unlink the clients
*/
mei_cl_remove_device(cldev);
+
+ mutex_lock(&dev->device_lock);
mei_nfc_free(ndev);
mutex_unlock(&dev->device_lock);
}
* Bjorn Helgaas <bjorn.helgaas@hp.com>
*/
-#include <linux/acpi.h>
#include <linux/pnp.h>
#include <linux/device.h>
#include <linux/init.h>
{"", 0}
};
-#ifdef CONFIG_ACPI
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
- u8 space_id = io ? ACPI_ADR_SPACE_SYSTEM_IO : ACPI_ADR_SPACE_SYSTEM_MEMORY;
- return !acpi_reserve_region(start, length, space_id, IORESOURCE_BUSY, desc);
-}
-#else
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
- struct resource *res;
-
- res = io ? request_region(start, length, desc) :
- request_mem_region(start, length, desc);
- if (res) {
- res->flags &= ~IORESOURCE_BUSY;
- return true;
- }
- return false;
-}
-#endif
-
static void reserve_range(struct pnp_dev *dev, struct resource *r, int port)
{
char *regionid;
const char *pnpid = dev_name(&dev->dev);
resource_size_t start = r->start, end = r->end;
- bool reserved;
+ struct resource *res;
regionid = kmalloc(16, GFP_KERNEL);
if (!regionid)
return;
snprintf(regionid, 16, "pnp %s", pnpid);
- reserved = __reserve_range(start, end - start + 1, !!port, regionid);
- if (!reserved)
+ if (port)
+ res = request_region(start, end - start + 1, regionid);
+ else
+ res = request_mem_region(start, end - start + 1, regionid);
+ if (res)
+ res->flags &= ~IORESOURCE_BUSY;
+ else
kfree(regionid);
/*
* have double reservations.
*/
dev_info(&dev->dev, "%pR %s reserved\n", r,
- reserved ? "has been" : "could not be");
+ res ? "has been" : "could not be");
}
static void reserve_resources_of_dev(struct pnp_dev *dev)
#define REG_3 0x0004a0
#define REG_4 0x000600
#define REG_6 0x000800
+#define REG_7 0x000804
#define REG_8 0x000820
#define REG_9 0x000a04
#define REG_10 0x018000
#define REG_21 0x200218
#define REG_22 0x0005a0
#define REG_23 0x0005c0
+#define REG_24 0x000808
+#define REG_25 0x000b00
#define REG_26 0x200118
#define REG_27 0x200308
#define REG_32 0x21003c
#define SET_LENXY_START_RECFILL(fb, lenxy) \
WRITE_WORD(lenxy, fb, REG_9)
+#define SETUP_COPYAREA(fb) \
+ WRITE_BYTE(0, fb, REG_16b1)
+
static void
HYPER_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable)
{
return 0;
}
+static void
+stifb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
+{
+ struct stifb_info *fb = container_of(info, struct stifb_info, info);
+
+ SETUP_COPYAREA(fb);
+
+ SETUP_HW(fb);
+ if (fb->info.var.bits_per_pixel == 32) {
+ WRITE_WORD(0xBBA0A000, fb, REG_10);
+
+ NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xffffffff);
+ } else {
+ WRITE_WORD(fb->id == S9000_ID_HCRX ? 0x13a02000 : 0x13a01000, fb, REG_10);
+
+ NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xff);
+ }
+
+ NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb,
+ IBOvals(RopSrc, MaskAddrOffset(0),
+ BitmapExtent08, StaticReg(1),
+ DataDynamic, MaskOtc, BGx(0), FGx(0)));
+
+ WRITE_WORD(((area->sx << 16) | area->sy), fb, REG_24);
+ WRITE_WORD(((area->width << 16) | area->height), fb, REG_7);
+ WRITE_WORD(((area->dx << 16) | area->dy), fb, REG_25);
+
+ SETUP_FB(fb);
+}
+
static void __init
stifb_init_display(struct stifb_info *fb)
{
.fb_setcolreg = stifb_setcolreg,
.fb_blank = stifb_blank,
.fb_fillrect = cfb_fillrect,
- .fb_copyarea = cfb_copyarea,
+ .fb_copyarea = stifb_copyarea,
.fb_imageblit = cfb_imageblit,
};
info->fbops = &stifb_ops;
info->screen_base = ioremap_nocache(REGION_BASE(fb,1), fix->smem_len);
info->screen_size = fix->smem_len;
- info->flags = FBINFO_DEFAULT;
+ info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA;
info->pseudo_palette = &fb->pseudo_palette;
/* This has to be done !!! */
/* 'X' - originally XFS but some now in the VFS */
COMPATIBLE_IOCTL(FIFREEZE)
COMPATIBLE_IOCTL(FITHAW)
+COMPATIBLE_IOCTL(FITRIM)
COMPATIBLE_IOCTL(KDGETKEYCODE)
COMPATIBLE_IOCTL(KDSETKEYCODE)
COMPATIBLE_IOCTL(KDGKBTYPE)
return rc;
switch (cmd) {
- case FITRIM:
case FS_IOC32_GETFLAGS:
case FS_IOC32_SETFLAGS:
case FS_IOC32_GETVERSION:
struct buffer_head *bh;
int err;
- bh = sb_getblk(inode->i_sb, pblk);
+ bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
err = -EIO;
goto cleanup;
}
- bh = sb_getblk(inode->i_sb, newblock);
+ bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh)) {
err = -ENOMEM;
goto cleanup;
if (newblock == 0)
return err;
- bh = sb_getblk(inode->i_sb, newblock);
+ bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh))
return -ENOMEM;
lock_buffer(bh);
unsigned int offset,
unsigned int length)
{
- int to_release = 0;
+ int to_release = 0, contiguous_blks = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
struct inode *inode = page->mapping->host;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
+ contiguous_blks++;
clear_buffer_delay(bh);
+ } else if (contiguous_blks) {
+ lblk = page->index <<
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ lblk += (curr_off >> inode->i_blkbits) -
+ contiguous_blks;
+ ext4_es_remove_extent(inode, lblk, contiguous_blks);
+ contiguous_blks = 0;
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- if (to_release) {
+ if (contiguous_blks) {
lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- ext4_es_remove_extent(inode, lblk, to_release);
+ lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+ ext4_es_remove_extent(inode, lblk, contiguous_blks);
}
/* If we have released all the blocks belonging to a cluster, then we
int inode_size = EXT4_INODE_SIZE(sb);
oi.orig_ino = orig_ino;
- ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
+ /*
+ * Calculate the first inode in the inode table block. Inode
+ * numbers are one-based. That is, the first inode in a block
+ * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
+ */
+ ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
return err;
}
case EXT4_IOC_MOVE_EXT:
- case FITRIM:
case EXT4_IOC_RESIZE_FS:
case EXT4_IOC_PRECACHE_EXTENTS:
case EXT4_IOC_SET_ENCRYPTION_POLICY:
/*
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
+ *
+ * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+ * to fail.
