Merge branch 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6
* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
drm/ttm: Read buffer overflow
drm/radeon: Read buffer overflow
drm/ttm: Fix a sync object leak.
drm/radeon/kms: fix memory leak in radeon_driver_load_kms
drm/radeon/kms: fix nomodeset.
drm/ttm: Fix a potential comparison of structs.
drm/radeon/kms: fix rv515 VRAM initialisation.
drm/radeon: add some new r7xx pci ids
drm: Catch stop possible NULL pointer reference
drm: Small logic fix in drm_mode_setcrtc
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index ae3e70cd..e552e54 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -553,7 +553,7 @@
* on most of those machines only handles cache transactions.
*/
extrd,u,*= \pte,_PAGE_NO_CACHE_BIT+32,1,%r0
- depi 1,12,1,\prot
+ depdi 1,12,1,\prot
/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
convert_for_tlb_insert20 \pte
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index ef5caf2..61ee0ee 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -86,8 +86,12 @@
* the bottom of the table, which has a maximum signed displacement of
* 0x3fff; however, since we're only going forward, this becomes
* 0x1fff, and thus, since each GOT entry is 8 bytes long we can have
- * at most 1023 entries */
-#define MAX_GOTS 1023
+ * at most 1023 entries.
+ * To overcome this 14bit displacement with some kernel modules, we'll
+ * use instead the unusal 16bit displacement method (see reassemble_16a)
+ * which gives us a maximum positive displacement of 0x7fff, and as such
+ * allows us to allocate up to 4095 GOT entries. */
+#define MAX_GOTS 4095
/* three functions to determine where in the module core
* or init pieces the location is */
@@ -145,12 +149,40 @@
/* The reassemble_* functions prepare an immediate value for
insertion into an opcode. pa-risc uses all sorts of weird bitfields
in the instruction to hold the value. */
+static inline int sign_unext(int x, int len)
+{
+ int len_ones;
+
+ len_ones = (1 << len) - 1;
+ return x & len_ones;
+}
+
+static inline int low_sign_unext(int x, int len)
+{
+ int sign, temp;
+
+ sign = (x >> (len-1)) & 1;
+ temp = sign_unext(x, len-1);
+ return (temp << 1) | sign;
+}
+
static inline int reassemble_14(int as14)
{
return (((as14 & 0x1fff) << 1) |
((as14 & 0x2000) >> 13));
}
+static inline int reassemble_16a(int as16)
+{
+ int s, t;
+
+ /* Unusual 16-bit encoding, for wide mode only. */
+ t = (as16 << 1) & 0xffff;
+ s = (as16 & 0x8000);
+ return (t ^ s ^ (s >> 1)) | (s >> 15);
+}
+
+
static inline int reassemble_17(int as17)
{
return (((as17 & 0x10000) >> 16) |
@@ -407,6 +439,7 @@
enum elf_stub_type stub_type, Elf_Addr loc0, unsigned int targetsec)
{
struct stub_entry *stub;
+ int __maybe_unused d;
/* initialize stub_offset to point in front of the section */
if (!me->arch.section[targetsec].stub_offset) {
@@ -460,12 +493,19 @@
*/
switch (stub_type) {
case ELF_STUB_GOT:
- stub->insns[0] = 0x537b0000; /* ldd 0(%dp),%dp */
+ d = get_got(me, value, addend);
+ if (d <= 15) {
+ /* Format 5 */
+ stub->insns[0] = 0x0f6010db; /* ldd 0(%dp),%dp */
+ stub->insns[0] |= low_sign_unext(d, 5) << 16;
+ } else {
+ /* Format 3 */
+ stub->insns[0] = 0x537b0000; /* ldd 0(%dp),%dp */
+ stub->insns[0] |= reassemble_16a(d);
+ }
stub->insns[1] = 0x53610020; /* ldd 10(%dp),%r1 */
stub->insns[2] = 0xe820d000; /* bve (%r1) */
stub->insns[3] = 0x537b0030; /* ldd 18(%dp),%dp */
-
- stub->insns[0] |= reassemble_14(get_got(me, value, addend) & 0x3fff);
break;
case ELF_STUB_MILLI:
stub->insns[0] = 0x20200000; /* ldil 0,%r1 */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index edc90f2..8406ed7 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -33,7 +33,7 @@
#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \
efi_call_virt(f, a1, a2, a3, a4, a5, a6)
-#define efi_ioremap(addr, size) ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type) ioremap_cache(addr, size)
#else /* !CONFIG_X86_32 */
@@ -84,7 +84,8 @@
efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
(u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
+ u32 type);
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2bdab21..c6ccbe7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -12,9 +12,15 @@
{
unsigned long flags;
+ /*
+ * Note: this needs to be "=r" not "=rm", because we have the
+ * stack offset from what gcc expects at the time the "pop" is
+ * executed, and so a memory reference with respect to the stack
+ * would end up using the wrong address.
+ */
asm volatile("# __raw_save_flags\n\t"
"pushf ; pop %0"
- : "=g" (flags)
+ : "=r" (flags)
: /* no input */
: "memory");
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 341070f..77a6850 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -175,7 +175,7 @@
#define UV_GLOBAL_MMR32_PNODE_BITS(p) ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
#define UV_GLOBAL_MMR64_PNODE_BITS(p) \
- ((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+ (((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
#define UV_APIC_PNODE_SHIFT 6
@@ -327,6 +327,7 @@
unsigned short nr_possible_cpus;
unsigned short nr_online_cpus;
unsigned short pnode;
+ short memory_nid;
};
extern struct uv_blade_info *uv_blade_info;
extern short *uv_node_to_blade;
@@ -363,6 +364,12 @@
return uv_blade_info[bid].pnode;
}
+/* Nid of memory node on blade. -1 if no blade-local memory */
+static inline int uv_blade_to_memory_nid(int bid)
+{
+ return uv_blade_info[bid].memory_nid;
+}
+
/* Determine the number of possible cpus on a blade */
static inline int uv_blade_nr_possible_cpus(int bid)
{
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 2284a481..d2ed6c5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3793,6 +3793,9 @@
mmr_pnode = uv_blade_to_pnode(mmr_blade);
uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+ if (cfg->move_in_progress)
+ send_cleanup_vector(cfg);
+
return irq;
}
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8e4cbb2..2ed4e2b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -170,7 +170,7 @@
static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb)
{
- return current_cpu_data.initial_apicid >> index_msb;
+ return initial_apicid >> index_msb;
}
static void x2apic_send_IPI_self(int vector)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index a284359..0b631c6 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -162,7 +162,7 @@
static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
{
- return current_cpu_data.initial_apicid >> index_msb;
+ return initial_apicid >> index_msb;
}
static void x2apic_send_IPI_self(int vector)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 096d19a..832e908 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -261,7 +261,7 @@
.apic_id_registered = uv_apic_id_registered,
