Merge commit 'v2.6.36-rc5' into perf/core

Merge reason: Pick up the latest fixes in -rc5.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

8 files changed, 38 insertions, 48 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8aa1b59..e8c8881 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -74,7 +74,7 @@ endif
 
 ifdef CONFIG_CC_STACKPROTECTOR
 	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
-        ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(biarch)),y)
+        ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
                 stackp-y := -fstack-protector
                 KBUILD_CFLAGS += $(stackp-y)
         else
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index b86feab..518bb99 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -50,7 +50,12 @@
 	/*
 	 * Reload arg registers from stack in case ptrace changed them.
 	 * We don't reload %eax because syscall_trace_enter() returned
-	 * the value it wants us to use in the table lookup.
+	 * the %rax value we should see.  Instead, we just truncate that
+	 * value to 32 bits again as we did on entry from user mode.
+	 * If it's a new value set by user_regset during entry tracing,
+	 * this matches the normal truncation of the user-mode value.
+	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
+	 * an appropriately invalid value.
 	 */
 	.macro LOAD_ARGS32 offset, _r9=0
 	.if \_r9
@@ -60,6 +65,7 @@
 	movl \offset+48(%rsp),%edx
 	movl \offset+56(%rsp),%esi
 	movl \offset+64(%rsp),%edi
+	movl %eax,%eax			/* zero extension */
 	.endm
 	
 	.macro CFI_STARTPROC32 simple
@@ -153,7 +159,7 @@ ENTRY(ia32_sysenter_target)
 	testl  $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	CFI_REMEMBER_STATE
 	jnz  sysenter_tracesys
-	cmpl	$(IA32_NR_syscalls-1),%eax
+	cmpq	$(IA32_NR_syscalls-1),%rax
 	ja	ia32_badsys
 sysenter_do_call:
 	IA32_ARG_FIXUP
@@ -195,7 +201,7 @@ sysexit_from_sys_call:
 	movl $AUDIT_ARCH_I386,%edi	/* 1st arg: audit arch */
 	call audit_syscall_entry
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall number */
-	cmpl $(IA32_NR_syscalls-1),%eax
+	cmpq $(IA32_NR_syscalls-1),%rax
 	ja ia32_badsys
 	movl %ebx,%edi			/* reload 1st syscall arg */
 	movl RCX-ARGOFFSET(%rsp),%esi	/* reload 2nd syscall arg */
@@ -248,7 +254,7 @@ sysenter_tracesys:
 	call	syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	cmpl	$(IA32_NR_syscalls-1),%eax
+	cmpq	$(IA32_NR_syscalls-1),%rax
 	ja	int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
 	jmp	sysenter_do_call
 	CFI_ENDPROC
@@ -314,7 +320,7 @@ ENTRY(ia32_cstar_target)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	CFI_REMEMBER_STATE
 	jnz   cstar_tracesys
-	cmpl $IA32_NR_syscalls-1,%eax
+	cmpq $IA32_NR_syscalls-1,%rax
 	ja  ia32_badsys
 cstar_do_call:
 	IA32_ARG_FIXUP 1
@@ -367,7 +373,7 @@ cstar_tracesys:
 	LOAD_ARGS32 ARGOFFSET, 1  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
 	xchgl %ebp,%r9d
-	cmpl $(IA32_NR_syscalls-1),%eax
+	cmpq $(IA32_NR_syscalls-1),%rax
 	ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
 	jmp cstar_do_call
 END(ia32_cstar_target)
@@ -425,7 +431,7 @@ ENTRY(ia32_syscall)
 	orl   $TS_COMPAT,TI_status(%r10)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	jnz ia32_tracesys
-	cmpl $(IA32_NR_syscalls-1),%eax
+	cmpq $(IA32_NR_syscalls-1),%rax
 	ja ia32_badsys
 ia32_do_call:
 	IA32_ARG_FIXUP
@@ -444,7 +450,7 @@ ia32_tracesys:
 	call syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	cmpl $(IA32_NR_syscalls-1),%eax
+	cmpq $(IA32_NR_syscalls-1),%rax
 	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
 	jmp ia32_do_call
 END(ia32_syscall)
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 306160e..1d9cd27 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -205,7 +205,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-static inline void __user *compat_alloc_user_space(long len)
+static inline void __user *arch_compat_alloc_user_space(long len)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	return (void __user *)regs->sp - len;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 781a50b..c6fbb7b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -296,6 +296,7 @@ extern const char * const x86_power_flags[32];
 