*/
- retry:
- new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
- if (!new_entry) {
- /*
- * We use a retry loop because
- * ext4_free_blocks() is not allowed to fail.
- */
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, HZ/50);
- goto retry;
- }
+ new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+ GFP_NOFS|__GFP_NOFAIL);
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
new_entry->efd_count = count_clusters;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
+ ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
+ /*
+ * In order to get correct extent info, force all delayed allocation
+ * blocks to be allocated, otherwise delayed allocation blocks may not
+ * be reflected and bypass the checks on extent header.
+ */
+ if (test_opt(inode->i_sb, DELALLOC))
+ ext4_alloc_da_blocks(inode);
+
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
goto errout;
}
if (eh->eh_entries == 0)
- blk = len = 0;
+ blk = len = start = end = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
- if (len > EXT4_NDIR_BLOCKS) {
+ start = le32_to_cpu(ex->ee_block);
+ end = start + len - 1;
+ if (end >= EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
- for (i=0; i < len; i++)
+ for (i = start; i <= end; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
a->btree.first_free = cpu_to_le16(8);
return a;
}
+
+static unsigned find_run(__le32 *bmp, unsigned *idx)
+{
+ unsigned len;
+ while (tstbits(bmp, *idx, 1)) {
+ (*idx)++;
+ if (unlikely(*idx >= 0x4000))
+ return 0;
+ }
+ len = 1;
+ while (!tstbits(bmp, *idx + len, 1))
+ len++;
+ return len;
+}
+
+static int do_trim(struct super_block *s, secno start, unsigned len, secno limit_start, secno limit_end, unsigned minlen, unsigned *result)
+{
+ int err;
+ secno end;
+ if (fatal_signal_pending(current))
+ return -EINTR;
+ end = start + len;
+ if (start < limit_start)
+ start = limit_start;
+ if (end > limit_end)
+ end = limit_end;
+ if (start >= end)
+ return 0;
+ if (end - start < minlen)
+ return 0;
+ err = sb_issue_discard(s, start, end - start, GFP_NOFS, 0);
+ if (err)
+ return err;
+ *result += end - start;
+ return 0;
+}
+
+int hpfs_trim_fs(struct super_block *s, u64 start, u64 end, u64 minlen, unsigned *result)
+{
+ int err = 0;
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ unsigned idx, len, start_bmp, end_bmp;
+ __le32 *bmp;
+ struct quad_buffer_head qbh;
+
+ *result = 0;
+ if (!end || end > sbi->sb_fs_size)
+ end = sbi->sb_fs_size;
+ if (start >= sbi->sb_fs_size)
+ return 0;
+ if (minlen > 0x4000)
+ return 0;
+ if (start < sbi->sb_dirband_start + sbi->sb_dirband_size && end > sbi->sb_dirband_start) {
+ hpfs_lock(s);
+ if (s->s_flags & MS_RDONLY) {
+ err = -EROFS;
+ goto unlock_1;
+ }
+ if (!(bmp = hpfs_map_dnode_bitmap(s, &qbh))) {
+ err = -EIO;
+ goto unlock_1;
+ }
+ idx = 0;
+ while ((len = find_run(bmp, &idx)) && !err) {
+ err = do_trim(s, sbi->sb_dirband_start + idx * 4, len * 4, start, end, minlen, result);
+ idx += len;
+ }
+ hpfs_brelse4(&qbh);
+unlock_1:
+ hpfs_unlock(s);
+ }
+ start_bmp = start >> 14;
+ end_bmp = (end + 0x3fff) >> 14;
+ while (start_bmp < end_bmp && !err) {
+ hpfs_lock(s);
+ if (s->s_flags & MS_RDONLY) {
+ err = -EROFS;
+ goto unlock_2;
+ }
+ if (!(bmp = hpfs_map_bitmap(s, start_bmp, &qbh, "trim"))) {
+ err = -EIO;
+ goto unlock_2;
+ }
+ idx = 0;
+ while ((len = find_run(bmp, &idx)) && !err) {
+ err = do_trim(s, (start_bmp << 14) + idx, len, start, end, minlen, result);
+ idx += len;
+ }
+ hpfs_brelse4(&qbh);
+unlock_2:
+ hpfs_unlock(s);
+ start_bmp++;
+ }
+ return err;
+}
.iterate = hpfs_readdir,
.release = hpfs_dir_release,
.fsync = hpfs_file_fsync,
+ .unlocked_ioctl = hpfs_ioctl,
};
.release = hpfs_file_release,
.fsync = hpfs_file_fsync,
.splice_read = generic_file_splice_read,
+ .unlocked_ioctl = hpfs_ioctl,
};
const struct inode_operations hpfs_file_iops =
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/blkdev.h>
#include <asm/unaligned.h>
#include "hpfs.h"
struct dnode *hpfs_alloc_dnode(struct super_block *, secno, dnode_secno *, struct quad_buffer_head *);
struct fnode *hpfs_alloc_fnode(struct super_block *, secno, fnode_secno *, struct buffer_head **);
struct anode *hpfs_alloc_anode(struct super_block *, secno, anode_secno *, struct buffer_head **);
+int hpfs_trim_fs(struct super_block *, u64, u64, u64, unsigned *);
/* anode.c */
void hpfs_error(struct super_block *, const char *, ...);
int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *);
unsigned hpfs_get_free_dnodes(struct super_block *);