.irq_delivery_mode = dest_Fixed,
- .irq_dest_mode = 1, /* logical */
+ .irq_dest_mode = 0, /* physical */
.target_cpus = uv_target_cpus,
.disable_esr = 0,
@@ -362,12 +362,6 @@
BUG();
}
-static __init void map_low_mmrs(void)
-{
- init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE);
- init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE);
-}
-
enum map_type {map_wb, map_uc};
static __init void map_high(char *id, unsigned long base, int shift,
@@ -395,26 +389,6 @@
map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
}
-static __init void map_config_high(int max_pnode)
-{
- union uvh_rh_gam_cfg_overlay_config_mmr_u cfg;
- int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT;
-
- cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR);
- if (cfg.s.enable)
- map_high("CONFIG", cfg.s.base, shift, max_pnode, map_uc);
-}
-
-static __init void map_mmr_high(int max_pnode)
-{
- union uvh_rh_gam_mmr_overlay_config_mmr_u mmr;
- int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT;
-
- mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR);
- if (mmr.s.enable)
- map_high("MMR", mmr.s.base, shift, max_pnode, map_uc);
-}
-
static __init void map_mmioh_high(int max_pnode)
{
union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
@@ -566,8 +540,6 @@
unsigned long mmr_base, present, paddr;
unsigned short pnode_mask;
- map_low_mmrs();
-
m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
m_val = m_n_config.s.m_skt;
n_val = m_n_config.s.n_skt;
@@ -591,6 +563,8 @@
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
uv_blade_info = kmalloc(bytes, GFP_KERNEL);
BUG_ON(!uv_blade_info);
+ for (blade = 0; blade < uv_num_possible_blades(); blade++)
+ uv_blade_info[blade].memory_nid = -1;
get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
@@ -629,6 +603,9 @@
lcpu = uv_blade_info[blade].nr_possible_cpus;
uv_blade_info[blade].nr_possible_cpus++;
+ /* Any node on the blade, else will contain -1. */
+ uv_blade_info[blade].memory_nid = nid;
+
uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
uv_cpu_hub_info(cpu)->m_val = m_val;
@@ -662,11 +639,10 @@
pnode = (paddr >> m_val) & pnode_mask;
blade = boot_pnode_to_blade(pnode);
uv_node_to_blade[nid] = blade;
+ max_pnode = max(pnode, max_pnode);
}
map_gru_high(max_pnode);
- map_mmr_high(max_pnode);
- map_config_high(max_pnode);
map_mmioh_high(max_pnode);
uv_cpu_init();
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 79302e9..442b550 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -811,7 +811,7 @@
u8 ret = 0;
int idled = 0;
int polling;
- int err;
+ int err = 0;
polling = !!(current_thread_info()->status & TS_POLLING);
if (polling) {
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 96f7ac0..19ccf6d 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -512,7 +512,7 @@
&& end_pfn <= max_pfn_mapped))
va = __va(md->phys_addr);
else
- va = efi_ioremap(md->phys_addr, size);
+ va = efi_ioremap(md->phys_addr, size, md->type);
md->virt_addr = (u64) (unsigned long) va;
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 22c3b78..ac0621a 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -98,10 +98,14 @@
early_runtime_code_mapping_set_exec(0);
}
-void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
+ u32 type)
{
unsigned long last_map_pfn;
+ if (type == EFI_MEMORY_MAPPED_IO)
+ return ioremap(phys_addr, size);
+
last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
return NULL;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 8663afb..0d98a01c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -602,7 +602,11 @@
#endif
iret
-.section .cpuinit.data,"wa"
+#ifndef CONFIG_HOTPLUG_CPU
+ __CPUINITDATA
+#else
+ __REFDATA
+#endif
.align 4
ENTRY(initial_code)
.long i386_start_kernel
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 508e982..834c9da 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -3,6 +3,7 @@
#include <linux/init.h>
#include <linux/pm.h>
#include <linux/efi.h>
+#include <linux/dmi.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
@@ -17,7 +18,6 @@
#include <asm/cpu.h>
#ifdef CONFIG_X86_32
-# include <linux/dmi.h>
# include <linux/ctype.h>
# include <linux/mc146818rtc.h>
#else
@@ -404,6 +404,38 @@
#endif /* CONFIG_X86_32 */
+/*
+ * Apple MacBook5,2 (2009 MacBook) needs reboot=p
+ */
+static int __init set_pci_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_CF9) {
+ reboot_type = BOOT_CF9;
+ printk(KERN_INFO "%s series board detected. "
+ "Selecting PCI-method for reboots.\n", d->ident);
+ }
+ return 0;
+}
+
+static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
+ { /* Handle problems with rebooting on Apple MacBook5,2 */
+ .callback = set_pci_reboot,
+ .ident = "Apple MacBook",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5,2"),
+ },
+ },
+ { }
+};
+
+static int __init pci_reboot_init(void)
+{
+ dmi_check_system(pci_reboot_dmi_table);
+ return 0;
+}
+core_initcall(pci_reboot_init);
+
static inline void kb_wait(void)
{
int i;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 59f31d2..78d185d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -393,8 +393,8 @@
#ifdef CONFIG_X86_32
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
+. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE");
#else
/*
* Per-cpu symbols which need to be offset from __per_cpu_load
@@ -407,12 +407,12 @@
/*
* Build-time check on the image size:
*/
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
+. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE");
#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
- "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((per_cpu__irq_stack_union == 0),
+ "irq_stack_union is not at start of per-cpu area");
#endif
#endif /* CONFIG_X86_32 */
@@ -420,7 +420,7 @@
#ifdef CONFIG_KEXEC
#include <asm/kexec.h>
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
+. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+ "kexec control code size is too big");
#endif
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 1440b9c..caa24ac 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -89,16 +89,13 @@
rv.msrs = msrs;
rv.msr_no = msr_no;
- preempt_disable();
- /*
- * FIXME: handle the CPU we're executing on separately for now until
- * smp_call_function_many has been fixed to not skip it.
- */
- this_cpu = raw_smp_processor_id();
- smp_call_function_single(this_cpu, __rdmsr_on_cpu, &rv, 1);
+ this_cpu = get_cpu();
+
+ if (cpumask_test_cpu(this_cpu, mask))
+ __rdmsr_on_cpu(&rv);
smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1);
- preempt_enable();
+ put_cpu();
}
EXPORT_SYMBOL(rdmsr_on_cpus);
@@ -121,16 +118,13 @@
rv.msrs = msrs;
rv.msr_no = msr_no;
- preempt_disable();
- /*
- * FIXME: handle the CPU we're executing on separately for now until
- * smp_call_function_many has been fixed to not skip it.