 #endif /* CONFIG_X86_64 */
 
+#if __GNUC__ >= 4
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These are only valid after alternatives have run, but will statically
@@ -304,7 +305,7 @@ extern const char * const x86_power_flags[32];
  */
 static __always_inline __pure bool __static_cpu_has(u16 bit)
 {
-#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5)
+#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
 		asm goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
@@ -345,7 +346,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 #endif
 }
 
-#if __GNUC__ >= 4
 #define static_cpu_has(bit)					\
 (								\
 	__builtin_constant_p(boot_cpu_has(bit)) ?		\
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 004e6e2..1d5c08a 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -68,7 +68,6 @@ extern unsigned long force_hpet_address;
 extern u8 hpet_blockid;
 extern int hpet_force_user;
 extern u8 hpet_msi_disable;
-extern u8 hpet_readback_cmp;
 extern int is_hpet_enabled(void);
 extern int hpet_enable(void);
 extern void hpet_disable(void);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 7b598b8..f744f54 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -698,9 +698,11 @@ void __init uv_system_init(void)
 		for (j = 0; j < 64; j++) {
 			if (!test_bit(j, &present))
 				continue;
-			uv_blade_info[blade].pnode = (i * 64 + j);
+			pnode = (i * 64 + j);
+			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
+			max_pnode = max(pnode, max_pnode);
 			blade++;
 		}
 	}
@@ -738,7 +740,6 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
-		max_pnode = max(pnode, max_pnode);
 	}
 
 	/* Add blade/pnode info for nodes without cpus */
@@ -750,7 +751,6 @@ void __init uv_system_init(void)
 		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);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index e5cc7e8..ebdb85c 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,7 +18,6 @@
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
-#include <asm/hpet.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -192,21 +191,6 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
-/*
- * Force the read back of the CMP register in hpet_next_event()
- * to work around the problem that the CMP register write seems to be
- * delayed. See hpet_next_event() for details.
- *
- * We do this on all SMBUS incarnations for now until we have more
- * information about the affected chipsets.
- */
-static void __init ati_hpet_bugs(int num, int slot, int func)
-{
-#ifdef CONFIG_HPET_TIMER
-	hpet_readback_cmp = 1;
-#endif
-}
-
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -236,8 +220,6 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
-	{ PCI_VENDOR_ID_ATI, PCI_ANY_ID,
-	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs },
 	{}
 };
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 351f9c0..410fdb3 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -35,7 +35,6 @@
 unsigned long				hpet_address;
 u8					hpet_blockid; /* OS timer block num */
 u8					hpet_msi_disable;
-u8					hpet_readback_cmp;
 
 #ifdef CONFIG_PCI_MSI
 static unsigned long			hpet_num_timers;
@@ -395,23 +394,27 @@ static int hpet_next_event(unsigned long delta,
 	 * at that point and we would wait for the next hpet interrupt
 	 * forever. We found out that reading the CMP register back
 	 * forces the transfer so we can rely on the comparison with
-	 * the counter register below.
+	 * the counter register below. If the read back from the
+	 * compare register does not match the value we programmed
+	 * then we might have a real hardware problem. We can not do
+	 * much about it here, but at least alert the user/admin with
+	 * a prominent warning.
 	 *
-	 * That works fine on those ATI chipsets, but on newer Intel
-	 * chipsets (ICH9...) this triggers due to an erratum: Reading
-	 * the comparator immediately following a write is returning
-	 * the old value.
+	 * An erratum on some chipsets (ICH9,..), results in
+	 * comparator read immediately following a write returning old
+	 * value. Workaround for this is to read this value second
+	 * time, when first read returns old value.
 	 *
-	 * We restrict the read back to the affected ATI chipsets (set
-	 * by quirks) and also run it with hpet=verbose for debugging
-	 * purposes.
+	 * In fact the write to the comparator register is delayed up
+	 * to two HPET cycles so the workaround we tried to restrict
+	 * the readback to those known to be borked ATI chipsets
+	 * failed miserably. So we give up on optimizations forever
+	 * and penalize all HPET incarnations unconditionally.
 	 */
-	if (hpet_readback_cmp || hpet_verbose) {
-		u32 cmp = hpet_readl(HPET_Tn_CMP(timer));
-
-		if (cmp != cnt)
+	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
+		if (hpet_readl(HPET_Tn_CMP(timer)) != cnt)
 			printk_once(KERN_WARNING
-			    "hpet: compare register read back failed.\n");
+				"hpet: compare register read back failed.\n");
 	}
 
 	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;