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg);
/*
* local time (HPFS) to GMT (Unix)
}
/* Filesystem error... */
-static char err_buf[1024];
-
void hpfs_error(struct super_block *s, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- vsnprintf(err_buf, sizeof(err_buf), fmt, args);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ pr_err("filesystem error: %pV", &vaf);
+
va_end(args);
- pr_err("filesystem error: %s", err_buf);
if (!hpfs_sb(s)->sb_was_error) {
if (hpfs_sb(s)->sb_err == 2) {
pr_cont("; crashing the system because you wanted it\n");
return 0;
}
+
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case FITRIM: {
+ struct fstrim_range range;
+ secno n_trimmed;
+ int r;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
+ return -EFAULT;
+ r = hpfs_trim_fs(file_inode(file)->i_sb, range.start >> 9, (range.start + range.len) >> 9, (range.minlen + 511) >> 9, &n_trimmed);
+ if (r)
+ return r;
+ range.len = (u64)n_trimmed << 9;
+ if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range)))
+ return -EFAULT;
+ return 0;
+ }
+ default: {
+ return -ENOIOCTLCMD;
+ }
+ }
+}
+
+
static struct kmem_cache * hpfs_inode_cachep;
static struct inode *hpfs_alloc_inode(struct super_block *sb)
{
struct hpfs_inode_info *ei;
- ei = (struct hpfs_inode_info *)kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
+ ei = kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
ei->vfs_inode.i_version = 1;
int o;
struct hpfs_sb_info *sbi = hpfs_sb(s);
char *new_opts = kstrdup(data, GFP_KERNEL);
-
+
+ if (!new_opts)
+ return -ENOMEM;
+
sync_filesystem(s);
*flags |= MS_NOATIME;
-
+
hpfs_lock(s);
uid = sbi->sb_uid; gid = sbi->sb_gid;
umask = 0777 & ~sbi->sb_mode;
case JFS_IOC_SETFLAGS32:
cmd = JFS_IOC_SETFLAGS;
break;
- case FITRIM:
- cmd = FITRIM;
- break;
}
return jfs_ioctl(filp, cmd, arg);
}
case NILFS_IOCTL_SYNC:
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
- case FITRIM:
break;
default:
return -ENOIOCTLCMD;
case OCFS2_IOC_GROUP_EXTEND:
case OCFS2_IOC_GROUP_ADD:
case OCFS2_IOC_GROUP_ADD64:
- case FITRIM:
break;
case OCFS2_IOC_REFLINK:
if (copy_from_user(&args, argp, sizeof(args)))
acpi_fwnode_handle(adev) : NULL)
#define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev))
+/**
+ * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with
+ * the PCI-defined class-code information
+ *
+ * @_cls : the class, subclass, prog-if triple for this device
+ * @_msk : the class mask for this device
+ *
+ * This macro is used to create a struct acpi_device_id that matches a
+ * specific PCI class. The .id and .driver_data fields will be left
+ * initialized with the default value.
+ */
+#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk),
+
static inline bool has_acpi_companion(struct device *dev)
{
return is_acpi_node(dev->fwnode);
int acpi_resources_are_enforced(void);
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
- unsigned long flags, char *desc);
-
#ifdef CONFIG_HIBERNATION
void __init acpi_no_s4_hw_signature(void);
#endif
#define ACPI_COMPANION(dev) (NULL)
#define ACPI_COMPANION_SET(dev, adev) do { } while (0)
#define ACPI_HANDLE(dev) (NULL)
+#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0),
struct fwnode_handle;
return 0;
}
-static inline int acpi_reserve_region(u64 start, unsigned int length,
- u8 space_id, unsigned long flags,
- char *desc)
-{
- return -ENXIO;
-}
-
struct acpi_table_header;
static inline int acpi_table_parse(char *id,
int (*handler)(struct acpi_table_header *))
return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
}
+
+static inline struct buffer_head *
+sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+{
+ return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+}
+
static inline struct buffer_head *
sb_find_get_block(struct super_block *sb, sector_t block)
{
#include <linux/radix-tree.h>
#include <linux/uio.h>
#include <linux/workqueue.h>
+#include <net/net_namespace.h>
#include <linux/ceph/types.h>
#include <linux/ceph/buffer.h>
struct ceph_entity_addr my_enc_addr;
atomic_t stopping;
+ possible_net_t net;
bool nocrc;
bool tcp_nodelay;
u64 required_features,
bool nocrc,
bool tcp_nodelay);
+extern void ceph_messenger_fini(struct ceph_messenger *msgr);
extern void ceph_con_init(struct ceph_connection *con, void *private,
const struct ceph_connection_operations *ops,
struct acpi_device_id {
__u8 id[ACPI_ID_LEN];
kernel_ulong_t driver_data;
+ __u32 cls;
+ __u32 cls_msk;
};
#define PNP_ID_LEN 8
* for strings that are too long, we should not have created
* any.