- */
- this_cpu = raw_smp_processor_id();
- smp_call_function_single(this_cpu, __wrmsr_on_cpu, &rv, 1);
+ this_cpu = get_cpu();
+
+ if (cpumask_test_cpu(this_cpu, mask))
+ __wrmsr_on_cpu(&rv);
smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1);
- preempt_enable();
+ put_cpu();
}
EXPORT_SYMBOL(wrmsr_on_cpus);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1b734d7..7e600c1 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -591,9 +591,12 @@
unsigned int level;
pte_t *kpte, old_pte;
- if (cpa->flags & CPA_PAGES_ARRAY)
- address = (unsigned long)page_address(cpa->pages[cpa->curpage]);
- else if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & CPA_PAGES_ARRAY) {
+ struct page *page = cpa->pages[cpa->curpage];
+ if (unlikely(PageHighMem(page)))
+ return 0;
+ address = (unsigned long)page_address(page);
+ } else if (cpa->flags & CPA_ARRAY)
address = cpa->vaddr[cpa->curpage];
else
address = *cpa->vaddr;
@@ -697,9 +700,12 @@
* No need to redo, when the primary call touched the direct
* mapping already:
*/
- if (cpa->flags & CPA_PAGES_ARRAY)
- vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]);
- else if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & CPA_PAGES_ARRAY) {
+ struct page *page = cpa->pages[cpa->curpage];
+ if (unlikely(PageHighMem(page)))
+ return 0;
+ vaddr = (unsigned long)page_address(page);
+ } else if (cpa->flags & CPA_ARRAY)
vaddr = cpa->vaddr[cpa->curpage];
else
vaddr = *cpa->vaddr;
@@ -997,12 +1003,15 @@
int _set_memory_wc(unsigned long addr, int numpages)
{
int ret;
+ unsigned long addr_copy = addr;
+
ret = change_page_attr_set(&addr, numpages,
__pgprot(_PAGE_CACHE_UC_MINUS), 0);
-
if (!ret) {
- ret = change_page_attr_set(&addr, numpages,
- __pgprot(_PAGE_CACHE_WC), 0);
+ ret = change_page_attr_set_clr(&addr_copy, numpages,
+ __pgprot(_PAGE_CACHE_WC),
+ __pgprot(_PAGE_CACHE_MASK),
+ 0, 0, NULL);
}
return ret;
}
@@ -1119,7 +1128,9 @@
int free_idx;
for (i = 0; i < addrinarray; i++) {
- start = (unsigned long)page_address(pages[i]);
+ if (PageHighMem(pages[i]))
+ continue;
+ start = page_to_pfn(pages[i]) << PAGE_SHIFT;
end = start + PAGE_SIZE;
if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
goto err_out;
@@ -1132,7 +1143,9 @@
err_out:
free_idx = i;
for (i = 0; i < free_idx; i++) {
- start = (unsigned long)page_address(pages[i]);
+ if (PageHighMem(pages[i]))
+ continue;
+ start = page_to_pfn(pages[i]) << PAGE_SHIFT;
end = start + PAGE_SIZE;
free_memtype(start, end);
}
@@ -1161,7 +1174,9 @@
return retval;
for (i = 0; i < addrinarray; i++) {
- start = (unsigned long)page_address(pages[i]);
+ if (PageHighMem(pages[i]))
+ continue;
+ start = page_to_pfn(pages[i]) << PAGE_SHIFT;
end = start + PAGE_SIZE;
free_memtype(start, end);
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index af8f965..ed34f5e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -329,7 +329,6 @@
printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
(int)-reserve);
__FIXADDR_TOP = -reserve - PAGE_SIZE;
- __VMALLOC_RESERVE += reserve;
#endif
}
diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c
index f4bb43f..e077701 100644
--- a/drivers/char/agp/parisc-agp.c
+++ b/drivers/char/agp/parisc-agp.c
@@ -225,7 +225,7 @@
.configure = parisc_agp_configure,
.fetch_size = parisc_agp_fetch_size,
.tlb_flush = parisc_agp_tlbflush,
- .mask_memory = parisc_agp_mask_memory,
+ .mask_memory = parisc_agp_page_mask_memory,
.masks = parisc_agp_masks,
.agp_enable = parisc_agp_enable,
.cache_flush = global_cache_flush,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b90eda8..fd69086 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -858,6 +858,8 @@
/* Check for existing affected CPUs.
* They may not be aware of it due to CPU Hotplug.
+ * cpufreq_cpu_put is called when the device is removed
+ * in __cpufreq_remove_dev()
*/
managed_policy = cpufreq_cpu_get(j);
if (unlikely(managed_policy)) {
@@ -884,7 +886,7 @@
ret = sysfs_create_link(&sys_dev->kobj,
&managed_policy->kobj,
"cpufreq");
- if (!ret)
+ if (ret)
cpufreq_cpu_put(managed_policy);
/*
* Success. We only needed to be added to the mask.
@@ -924,6 +926,8 @@
spin_lock_irqsave(&cpufreq_driver_lock, flags);
for_each_cpu(j, policy->cpus) {
+ if (!cpu_online(j))
+ continue;
per_cpu(cpufreq_cpu_data, j) = policy;
per_cpu(policy_cpu, j) = policy->cpu;
}
@@ -1244,13 +1248,22 @@
static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
{
- int cpu = sysdev->id;
int ret = 0;
+
+#ifdef __powerpc__
+ int cpu = sysdev->id;
unsigned int cur_freq = 0;
struct cpufreq_policy *cpu_policy;
dprintk("suspending cpu %u\n", cpu);
+ /*
+ * This whole bogosity is here because Powerbooks are made of fail.
+ * No sane platform should need any of the code below to be run.
+ * (it's entirely the wrong thing to do, as driver->get may
+ * reenable interrupts on some architectures).
+ */
+
if (!cpu_online(cpu))
return 0;
@@ -1309,6 +1322,7 @@
out:
cpufreq_cpu_put(cpu_policy);
+#endif /* __powerpc__ */
return ret;
}
@@ -1322,12 +1336,18 @@
*/
static int cpufreq_resume(struct sys_device *sysdev)
{
- int cpu = sysdev->id;
int ret = 0;
+
+#ifdef __powerpc__
+ int cpu = sysdev->id;
struct cpufreq_policy *cpu_policy;
dprintk("resuming cpu %u\n", cpu);
+ /* As with the ->suspend method, all the code below is
+ * only necessary because Powerbooks suck.