*/
- if (unlikely((len == 0) || len > MAX_ARG_STRLEN - 1)) {
- WARN_ON(1);
+ if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
send_sig(SIGKILL, current, 0);
return -1;
}
rcu_read_unlock();
}
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
- struct ring_buffer *rb;
-
- rb = container_of(rcu_head, struct ring_buffer, rcu_head);
- rb_free(rb);
-}
-
struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
struct ring_buffer *rb;
struct ring_buffer {
atomic_t refcount;
struct rcu_head rcu_head;
+ struct irq_work irq_work;
#ifdef CONFIG_PERF_USE_VMALLOC
struct work_struct work;
int page_order; /* allocation order */
};
extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+ struct ring_buffer *rb;
+
+ rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+ rb_free(rb);
+}
+
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
rcu_read_unlock();
}
+static void rb_irq_work(struct irq_work *work);
+
static void
ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
{
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
+ init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+ if (!atomic_dec_and_test(&rb->refcount))
+ return;
+
+ rb->rcu_head.next = (void *)rb;
+ irq_work_queue(&rb->irq_work);
}
/*
rb_free_aux(rb);
err:
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
handle->event = NULL;
return NULL;
local_set(&rb->aux_nest, 0);
rb_free_aux(rb);
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
}
/*
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
+ irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+ struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+ if (!atomic_read(&rb->aux_refcount))
__rb_free_aux(rb);
+
+ if (rb->rcu_head.next == (void *)rb)
+ call_rcu(&rb->rcu_head, rb_free_rcu);
}
#ifndef CONFIG_PERF_USE_VMALLOC
mutex_lock(&module_mutex);
/* Unlink carefully: kallsyms could be walking list. */
list_del_rcu(&mod->list);
+ mod_tree_remove(mod);
wake_up_all(&module_wq);
/* Wait for RCU-sched synchronizing before releasing mod->list. */
synchronize_sched();
pte_unmap(page_table);
+ /* File mapping without ->vm_ops ? */
+ if (vma->vm_flags & VM_SHARED)
+ return VM_FAULT_SIGBUS;
+
/* Check if we need to add a guard page to the stack */
if (check_stack_guard_page(vma, address) < 0)
return VM_FAULT_SIGSEGV;
- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
pte_unmap(page_table);
+ /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
+ if (!vma->vm_ops->fault)
+ return VM_FAULT_SIGBUS;
if (!(flags & FAULT_FLAG_WRITE))
return do_read_fault(mm, vma, address, pmd, pgoff, flags,
orig_pte);
barrier();
if (!pte_present(entry)) {
if (pte_none(entry)) {
- if (vma->vm_ops) {
- if (likely(vma->vm_ops->fault))
- return do_fault(mm, vma, address, pte,
- pmd, flags, entry);
- }
- return do_anonymous_page(mm, vma, address,
- pte, pmd, flags);
+ if (vma->vm_ops)
+ return do_fault(mm, vma, address, pte, pmd,
+ flags, entry);
+
+ return do_anonymous_page(mm, vma, address, pte, pmd,
+ flags);
}
return do_swap_page(mm, vma, address,
pte, pmd, flags, entry);
#include <keys/ceph-type.h>
#include <linux/module.h>
#include <linux/mount.h>
+#include <linux/nsproxy.h>
#include <linux/parser.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/statfs.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
-#include <linux/nsproxy.h>
-#include <net/net_namespace.h>
#include <linux/ceph/ceph_features.h>
int i;
int ret;
+ /*
+ * Don't bother comparing options if network namespaces don't
+ * match.
+ */
+ if (!net_eq(current->nsproxy->net_ns, read_pnet(&client->msgr.net)))
+ return -1;
+
ret = memcmp(opt1, opt2, ofs);
if (ret)
return ret;
int err = -ENOMEM;
substring_t argstr[MAX_OPT_ARGS];
- if (current->nsproxy->net_ns != &init_net)
- return ERR_PTR(-EINVAL);
-
opt = kzalloc(sizeof(*opt), GFP_KERNEL);
if (!opt)
return ERR_PTR(-ENOMEM);
fail_monc:
ceph_monc_stop(&client->monc);
fail:
+ ceph_messenger_fini(&client->msgr);
kfree(client);
return ERR_PTR(err);
}
/* unmount */
ceph_osdc_stop(&client->osdc);
-
ceph_monc_stop(&client->monc);
+ ceph_messenger_fini(&client->msgr);
ceph_debugfs_client_cleanup(client);
#include <linux/inet.h>
#include <linux/kthread.h>
#include <linux/net.h>
+#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/string.h>
int ret;
BUG_ON(con->sock);
- ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family,
+ ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
SOCK_STREAM, IPPROTO_TCP, &sock);
if (ret)
return ret;
static bool addr_is_blank(struct sockaddr_storage *ss)
{
+ struct in_addr *addr = &((struct sockaddr_in *)ss)->sin_addr;
+ struct in6_addr *addr6 = &((struct sockaddr_in6 *)ss)->sin6_addr;
+
switch (ss->ss_family) {
case AF_INET:
- return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
+ return addr->s_addr == htonl(INADDR_ANY);
case AF_INET6:
- return
- ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
- ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
- ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
- ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
+ return ipv6_addr_any(addr6);
+ default:
+ return true;
}
- return false;
}
static int addr_port(struct sockaddr_storage *ss)
msgr->tcp_nodelay = tcp_nodelay;
atomic_set(&msgr->stopping, 0);
+ write_pnet(&msgr->net, get_net(current->nsproxy->net_ns));
dout("%s %p\n", __func__, msgr);
}
EXPORT_SYMBOL(ceph_messenger_init);
+void ceph_messenger_fini(struct ceph_messenger *msgr)
+{
+ put_net(read_pnet(&msgr->net));
+}
+EXPORT_SYMBOL(ceph_messenger_fini);
+
static void clear_standby(struct ceph_connection *con)
{
/* come back from STANDBY? */
DEVID(acpi_device_id);
DEVID_FIELD(acpi_device_id, id);
+ DEVID_FIELD(acpi_device_id, cls);
+ DEVID_FIELD(acpi_device_id, cls_msk);
DEVID(pnp_device_id);
DEVID_FIELD(pnp_device_id, id);
}
ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry);
-/* looks like: "acpi:ACPI0003 or acpi:PNP0C0B" or "acpi:LNXVIDEO" */
+/* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or
+ * "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if)
+ *
+ * NOTE: Each driver should use one of the following : _HID, _CIDs
+ * or _CLS. Also, bb, ss, and pp can be substituted with ??