+ * See commit 42d4dc3f4e1e for jokes. */
+
if (!cpu_online(cpu))
return 0;
@@ -1391,6 +1411,7 @@
schedule_work(&cpu_policy->update);
fail:
cpufreq_cpu_put(cpu_policy);
+#endif /* __powerpc__ */
return ret;
}
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 5749050..bdea7e2f 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -63,6 +63,7 @@
unsigned int down_skip;
unsigned int requested_freq;
int cpu;
+ unsigned int enable:1;
/*
* percpu mutex that serializes governor limit change with
* do_dbs_timer invocation. We do not want do_dbs_timer to run
@@ -141,6 +142,9 @@
struct cpufreq_policy *policy;
+ if (!this_dbs_info->enable)
+ return 0;
+
policy = this_dbs_info->cur_policy;
/*
@@ -497,6 +501,7 @@
int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
delay -= jiffies % delay;
+ dbs_info->enable = 1;
INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer);
queue_delayed_work_on(dbs_info->cpu, kconservative_wq, &dbs_info->work,
delay);
@@ -504,6 +509,7 @@
static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
{
+ dbs_info->enable = 0;
cancel_delayed_work_sync(&dbs_info->work);
}
diff --git a/drivers/input/serio/hp_sdc_mlc.c b/drivers/input/serio/hp_sdc_mlc.c
index b587e2d..820e516 100644
--- a/drivers/input/serio/hp_sdc_mlc.c
+++ b/drivers/input/serio/hp_sdc_mlc.c
@@ -296,7 +296,7 @@
priv->tseq[3] = 0;
if (mlc->opacket & HIL_CTRL_APE) {
priv->tseq[3] |= HP_SDC_LPC_APE_IPF;
- down_trylock(&mlc->csem);
+ BUG_ON(down_trylock(&mlc->csem));
}
enqueue:
hp_sdc_enqueue_transaction(&priv->trans);
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index bae61b2..7d43083 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -180,14 +180,9 @@
static int twl4030_irq_thread(void *data)
{
long irq = (long)data;
- struct irq_desc *desc = irq_to_desc(irq);
static unsigned i2c_errors;
static const unsigned max_i2c_errors = 100;
- if (!desc) {
- pr_err("twl4030: Invalid IRQ: %ld\n", irq);
- return -EINVAL;
- }
current->flags |= PF_NOFREEZE;
@@ -240,7 +235,7 @@
}
local_irq_enable();
- desc->chip->unmask(irq);
+ enable_irq(irq);
}
return 0;
@@ -255,25 +250,13 @@
* thread. All we do here is acknowledge and mask the interrupt and wakeup
* the kernel thread.
*/
-static void handle_twl4030_pih(unsigned int irq, struct irq_desc *desc)
+static irqreturn_t handle_twl4030_pih(int irq, void *devid)
{
/* Acknowledge, clear *AND* mask the interrupt... */
- desc->chip->ack(irq);
- complete(&irq_event);
+ disable_irq_nosync(irq);
+ complete(devid);
+ return IRQ_HANDLED;
}
-
-static struct task_struct *start_twl4030_irq_thread(long irq)
-{
- struct task_struct *thread;
-
- init_completion(&irq_event);
- thread = kthread_run(twl4030_irq_thread, (void *)irq, "twl4030-irq");
- if (!thread)
- pr_err("twl4030: could not create irq %ld thread!\n", irq);
-
- return thread;
-}
-
/*----------------------------------------------------------------------*/
/*
@@ -734,18 +717,28 @@
}
/* install an irq handler to demultiplex the TWL4030 interrupt */
- task = start_twl4030_irq_thread(irq_num);
- if (!task) {
- pr_err("twl4030: irq thread FAIL\n");
- status = -ESRCH;
- goto fail;
+
+
+ init_completion(&irq_event);
+
+ status = request_irq(irq_num, handle_twl4030_pih, IRQF_DISABLED,
+ "TWL4030-PIH", &irq_event);
+ if (status < 0) {
+ pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status);
+ goto fail_rqirq;
}
- set_irq_data(irq_num, task);
- set_irq_chained_handler(irq_num, handle_twl4030_pih);
-
+ task = kthread_run(twl4030_irq_thread, (void *)irq_num, "twl4030-irq");
+ if (IS_ERR(task)) {
+ pr_err("twl4030: could not create irq %d thread!\n", irq_num);
+ status = PTR_ERR(task);
+ goto fail_kthread;
+ }
return status;
-
+fail_kthread:
+ free_irq(irq_num, &irq_event);
+fail_rqirq:
+ /* clean up twl4030_sih_setup */
fail:
for (i = irq_base; i < irq_end; i++)
set_irq_chip_and_handler(i, NULL, NULL);
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 0f0e0b9..a45b0c0 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -70,7 +70,6 @@
#undef CCIO_COLLECT_STATS
#endif
-#include <linux/proc_fs.h>
#include <asm/runway.h> /* for proc_runway_root */
#ifdef DEBUG_CCIO_INIT
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index c590974e..d69bde6 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -614,7 +614,7 @@
dev_name(&bus->self->dev), i,
bus->self->resource[i].start,
bus->self->resource[i].end);
- pci_assign_resource(bus->self, i);
+ WARN_ON(pci_assign_resource(bus->self, i));
DBG("DEBUG %s after assign %d [0x%lx,0x%lx]\n",
dev_name(&bus->self->dev), i,
bus->self->resource[i].start,
diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c
index 685d94e..8c0b26e9 100644
--- a/drivers/parisc/eisa_eeprom.c
+++ b/drivers/parisc/eisa_eeprom.c
@@ -55,7 +55,7 @@
ssize_t ret;
int i;
- if (*ppos >= HPEE_MAX_LENGTH)
+ if (*ppos < 0 || *ppos >= HPEE_MAX_LENGTH)
return 0;
count = *ppos + count < HPEE_MAX_LENGTH ? count : HPEE_MAX_LENGTH - *ppos;
diff --git a/drivers/parisc/hppb.c b/drivers/parisc/hppb.c
index 1385641..815db17 100644
--- a/drivers/parisc/hppb.c
+++ b/drivers/parisc/hppb.c
@@ -62,7 +62,8 @@
}
card = card->next;
}
- printk(KERN_INFO "Found GeckoBoa at 0x%x\n", dev->hpa.start);
+ printk(KERN_INFO "Found GeckoBoa at 0x%llx\n",
+ (unsigned long long) dev->hpa.start);
card->hpa = dev->hpa.start;
card->mmio_region.name = "HP-PB Bus";
@@ -73,8 +74,10 @@
status = ccio_request_resource(dev, &card->mmio_region);
if(status < 0) {
- printk(KERN_ERR "%s: failed to claim HP-PB bus space (%08x, %08x)\n",
- __FILE__, card->mmio_region.start, card->mmio_region.end);
+ printk(KERN_ERR "%s: failed to claim HP-PB "
+ "bus space (0x%08llx, 0x%08llx)\n",
+ __FILE__, (unsigned long long) card->mmio_region.start,
+ (unsigned long long) card->mmio_region.end);
}
return 0;
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index ede614616..3aeb327 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -992,7 +992,7 @@
return;
io_pdc_cell = kzalloc(sizeof(pdc_pat_cell_mod_maddr_block_t), GFP_KERNEL);
- if (!pa_pdc_cell) {
+ if (!io_pdc_cell) {
kfree(pa_pdc_cell);
return;
}
diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c
index f9f9a5f..13a64bc 100644
--- a/drivers/parisc/pdc_stable.c
+++ b/drivers/parisc/pdc_stable.c
@@ -370,7 +370,7 @@
if (!i) /* entry is not ready */
return -ENODATA;
- for (i = 0; devpath->layers[i] && (likely(i < 6)); i++)
+ for (i = 0; i < 6 && devpath->layers[i]; i++)
out += sprintf(out, "%u ", devpath->layers[i]);
out += sprintf(out, "\n");
diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index ef7870f..857b366 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -957,9 +957,14 @@
#ifdef CONFIG_PCI
unsigned long fb_base, rom_base;
unsigned int fb_len, rom_len;
+ int err;
struct sti_struct *sti;
- pci_enable_device(pd);
+ err = pci_enable_device(pd);
+ if (err < 0) {
+ dev_err(&pd->dev, "Cannot enable PCI device\n");
+ return err;
+ }
fb_base = pci_resource_start(pd, 0);
fb_len = pci_resource_len(pd, 0);
@@ -1048,7 +1053,7 @@
/* Register drivers for native & PCI cards */
register_parisc_driver(&pa_sti_driver);
- pci_register_driver(&pci_sti_driver);
+ WARN_ON(pci_register_driver(&pci_sti_driver));
/* if we didn't find the given default sti, take the first one */
if (!default_sti)
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 92888aa..e85b1e4 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -1,3 +1,10 @@
+Version 1.60
+-------------
+Fix memory leak in reconnect. Fix oops in DFS mount error path.