+ * as don't care byte.
+ */
static int do_acpi_entry(const char *filename,
void *symval, char *alias)
{
DEF_FIELD_ADDR(symval, acpi_device_id, id);
- sprintf(alias, "acpi*:%s:*", *id);
+ DEF_FIELD_ADDR(symval, acpi_device_id, cls);
+ DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk);
+
+ if (id && strlen((const char *)*id))
+ sprintf(alias, "acpi*:%s:*", *id);
+ else if (cls) {
+ int i, byte_shift, cnt = 0;
+ unsigned int msk;
+
+ sprintf(&alias[cnt], "acpi*:");
+ cnt = 6;
+ for (i = 1; i <= 3; i++) {
+ byte_shift = 8 * (3-i);
+ msk = (*cls_msk >> byte_shift) & 0xFF;
+ if (msk)
+ sprintf(&alias[cnt], "%02x",
+ (*cls >> byte_shift) & 0xFF);
+ else
+ sprintf(&alias[cnt], "??");
+ cnt += 2;
+ }
+ sprintf(&alias[cnt], ":*");
+ }
return 1;
}
ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry);
#define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \
".kprobes.text"
#define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
- ".fixup", ".entry.text", ".exception.text", ".text.*"
+ ".fixup", ".entry.text", ".exception.text", ".text.*", \
+ ".coldtext"
#define INIT_SECTIONS ".init.*"
#define MEM_INIT_SECTIONS ".meminit.*"
#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+#include <linux/types.h>
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+ switch (size) {
+ case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+ case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+ case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+ case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)res, (const void *)p, size);
+ barrier();
+ }
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+ switch (size) {
+ case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+ case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+ case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+ case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)p, (const void *)res, size);
+ barrier();
+ }
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering. One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+ ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
#endif /* _TOOLS_LINUX_COMPILER_H */
+++ /dev/null
-#ifndef _TOOLS_LINUX_EXPORT_H_
-#define _TOOLS_LINUX_EXPORT_H_
-
-#define EXPORT_SYMBOL(sym)
-#define EXPORT_SYMBOL_GPL(sym)
-#define EXPORT_SYMBOL_GPL_FUTURE(sym)
-#define EXPORT_UNUSED_SYMBOL(sym)
-#define EXPORT_UNUSED_SYMBOL_GPL(sym)
-
-#endif
--- /dev/null
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ linux/include/linux/rbtree.h
+
+ To use rbtrees you'll have to implement your own insert and search cores.
+ This will avoid us to use callbacks and to drop drammatically performances.
+ I know it's not the cleaner way, but in C (not in C++) to get
+ performances and genericity...
+
+ See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+ unsigned long __rb_parent_color;
+ struct rb_node *rb_right;
+ struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+ /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+ struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT (struct rb_root) { NULL, }
+#define rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node) \
+ ((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node) \
+ ((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+ struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+ struct rb_node **rb_link)
+{
+ node->__rb_parent_color = (unsigned long)parent;
+ node->rb_left = node->rb_right = NULL;
+
+ *rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+ })
+
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+ rb_erase(n, root);
+ RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
--- /dev/null
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+ (C) 2002 David Woodhouse <dwmw2@infradead.org>
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ tools/linux/include/linux/rbtree_augmented.h
+
+ Copied from:
+ linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+ void (*propagate)(struct rb_node *node, struct rb_node *stop);
+ void (*copy)(struct rb_node *old, struct rb_node *new);
+ void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ __rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \
+ rbtype, rbaugmented, rbcompute) \
+static inline void \
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop) \
+{ \
+ while (rb != stop) { \
+ rbstruct *node = rb_entry(rb, rbstruct, rbfield); \
+ rbtype augmented = rbcompute(node); \
+ if (node->rbaugmented == augmented) \
+ break; \
+ node->rbaugmented = augmented; \
+ rb = rb_parent(&node->rbfield); \
+ } \
+} \
+static inline void \
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \
+ rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \
+ new->rbaugmented = old->rbaugmented; \
+} \
+static void \
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \
+ rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \
+ new->rbaugmented = old->rbaugmented; \
+ old->rbaugmented = rbcompute(old); \
+} \
+rbstatic const struct rb_augment_callbacks rbname = { \
+ rbname ## _propagate, rbname ## _copy, rbname ## _rotate \
+};
+
+
+#define RB_RED 0
+#define RB_BLACK 1
+
+#define __rb_parent(pc) ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc) ((pc) & 1)
+#define __rb_is_black(pc) __rb_color(pc)
+#define __rb_is_red(pc) (!__rb_color(pc))
+#define rb_color(rb) __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+ rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+ struct rb_node *p, int color)
+{
+ rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+ struct rb_node *parent, struct rb_root *root)
+{
+ if (parent) {
+ if (parent->rb_left == old)
+ parent->rb_left = new;
+ else
+ parent->rb_right = new;
+ } else
+ root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+ struct rb_node *parent, *rebalance;
+ unsigned long pc;
+
+ if (!tmp) {
+ /*
+ * Case 1: node to erase has no more than 1 child (easy!)