+Set s_maxbytes to smaller (the max that vfs can handle) so that
+sendfile will now work over cifs mounts again. Add noforcegid
+and noforceuid mount parameters.
+
Version 1.59
------------
Client uses server inode numbers (which are persistent) rather than
diff --git a/fs/cifs/README b/fs/cifs/README
index ad92921..79c1a93 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -262,11 +262,11 @@
mount.
domain Set the SMB/CIFS workgroup name prepended to the
username during CIFS session establishment
- forceuid Set the default uid for inodes based on the uid
- passed in. For mounts to servers
+ forceuid Set the default uid for inodes to the uid
+ passed in on mount. For mounts to servers
which do support the CIFS Unix extensions, such as a
properly configured Samba server, the server provides
- the uid, gid and mode so this parameter should not be
+ the uid, gid and mode so this parameter should not be
specified unless the server and clients uid and gid
numbering differ. If the server and client are in the
same domain (e.g. running winbind or nss_ldap) and
@@ -278,11 +278,7 @@
of existing files will be the uid (gid) of the person
who executed the mount (root, except when mount.cifs
is configured setuid for user mounts) unless the "uid="
- (gid) mount option is specified. For the uid (gid) of newly
- created files and directories, ie files created since
- the last mount of the server share, the expected uid
- (gid) is cached as long as the inode remains in
- memory on the client. Also note that permission
+ (gid) mount option is specified. Also note that permission
checks (authorization checks) on accesses to a file occur
at the server, but there are cases in which an administrator
may want to restrict at the client as well. For those
@@ -290,12 +286,15 @@
(such as Windows), permissions can also be checked at the
client, and a crude form of client side permission checking
can be enabled by specifying file_mode and dir_mode on
- the client. Note that the mount.cifs helper must be
- at version 1.10 or higher to support specifying the uid
- (or gid) in non-numeric form.
- forcegid (similar to above but for the groupid instead of uid)
+ the client. (default)
+ forcegid (similar to above but for the groupid instead of uid) (default)
+ noforceuid Fill in file owner information (uid) by requesting it from
+ the server if possible. With this option, the value given in
+ the uid= option (on mount) will only be used if the server
+ can not support returning uids on inodes.
+ noforcegid (similar to above but for the group owner, gid, instead of uid)
uid Set the default uid for inodes, and indicate to the
- cifs kernel driver which local user mounted . If the server
+ cifs kernel driver which local user mounted. If the server
supports the unix extensions the default uid is
not used to fill in the owner fields of inodes (files)
unless the "forceuid" parameter is specified.
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 3bb11be..606912d 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -55,7 +55,7 @@
* i.e. strips from UNC trailing path that is not part of share
* name and fixup missing '\' in the begining of DFS node refferal
* if neccessary.
- * Returns pointer to share name on success or NULL on error.
+ * Returns pointer to share name on success or ERR_PTR on error.
* Caller is responsible for freeing returned string.
*/
static char *cifs_get_share_name(const char *node_name)
@@ -68,7 +68,7 @@
UNC = kmalloc(len+2 /*for term null and additional \ if it's missed */,
GFP_KERNEL);
if (!UNC)
- return NULL;
+ return ERR_PTR(-ENOMEM);
/* get share name and server name */
if (node_name[1] != '\\') {
@@ -87,7 +87,7 @@
cERROR(1, ("%s: no server name end in node name: %s",
__func__, node_name));
kfree(UNC);
- return NULL;
+ return ERR_PTR(-EINVAL);
}
/* find sharename end */
@@ -133,6 +133,12 @@
return ERR_PTR(-EINVAL);
*devname = cifs_get_share_name(ref->node_name);
+ if (IS_ERR(*devname)) {
+ rc = PTR_ERR(*devname);
+ *devname = NULL;
+ goto compose_mount_options_err;
+ }
+
rc = dns_resolve_server_name_to_ip(*devname, &srvIP);
if (rc != 0) {
cERROR(1, ("%s: Failed to resolve server part of %s to IP: %d",
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 60e3c42..714a542 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -44,7 +44,7 @@
int maxwords = maxbytes / 2;
char tmp[NLS_MAX_CHARSET_SIZE];
- for (i = 0; from[i] && i < maxwords; i++) {
+ for (i = 0; i < maxwords && from[i]; i++) {
charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp,
NLS_MAX_CHARSET_SIZE);
if (charlen > 0)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 44f3050..84b7525 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -376,10 +376,14 @@
seq_printf(s, ",uid=%d", cifs_sb->mnt_uid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
seq_printf(s, ",forceuid");
+ else
+ seq_printf(s, ",noforceuid");
seq_printf(s, ",gid=%d", cifs_sb->mnt_gid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
seq_printf(s, ",forcegid");
+ else
+ seq_printf(s, ",noforcegid");
cifs_show_address(s, tcon->ses->server);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index fc44d31..1f3345d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -803,6 +803,10 @@
char *data;
unsigned int temp_len, i, j;
char separator[2];
+ short int override_uid = -1;
+ short int override_gid = -1;
+ bool uid_specified = false;
+ bool gid_specified = false;
separator[0] = ',';
separator[1] = 0;
@@ -1093,18 +1097,20 @@
"too long.\n");
return 1;
}
- } else if (strnicmp(data, "uid", 3) == 0) {
- if (value && *value)
- vol->linux_uid =
- simple_strtoul(value, &value, 0);
- } else if (strnicmp(data, "forceuid", 8) == 0) {
- vol->override_uid = 1;
- } else if (strnicmp(data, "gid", 3) == 0) {
- if (value && *value)
- vol->linux_gid =
- simple_strtoul(value, &value, 0);
- } else if (strnicmp(data, "forcegid", 8) == 0) {
- vol->override_gid = 1;
+ } else if (!strnicmp(data, "uid", 3) && value && *value) {
+ vol->linux_uid = simple_strtoul(value, &value, 0);
+ uid_specified = true;
+ } else if (!strnicmp(data, "forceuid", 8)) {
+ override_uid = 1;
+ } else if (!strnicmp(data, "noforceuid", 10)) {