+ *
+ * Note that if there is one child it must be red due to 5)
+ * and node must be black due to 4). We adjust colors locally
+ * so as to bypass __rb_erase_color() later on.
+ */
+ pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, child, parent, root);
+ if (child) {
+ child->__rb_parent_color = pc;
+ rebalance = NULL;
+ } else
+ rebalance = __rb_is_black(pc) ? parent : NULL;
+ tmp = parent;
+ } else if (!child) {
+ /* Still case 1, but this time the child is node->rb_left */
+ tmp->__rb_parent_color = pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, tmp, parent, root);
+ rebalance = NULL;
+ tmp = parent;
+ } else {
+ struct rb_node *successor = child, *child2;
+ tmp = child->rb_left;
+ if (!tmp) {
+ /*
+ * Case 2: node's successor is its right child
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (s) -> (x) (c)
+ * \
+ * (c)
+ */
+ parent = successor;
+ child2 = successor->rb_right;
+ augment->copy(node, successor);
+ } else {
+ /*
+ * Case 3: node's successor is leftmost under
+ * node's right child subtree
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (y) -> (x) (y)
+ * / /
+ * (p) (p)
+ * / /
+ * (s) (c)
+ * \
+ * (c)
+ */
+ do {
+ parent = successor;
+ successor = tmp;
+ tmp = tmp->rb_left;
+ } while (tmp);
+ parent->rb_left = child2 = successor->rb_right;
+ successor->rb_right = child;
+ rb_set_parent(child, successor);
+ augment->copy(node, successor);
+ augment->propagate(parent, successor);
+ }
+
+ successor->rb_left = tmp = node->rb_left;
+ rb_set_parent(tmp, successor);
+
+ pc = node->__rb_parent_color;
+ tmp = __rb_parent(pc);
+ __rb_change_child(node, successor, tmp, root);
+ if (child2) {
+ successor->__rb_parent_color = pc;
+ rb_set_parent_color(child2, parent, RB_BLACK);
+ rebalance = NULL;
+ } else {
+ unsigned long pc2 = successor->__rb_parent_color;
+ successor->__rb_parent_color = pc;
+ rebalance = __rb_is_black(pc2) ? parent : NULL;
+ }
+ tmp = successor;
+ }
+
+ augment->propagate(tmp, NULL);
+ return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+ if (rebalance)
+ __rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
--- /dev/null
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+ (C) 2002 David Woodhouse <dwmw2@infradead.org>
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree
+ *
+ * 1) A node is either red or black
+ * 2) The root is black
+ * 3) All leaves (NULL) are black
+ * 4) Both children of every red node are black
+ * 5) Every simple path from root to leaves contains the same number
+ * of black nodes.
+ *
+ * 4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ * consecutive red nodes in a path and every red node is therefore followed by
+ * a black. So if B is the number of black nodes on every simple path (as per
+ * 5), then the longest possible path due to 4 is 2B.
+ *
+ * We shall indicate color with case, where black nodes are uppercase and red
+ * nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ * parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+ rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+ return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+ struct rb_root *root, int color)
+{
+ struct rb_node *parent = rb_parent(old);
+ new->__rb_parent_color = old->__rb_parent_color;
+ rb_set_parent_color(old, new, color);
+ __rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+ while (true) {
+ /*
+ * Loop invariant: node is red
+ *
+ * If there is a black parent, we are done.
+ * Otherwise, take some corrective action as we don't
+ * want a red root or two consecutive red nodes.
+ */
+ if (!parent) {
+ rb_set_parent_color(node, NULL, RB_BLACK);
+ break;
+ } else if (rb_is_black(parent))
+ break;
+
+ gparent = rb_red_parent(parent);
+
+ tmp = gparent->rb_right;
+ if (parent != tmp) { /* parent == gparent->rb_left */
+ if (tmp && rb_is_red(tmp)) {
+ /*
+ * Case 1 - color flips
+ *
+ * G g
+ * / \ / \
+ * p u --> P U
+ * / /
+ * n n
+ *
+ * However, since g's parent might be red, and
+ * 4) does not allow this, we need to recurse
+ * at g.
+ */
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ rb_set_parent_color(parent, gparent, RB_BLACK);
+ node = gparent;
+ parent = rb_parent(node);
+ rb_set_parent_color(node, parent, RB_RED);
+ continue;
+ }
+
+ tmp = parent->rb_right;
+ if (node == tmp) {
+ /*
+ * Case 2 - left rotate at parent
+ *
+ * G G
+ * / \ / \
+ * p U --> n U
+ * \ /
+ * n p
+ *
+ * This still leaves us in violation of 4), the
+ * continuation into Case 3 will fix that.