+ override_uid = 0;
+ } else if (!strnicmp(data, "gid", 3) && value && *value) {
+ vol->linux_gid = simple_strtoul(value, &value, 0);
+ gid_specified = true;
+ } else if (!strnicmp(data, "forcegid", 8)) {
+ override_gid = 1;
+ } else if (!strnicmp(data, "noforcegid", 10)) {
+ override_gid = 0;
} else if (strnicmp(data, "file_mode", 4) == 0) {
if (value && *value) {
vol->file_mode =
@@ -1355,6 +1361,18 @@
if (vol->UNCip == NULL)
vol->UNCip = &vol->UNC[2];
+ if (uid_specified)
+ vol->override_uid = override_uid;
+ else if (override_uid == 1)
+ printk(KERN_NOTICE "CIFS: ignoring forceuid mount option "
+ "specified with no uid= option.\n");
+
+ if (gid_specified)
+ vol->override_gid = override_gid;
+ else if (override_gid == 1)
+ printk(KERN_NOTICE "CIFS: ignoring forcegid mount option "
+ "specified with no gid= option.\n");
+
return 0;
}
@@ -2544,11 +2562,20 @@
if (mount_data != mount_data_global)
kfree(mount_data);
+
mount_data = cifs_compose_mount_options(
cifs_sb->mountdata, full_path + 1,
referrals, &fake_devname);
- kfree(fake_devname);
+
free_dfs_info_array(referrals, num_referrals);
+ kfree(fake_devname);
+ kfree(full_path);
+
+ if (IS_ERR(mount_data)) {
+ rc = PTR_ERR(mount_data);
+ mount_data = NULL;
+ goto mount_fail_check;
+ }
if (tcon)
cifs_put_tcon(tcon);
@@ -2556,8 +2583,6 @@
cifs_put_smb_ses(pSesInfo);
cleanup_volume_info(&volume_info);
- FreeXid(xid);
- kfree(full_path);
referral_walks_count++;
goto try_mount_again;
}
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 3d3ddb3..2dfd477 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -412,8 +412,10 @@
return 0; /* Do not request flush for shadow page cache */
if (!sb) {
writer = nilfs_get_writer(NILFS_MDT(inode)->mi_nilfs);
- if (!writer)
+ if (!writer) {
+ nilfs_put_writer(NILFS_MDT(inode)->mi_nilfs);
return -EROFS;
+ }
sb = writer->s_super;
}
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 8b5e477..51ff3d0a 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1859,12 +1859,26 @@
if (!page)
return;
- if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page))
+ if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) {
/*
* For b-tree node pages, this function may be called twice
* or more because they might be split in a segment.
*/
+ if (PageDirty(page)) {
+ /*
+ * For pages holding split b-tree node buffers, dirty
+ * flag on the buffers may be cleared discretely.
+ * In that case, the page is once redirtied for
+ * remaining buffers, and it must be cancelled if
+ * all the buffers get cleaned later.
+ */
+ lock_page(page);
+ if (nilfs_page_buffers_clean(page))
+ __nilfs_clear_page_dirty(page);
+ unlock_page(page);
+ }
return;
+ }
__nilfs_end_page_io(page, err);
}
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index bd15d7a..e604e6e 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -181,8 +181,9 @@
freq : 1, /* use freq, not period */
inherit_stat : 1, /* per task counts */
enable_on_exec : 1, /* next exec enables */
+ task : 1, /* trace fork/exit */
- __reserved_1 : 51;
+ __reserved_1 : 50;
__u32 wakeup_events; /* wakeup every n events */
__u32 __reserved_2;
@@ -311,6 +312,15 @@
/*
* struct {
* struct perf_event_header header;
+ * u32 pid, ppid;
+ * u32 tid, ptid;
+ * };
+ */
+ PERF_EVENT_EXIT = 4,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
* u64 time;
* u64 id;
* u64 stream_id;
@@ -323,6 +333,7 @@
* struct {
* struct perf_event_header header;
* u32 pid, ppid;
+ * u32 tid, ptid;
* };
*/
PERF_EVENT_FORK = 7,
diff --git a/init/Kconfig b/init/Kconfig
index cb2c092..3f7e609 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -940,6 +940,7 @@
config PERF_COUNTERS
bool "Kernel Performance Counters"
+ default y if PROFILING
depends on HAVE_PERF_COUNTERS
select ANON_INODES
help
@@ -961,9 +962,17 @@
Say Y if unsure.
config EVENT_PROFILE
- bool "Tracepoint profile sources"
+ bool "Tracepoint profiling sources"
depends on PERF_COUNTERS && EVENT_TRACING
default y
+ help
+ Allow the use of tracepoints as software performance counters.
+
+ When this is enabled, you can create perf counters based on
+ tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
+ found in debugfs://tracing/events/*/*/id. (The -e/--events
+ option to the perf tool can parse and interpret symbolic
+ tracepoints, in the subsystem:tracepoint_name format.)
endmenu
diff --git a/kernel/fork.c b/kernel/fork.c
index 29b532e..466531e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1269,6 +1269,7 @@
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
+ perf_counter_fork(p);
return p;
bad_fork_free_pid:
@@ -1410,9 +1411,6 @@
init_completion(&vfork);
}
- if (!(clone_flags & CLONE_THREAD))
- perf_counter_fork(p);
-
audit_finish_fork(p);
tracehook_report_clone(regs, clone_flags, nr, p);
diff --git a/kernel/panic.c b/kernel/panic.c
index 984b3ec..512ab73 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -301,6 +301,7 @@
*/
void oops_enter(void)
{
+ tracing_off();
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
do_oops_enter_exit();
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 9509310..199ed47 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -42,6 +42,7 @@
static atomic_t nr_counters __read_mostly;
static atomic_t nr_mmap_counters __read_mostly;
static atomic_t nr_comm_counters __read_mostly;
+static atomic_t nr_task_counters __read_mostly;
/*
* perf counter paranoia level:
@@ -1654,6 +1655,8 @@
atomic_dec(&nr_mmap_counters);
if (counter->attr.comm)
atomic_dec(&nr_comm_counters);
+ if (counter->attr.task)
+ atomic_dec(&nr_task_counters);
}
if (counter->destroy)
@@ -1688,6 +1691,18 @@
return 0;
}
+static u64 perf_counter_read_tree(struct perf_counter *counter)
+{
+ struct perf_counter *child;
+ u64 total = 0;
+
+ total += perf_counter_read(counter);
+ list_for_each_entry(child, &counter->child_list, child_list)
+ total += perf_counter_read(child);
+
+ return total;
+}
+
/*
* Read the performance counter - simple non blocking version for now
*/
@@ -1707,7 +1722,7 @@
WARN_ON_ONCE(counter->ctx->parent_ctx);
mutex_lock(&counter->child_mutex);
- values[0] = perf_counter_read(counter);
+ values[0] = perf_counter_read_tree(counter);
n = 1;
if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
values[n++] = counter->total_time_enabled +
@@ -2819,10 +2834,12 @@
}
/*
- * fork tracking
+ * task tracking -- fork/exit
+ *
+ * enabled by: attr.comm | attr.mmap | attr.task
*/
-struct perf_fork_event {
+struct perf_task_event {
struct task_struct *task;
struct {
@@ -2830,37 +2847,42 @@
u32 pid;
u32 ppid;
+ u32 tid;
+ u32 ptid;
} event;
};
-static void perf_counter_fork_output(struct perf_counter *counter,
- struct perf_fork_event *fork_event)
+static void perf_counter_task_output(struct perf_counter *counter,
+ struct perf_task_event *task_event)
{
struct perf_output_handle handle;
- int size = fork_event->event.header.size;
- struct task_struct *task = fork_event->task;
+ int size = task_event->event.header.size;
+ struct task_struct *task = task_event->task;
int ret = perf_output_begin(&handle, counter, size, 0, 0);
if (ret)
return;
- fork_event->event.pid = perf_counter_pid(counter, task);
- fork_event->event.ppid = perf_counter_pid(counter, task->real_parent);
+ task_event->event.pid = perf_counter_pid(counter, task);
+ task_event->event.ppid = perf_counter_pid(counter, task->real_parent);
- perf_output_put(&handle, fork_event->event);
+ task_event->event.tid = perf_counter_tid(counter, task);
+ task_event->event.ptid = perf_counter_tid(counter, task->real_parent);
+
+ perf_output_put(&handle, task_event->event);
perf_output_end(&handle);
}
-static int perf_counter_fork_match(struct perf_counter *counter)
+static int perf_counter_task_match(struct perf_counter *counter)
{
- if (counter->attr.comm || counter->attr.mmap)
+ if (counter->attr.comm || counter->attr.mmap || counter->attr.task)
return 1;
return 0;
}
-static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
- struct perf_fork_event *fork_event)
+static void perf_counter_task_ctx(struct perf_counter_context *ctx,
+ struct perf_task_event *task_event)
{
struct perf_counter *counter;
@@ -2869,19 +2891,19 @@
rcu_read_lock();
list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
- if (perf_counter_fork_match(counter))
- perf_counter_fork_output(counter, fork_event);
+ if (perf_counter_task_match(counter))
+ perf_counter_task_output(counter, task_event);
}
rcu_read_unlock();
}
-static void perf_counter_fork_event(struct perf_fork_event *fork_event)
+static void perf_counter_task_event(struct perf_task_event *task_event)
{
struct perf_cpu_context *cpuctx;
struct perf_counter_context *ctx;
cpuctx = &get_cpu_var(perf_cpu_context);
- perf_counter_fork_ctx(&cpuctx->ctx, fork_event);
+ perf_counter_task_ctx(&cpuctx->ctx, task_event);
put_cpu_var(perf_cpu_context);
rcu_read_lock();
@@ -2891,32 +2913,40 @@
*/
ctx = rcu_dereference(current->perf_counter_ctxp);
if (ctx)
- perf_counter_fork_ctx(ctx, fork_event);
+ perf_counter_task_ctx(ctx, task_event);
rcu_read_unlock();
}
+static void perf_counter_task(struct task_struct *task, int new)
+{
+ struct perf_task_event task_event;
+
+ if (!atomic_read(&nr_comm_counters) &&
+ !atomic_read(&nr_mmap_counters) &&
+ !atomic_read(&nr_task_counters))
+ return;
+
+ task_event = (struct perf_task_event){
+ .task = task,
+ .event = {
+ .header = {
+ .type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
+ .misc = 0,
+ .size = sizeof(task_event.event),
+ },
+ /* .pid */
+ /* .ppid */
+ /* .tid */
+ /* .ptid */
+ },
+ };
+
+ perf_counter_task_event(&task_event);
+}
+
void perf_counter_fork(struct task_struct *task)
{
- struct perf_fork_event fork_event;
-
- if (!atomic_read(&nr_comm_counters) &&
- !atomic_read(&nr_mmap_counters))
- return;
-
- fork_event = (struct perf_fork_event){
- .task = task,
- .event = {
- .header = {
- .type = PERF_EVENT_FORK,
- .misc = 0,
- .size = sizeof(fork_event.event),
- },
- /* .pid */
- /* .ppid */
- },
- };
-
- perf_counter_fork_event(&fork_event);
+ perf_counter_task(task, 1);
}
/*
@@ -3875,6 +3905,8 @@
atomic_inc(&nr_mmap_counters);
if (counter->attr.comm)
atomic_inc(&nr_comm_counters);
+ if (counter->attr.task)
+ atomic_inc(&nr_task_counters);
}
return counter;
@@ -4236,8 +4268,10 @@
struct perf_counter_context *child_ctx;
unsigned long flags;
- if (likely(!child->perf_counter_ctxp))
+ if (likely(!child->perf_counter_ctxp)) {
+ perf_counter_task(child, 0);
return;
+ }
local_irq_save(flags);
/*
@@ -4255,15 +4289,22 @@
* incremented the context's refcount before we do put_ctx below.
*/
spin_lock(&child_ctx->lock);
- child->perf_counter_ctxp = NULL;
/*
* If this context is a clone; unclone it so it can't get
* swapped to another process while we're removing all
* the counters from it.
*/
unclone_ctx(child_ctx);
- spin_unlock(&child_ctx->lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+ /*
+ * Report the task dead after unscheduling the counters so that we
+ * won't get any samples after PERF_EVENT_EXIT. We can however still
+ * get a few PERF_EVENT_READ events.
+ */
+ perf_counter_task(child, 0);
+
+ child->perf_counter_ctxp = NULL;
/*
* We can recurse on the same lock type through:
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 052ec4d..d089d05 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -202,6 +202,12 @@
return -EOPNOTSUPP;
}
+static int no_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *tsave, struct timespec __user *rmtp)
+{
+ return -EOPNOTSUPP;
+}
+
/*
* Return nonzero if we know a priori this clockid_t value is bogus.
*/
@@ -254,6 +260,7 @@
.clock_get = posix_get_monotonic_raw,
.clock_set = do_posix_clock_nosettime,
.timer_create = no_timer_create,
+ .nsleep = no_nsleep,
};
register_posix_clock(CLOCK_REALTIME, &clock_realtime);
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index e6c2517..d014efb 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -81,8 +81,21 @@
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
- if (lowest_mask)
+ if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+
+ /*
+ * We have to ensure that we have at least one bit
+ * still set in the array, since the map could have
+ * been concurrently emptied between the first and
+ * second reads of vec->mask. If we hit this
+ * condition, simply act as though we never hit this
+ * priority level and continue on.