+ */
+ parent->rb_right = tmp = node->rb_left;
+ node->rb_left = parent;
+ if (tmp)
+ rb_set_parent_color(tmp, parent,
+ RB_BLACK);
+ rb_set_parent_color(parent, node, RB_RED);
+ augment_rotate(parent, node);
+ parent = node;
+ tmp = node->rb_right;
+ }
+
+ /*
+ * Case 3 - right rotate at gparent
+ *
+ * G P
+ * / \ / \
+ * p U --> n g
+ * / \
+ * n U
+ */
+ gparent->rb_left = tmp; /* == parent->rb_right */
+ parent->rb_right = gparent;
+ if (tmp)
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+ augment_rotate(gparent, parent);
+ break;
+ } else {
+ tmp = gparent->rb_left;
+ if (tmp && rb_is_red(tmp)) {
+ /* Case 1 - color flips */
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ rb_set_parent_color(parent, gparent, RB_BLACK);
+ node = gparent;
+ parent = rb_parent(node);
+ rb_set_parent_color(node, parent, RB_RED);
+ continue;
+ }
+
+ tmp = parent->rb_left;
+ if (node == tmp) {
+ /* Case 2 - right rotate at parent */
+ parent->rb_left = tmp = node->rb_right;
+ node->rb_right = parent;
+ if (tmp)
+ rb_set_parent_color(tmp, parent,
+ RB_BLACK);
+ rb_set_parent_color(parent, node, RB_RED);
+ augment_rotate(parent, node);
+ parent = node;
+ tmp = node->rb_left;
+ }
+
+ /* Case 3 - left rotate at gparent */
+ gparent->rb_right = tmp; /* == parent->rb_left */
+ parent->rb_left = gparent;
+ if (tmp)
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+ augment_rotate(gparent, parent);
+ break;
+ }
+ }
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+ while (true) {
+ /*
+ * Loop invariants:
+ * - node is black (or NULL on first iteration)
+ * - node is not the root (parent is not NULL)
+ * - All leaf paths going through parent and node have a
+ * black node count that is 1 lower than other leaf paths.
+ */
+ sibling = parent->rb_right;
+ if (node != sibling) { /* node == parent->rb_left */
+ if (rb_is_red(sibling)) {
+ /*
+ * Case 1 - left rotate at parent
+ *
+ * P S
+ * / \ / \
+ * N s --> p Sr
+ * / \ / \
+ * Sl Sr N Sl
+ */
+ parent->rb_right = tmp1 = sibling->rb_left;
+ sibling->rb_left = parent;
+ rb_set_parent_color(tmp1, parent, RB_BLACK);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_RED);
+ augment_rotate(parent, sibling);
+ sibling = tmp1;
+ }
+ tmp1 = sibling->rb_right;
+ if (!tmp1 || rb_is_black(tmp1)) {
+ tmp2 = sibling->rb_left;
+ if (!tmp2 || rb_is_black(tmp2)) {
+ /*
+ * Case 2 - sibling color flip
+ * (p could be either color here)
+ *
+ * (p) (p)
+ * / \ / \
+ * N S --> N s
+ * / \ / \
+ * Sl Sr Sl Sr
+ *
+ * This leaves us violating 5) which
+ * can be fixed by flipping p to black
+ * if it was red, or by recursing at p.
+ * p is red when coming from Case 1.
+ */
+ rb_set_parent_color(sibling, parent,
+ RB_RED);
+ if (rb_is_red(parent))
+ rb_set_black(parent);
+ else {
+ node = parent;
+ parent = rb_parent(node);
+ if (parent)
+ continue;
+ }
+ break;
+ }
+ /*
+ * Case 3 - right rotate at sibling
+ * (p could be either color here)
+ *
+ * (p) (p)
+ * / \ / \
+ * N S --> N Sl
+ * / \ \
+ * sl Sr s
+ * \
+ * Sr
+ */
+ sibling->rb_left = tmp1 = tmp2->rb_right;
+ tmp2->rb_right = sibling;
+ parent->rb_right = tmp2;
+ if (tmp1)
+ rb_set_parent_color(tmp1, sibling,
+ RB_BLACK);
+ augment_rotate(sibling, tmp2);
+ tmp1 = sibling;
+ sibling = tmp2;
+ }
+ /*
+ * Case 4 - left rotate at parent + color flips
+ * (p and sl could be either color here.
+ * After rotation, p becomes black, s acquires
+ * p's color, and sl keeps its color)
+ *
+ * (p) (s)
+ * / \ / \
+ * N S --> P Sr
+ * / \ / \
+ * (sl) sr N (sl)
+ */
+ parent->rb_right = tmp2 = sibling->rb_left;
+ sibling->rb_left = parent;
+ rb_set_parent_color(tmp1, sibling, RB_BLACK);
+ if (tmp2)
+ rb_set_parent(tmp2, parent);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_BLACK);
+ augment_rotate(parent, sibling);
+ break;
+ } else {
+ sibling = parent->rb_left;
+ if (rb_is_red(sibling)) {
+ /* Case 1 - right rotate at parent */
+ parent->rb_left = tmp1 = sibling->rb_right;
+ sibling->rb_right = parent;
+ rb_set_parent_color(tmp1, parent, RB_BLACK);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_RED);
+ augment_rotate(parent, sibling);
+ sibling = tmp1;
+ }
+ tmp1 = sibling->rb_left;
+ if (!tmp1 || rb_is_black(tmp1)) {
+ tmp2 = sibling->rb_right;
+ if (!tmp2 || rb_is_black(tmp2)) {
+ /* Case 2 - sibling color flip */
+ rb_set_parent_color(sibling, parent,
+ RB_RED);
+ if (rb_is_red(parent))
+ rb_set_black(parent);
+ else {
+ node = parent;
+ parent = rb_parent(node);
+ if (parent)
+ continue;
+ }
+ break;
+ }
+ /* Case 3 - right rotate at sibling */
+ sibling->rb_right = tmp1 = tmp2->rb_left;
+ tmp2->rb_left = sibling;
+ parent->rb_left = tmp2;
+ if (tmp1)
+ rb_set_parent_color(tmp1, sibling,
+ RB_BLACK);
+ augment_rotate(sibling, tmp2);
+ tmp1 = sibling;
+ sibling = tmp2;
+ }
+ /* Case 4 - left rotate at parent + color flips */
+ parent->rb_left = tmp2 = sibling->rb_right;
+ sibling->rb_right = parent;
+ rb_set_parent_color(tmp1, sibling, RB_BLACK);
+ if (tmp2)
+ rb_set_parent(tmp2, parent);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_BLACK);
+ augment_rotate(parent, sibling);
+ break;
+ }
+ }
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ ____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+ dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+ __rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+ struct rb_node *rebalance;
+ rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+ if (rebalance)
+ ____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ __rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+ struct rb_node *n;
+
+ n = root->rb_node;
+ if (!n)
+ return NULL;
+ while (n->rb_left)
+ n = n->rb_left;
+ return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+ struct rb_node *n;
+
+ n = root->rb_node;
+ if (!n)
+ return NULL;
+ while (n->rb_right)
+ n = n->rb_right;
+ return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+ struct rb_node *parent;
+
+ if (RB_EMPTY_NODE(node))
+ return NULL;
+
+ /*
+ * If we have a right-hand child, go down and then left as far
+ * as we can.
+ */
+ if (node->rb_right) {
+ node = node->rb_right;
+ while (node->rb_left)
+ node=node->rb_left;
+ return (struct rb_node *)node;
+ }
+
+ /*
+ * No right-hand children. Everything down and left is smaller than us,
+ * so any 'next' node must be in the general direction of our parent.
+ * Go up the tree; any time the ancestor is a right-hand child of its
+ * parent, keep going up. First time it's a left-hand child of its
+ * parent, said parent is our 'next' node.
+ */
+ while ((parent = rb_parent(node)) && node == parent->rb_right)
+ node = parent;
+
+ return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+ struct rb_node *parent;
+
+ if (RB_EMPTY_NODE(node))
+ return NULL;
+
+ /*
+ * If we have a left-hand child, go down and then right as far
+ * as we can.
+ */
+ if (node->rb_left) {
+ node = node->rb_left;
+ while (node->rb_right)
+ node=node->rb_right;
+ return (struct rb_node *)node;
+ }
+
+ /*
+ * No left-hand children. Go up till we find an ancestor which
+ * is a right-hand child of its parent.
+ */
+ while ((parent = rb_parent(node)) && node == parent->rb_left)
+ node = parent;
+
+ return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+ struct rb_root *root)
+{
+ struct rb_node *parent = rb_parent(victim);
+
+ /* Set the surrounding nodes to point to the replacement */
+ __rb_change_child(victim, new, parent, root);
+ if (victim->rb_left)
+ rb_set_parent(victim->rb_left, new);
+ if (victim->rb_right)
+ rb_set_parent(victim->rb_right, new);
+
+ /* Copy the pointers/colour from the victim to the replacement */
+ *new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+ for (;;) {
+ if (node->rb_left)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+ else
+ return (struct rb_node *)node;
+ }
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+ const struct rb_node *parent;
+ if (!node)
+ return NULL;
+ parent = rb_parent(node);
+
+ /* If we're sitting on node, we've already seen our children */
+ if (parent && node == parent->rb_left && parent->rb_right) {
+ /* If we are the parent's left node, go to the parent's right
+ * node then all the way down to the left */
+ return rb_left_deepest_node(parent->rb_right);
+ } else
+ /* Otherwise we are the parent's right node, and the parent
+ * should be next */
+ return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+ if (!root->rb_node)
+ return NULL;
+
+ return rb_left_deepest_node(root->rb_node);
+}
tools/arch/x86/include/asm/rmwcc.h
tools/lib/traceevent
tools/lib/api
+tools/lib/rbtree.c
tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
tools/include/linux/list.h
tools/include/linux/log2.h
tools/include/linux/poison.h
+tools/include/linux/rbtree.h
+tools/include/linux/rbtree_augmented.h
tools/include/linux/types.h
include/asm-generic/bitops/arch_hweight.h
include/asm-generic/bitops/const_hweight.h
include/asm-generic/bitops/__fls.h
include/asm-generic/bitops/fls.h
include/linux/perf_event.h
-include/linux/rbtree.h
include/linux/list.h
include/linux/hash.h
include/linux/stringify.h
lib/hweight.c
-lib/rbtree.c
include/linux/swab.h
arch/*/include/asm/unistd*.h
arch/*/include/uapi/asm/unistd*.h
arch/*/lib/memset*.S
include/linux/poison.h
include/linux/hw_breakpoint.h
-include/linux/rbtree_augmented.h
include/uapi/linux/perf_event.h
include/uapi/linux/const.h
include/uapi/linux/swab.h
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+++ /dev/null
-#ifndef __TOOLS_LINUX_PERF_RBTREE_H
-#define __TOOLS_LINUX_PERF_RBTREE_H
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
- */
-static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
-{
- rb_erase(n, root);
- RB_CLEAR_NODE(n);
-}
-#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
+++ /dev/null
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"
OSDN Git Service