+ */
+ if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+ continue;
+ }
+
return 1;
}
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 9ffb2b2..652e8bde 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -611,9 +611,13 @@
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
+ struct task_struct *tsk = NULL;
+
+ if (entity_is_task(se))
+ tsk = task_of(se);
+
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@@ -624,11 +628,11 @@
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
- account_scheduler_latency(tsk, delta >> 10, 1);
+ if (tsk)
+ account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@@ -639,17 +643,19 @@
se->block_start = 0;
se->sum_sleep_runtime += delta;
- /*
- * Blocking time is in units of nanosecs, so shift by 20 to
- * get a milliseconds-range estimation of the amount of
- * time that the task spent sleeping:
- */
- if (unlikely(prof_on == SLEEP_PROFILING)) {
-
- profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
- delta >> 20);
+ if (tsk) {
+ /*
+ * Blocking time is in units of nanosecs, so shift by
+ * 20 to get a milliseconds-range estimation of the
+ * amount of time that the task spent sleeping:
+ */
+ if (unlikely(prof_on == SLEEP_PROFILING)) {
+ profile_hits(SLEEP_PROFILING,
+ (void *)get_wchan(tsk),
+ delta >> 20);
+ }
+ account_scheduler_latency(tsk, delta >> 10, 0);
}
- account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1f3ec2a..1e1d23c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1662,7 +1662,7 @@
mutex_lock(&ftrace_regex_lock);
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND))
+ (file->f_flags & O_TRUNC))
ftrace_filter_reset(enable);
if (file->f_mode & FMODE_READ) {
@@ -2577,7 +2577,7 @@
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND)) {
+ (file->f_flags & O_TRUNC)) {
ftrace_graph_count = 0;
memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8bc8d8a..8930e39 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2031,7 +2031,7 @@
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND)) {
+ (file->f_flags & O_TRUNC)) {
long cpu = (long) inode->i_private;
if (cpu == TRACE_PIPE_ALL_CPU)
@@ -3085,7 +3085,8 @@
break;
}
- trace_consume(iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(iter);
rem -= count;
if (!find_next_entry_inc(iter)) {
rem = 0;
@@ -4233,8 +4234,11 @@
iter.pos = -1;
if (find_next_entry_inc(&iter) != NULL) {
- print_trace_line(&iter);
- trace_consume(&iter);
+ int ret;
+
+ ret = print_trace_line(&iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(&iter);
}
trace_printk_seq(&iter.seq);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 53c8fd3..23d2972b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -376,7 +376,7 @@
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND))
+ (file->f_flags & O_TRUNC))
ftrace_clear_events();
seq_ops = inode->i_private;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d2249ab..420ec348 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -843,9 +843,16 @@
switch (entry->type) {
case TRACE_GRAPH_ENT: {
- struct ftrace_graph_ent_entry *field;
+ /*
+ * print_graph_entry() may consume the current event,
+ * thus @field may become invalid, so we need to save it.
+ * sizeof(struct ftrace_graph_ent_entry) is very small,
+ * it can be safely saved at the stack.
+ */
+ struct ftrace_graph_ent_entry *field, saved;
trace_assign_type(field, entry);
- return print_graph_entry(field, s, iter);
+ saved = *field;
+ return print_graph_entry(&saved, s, iter);
}
case TRACE_GRAPH_RET: {
struct ftrace_graph_ret_entry *field;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 7b62781..687699d 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -176,7 +176,7 @@
const char *str = *fmt;
int i;
- seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
+ seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
/*
* Tabs and new lines need to be converted.
diff --git a/lib/flex_array.c b/lib/flex_array.c
index 0e7894c..08f1636 100644
--- a/lib/flex_array.c
+++ b/lib/flex_array.c
@@ -254,7 +254,6 @@
{
int part_nr = fa_element_to_part_nr(fa, element_nr);
struct flex_array_part *part;
- int index;
if (element_nr >= fa->total_nr_elements)
return NULL;
@@ -264,6 +263,5 @@
part = (struct flex_array_part *)&fa->parts[0];
else
part = fa->parts[part_nr];
- index = index_inside_part(fa, element_nr);
return &part->elements[index_inside_part(fa, element_nr)];
}
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 7109e2b..d29baa2 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -403,7 +403,6 @@
# section found, now is this a start of a function?
} elsif ($read_function && /$function_regex/) {
$text_found = 1;
- $offset = hex $1;
$text = $2;
# if this is either a local function or a weak function
@@ -412,10 +411,12 @@
if (!defined($locals{$text}) && !defined($weak{$text})) {
$ref_func = $text;
$read_function = 0;
+ $offset = hex $1;
} else {
# if we already have a function, and this is weak, skip it
- if (!defined($ref_func) || !defined($weak{$text})) {
+ if (!defined($ref_func) && !defined($weak{$text})) {
$ref_func = $text;
+ $offset = hex $1;
}
}
} elsif ($read_headers && /$mcount_section/) {
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index a5e9b87..4b20fa4 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -345,7 +345,7 @@
BUILTIN_OBJS += builtin-top.o
PERFLIBS = $(LIB_FILE)
-EXTLIBS = -lbfd
+EXTLIBS = -lbfd -liberty
#
# Platform specific tweaks
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b20a4b6..ce4f286 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -99,6 +99,7 @@
struct fork_event {
struct perf_event_header header;
u32 pid, ppid;
+ u32 tid, ptid;
};
struct lost_event {
@@ -252,7 +253,7 @@
{
int n = 0;
- while (pathname[n] == cwd[n] && n < cwdlen)
+ while (n < cwdlen && pathname[n] == cwd[n])
++n;
return n;
@@ -1608,15 +1609,27 @@
}
static int
-process_fork_event(event_t *event, unsigned long offset, unsigned long head)
+process_task_event(event_t *event, unsigned long offset, unsigned long head)
{
struct thread *thread = threads__findnew(event->fork.pid);
struct thread *parent = threads__findnew(event->fork.ppid);
- dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n",
+ dprintf("%p [%p]: PERF_EVENT_%s: (%d:%d):(%d:%d)\n",
(void *)(offset + head),
(void *)(long)(event->header.size),
- event->fork.pid, event->fork.ppid);
+ event->header.type == PERF_EVENT_FORK ? "FORK" : "EXIT",
+ event->fork.pid, event->fork.tid,
+ event->fork.ppid, event->fork.ptid);
+
+ /*
+ * A thread clone will have the same PID for both
+ * parent and child.
+ */
+ if (thread == parent)
+ return 0;
+
+ if (event->header.type == PERF_EVENT_EXIT)
+ return 0;
if (!thread || !parent || thread__fork(thread, parent)) {
dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
@@ -1706,7 +1719,8 @@
return process_comm_event(event, offset, head);
case PERF_EVENT_FORK:
- return process_fork_event(event, offset, head);
+ case PERF_EVENT_EXIT:
+ return process_task_event(event, offset, head);
case PERF_EVENT_LOST:
return process_lost_event(event, offset, head);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c0a4230..f139f1a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -285,6 +285,7 @@
"enter_idle",
"exit_idle",
"mwait_idle",
+ "mwait_idle_with_hints",
"ppc64_runlatch_off",
"pseries_dedicated_idle_sleep",
NULL
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index c6e5dc0..2726fe40 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -318,7 +318,7 @@
strbuf_addch(out, '"');
if (prefix) {
int off = 0;
- while (prefix[off] && off < len && prefix[off] == in[off])
+ while (off < len && prefix[off] && prefix[off] == in[off])
if (prefix[off] == '/') {
prefix += off + 1;
in += off + 1;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 2810605..b4fe057 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -565,7 +565,7 @@
goto out_elf_end;
secstrs = elf_getdata(sec_strndx, NULL);
- if (symstrs == NULL)
+ if (secstrs == NULL)
goto out_elf_end;
nr_syms = shdr.sh_size / shdr.sh_entsize;
