Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Two documentation updates, plus a debugging annotation fix"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/crash: Update the stale comment in reserve_crashkernel()
  x86/irq, trace: Add __irq_entry annotation to x86's platform IRQ handlers
  Documentation, x86, resctrl: Recommend locking for resctrlfs

10 files changed, 144 insertions, 22 deletions

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index d918d268cd72..51cf6fa5591f 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -212,3 +212,117 @@ Finally we move core 4-7 over to the new group and make sure that the
 kernel and the tasks running there get 50% of the cache.
 
 # echo C0 > p0/cpus
+
+4) Locking between applications
+
+Certain operations on the resctrl filesystem, composed of read/writes
+to/from multiple files, must be atomic.
+
+As an example, the allocation of an exclusive reservation of L3 cache
+involves:
+
+  1. Read the cbmmasks from each directory
+  2. Find a contiguous set of bits in the global CBM bitmask that is clear
+     in any of the directory cbmmasks
+  3. Create a new directory
+  4. Set the bits found in step 2 to the new directory "schemata" file
+
+If two applications attempt to allocate space concurrently then they can
+end up allocating the same bits so the reservations are shared instead of
+exclusive.
+
+To coordinate atomic operations on the resctrlfs and to avoid the problem
+above, the following locking procedure is recommended:
+
+Locking is based on flock, which is available in libc and also as a shell
+script command
+
+Write lock:
+
+ A) Take flock(LOCK_EX) on /sys/fs/resctrl
+ B) Read/write the directory structure.
+ C) funlock
+
+Read lock:
+
+ A) Take flock(LOCK_SH) on /sys/fs/resctrl
+ B) If success read the directory structure.
+ C) funlock
+
+Example with bash:
+
+# Atomically read directory structure
+$ flock -s /sys/fs/resctrl/ find /sys/fs/resctrl
+
+# Read directory contents and create new subdirectory
+
+$ cat create-dir.sh
+find /sys/fs/resctrl/ > output.txt
+mask = function-of(output.txt)
+mkdir /sys/fs/resctrl/newres/
+echo mask > /sys/fs/resctrl/newres/schemata
+
+$ flock /sys/fs/resctrl/ ./create-dir.sh
+
+Example with C:
+
+/*
+ * Example code do take advisory locks
+ * before accessing resctrl filesystem
+ */
+#include <sys/file.h>
+#include <stdlib.h>
+
+void resctrl_take_shared_lock(int fd)
+{
+	int ret;
+
+	/* take shared lock on resctrl filesystem */
+	ret = flock(fd, LOCK_SH);
+	if (ret) {
+		perror("flock");
+		exit(-1);
+	}
+}
+
+void resctrl_take_exclusive_lock(int fd)
+{
+	int ret;
+
+	/* release lock on resctrl filesystem */
+	ret = flock(fd, LOCK_EX);
+	if (ret) {
+		perror("flock");
+		exit(-1);
+	}
+}
+
+void resctrl_release_lock(int fd)
+{
+	int ret;
+
+	/* take shared lock on resctrl filesystem */
+	ret = flock(fd, LOCK_UN);
+	if (ret) {
+		perror("flock");
+		exit(-1);
+	}
+}
+
+void main(void)
+{
+	int fd, ret;
+
+	fd = open("/sys/fs/resctrl", O_DIRECTORY);
+	if (fd == -1) {
+		perror("open");
+		exit(-1);
+	}
+	resctrl_take_shared_lock(fd);
+	/* code to read directory contents */
+	resctrl_release_lock(fd);
+
+	resctrl_take_exclusive_lock(fd);
+	/* code to read and write directory contents */
+	resctrl_release_lock(fd);
+}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8567c851172c..4261b3282ad9 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1865,14 +1865,14 @@ static void __smp_spurious_interrupt(u8 vector)
 		"should never happen.\n", vector, smp_processor_id());
 }
 
-__visible void smp_spurious_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_spurious_interrupt(~regs->orig_ax);
 	exiting_irq();
 }
 
-__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs)
 {
 	u8 vector = ~regs->orig_ax;
 
@@ -1923,14 +1923,14 @@ static void __smp_error_interrupt(struct pt_regs *regs)
 
 }
 
-__visible void smp_error_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_error_interrupt(regs);
 	exiting_irq();
 }
 
-__visible void smp_trace_error_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_error_apic_entry(ERROR_APIC_VECTOR);
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 5d30c5e42bb1..f3557a1eb562 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -559,7 +559,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 		__send_cleanup_vector(data);
 }
 
-asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
+asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 9e5427df3243..524cc5780a77 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -816,14 +816,14 @@ static inline void __smp_deferred_error_interrupt(void)
 	deferred_error_int_vector();
 }
 
-asmlinkage __visible void smp_deferred_error_interrupt(void)
+asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void)
 {
 	entering_irq();
 	__smp_deferred_error_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void)
 {
 	entering_irq();
 	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 85469f84c921..d7cc190ae457 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -396,14 +396,16 @@ static inline void __smp_thermal_interrupt(void)
 	smp_thermal_vector();
 }
 
-asmlinkage __visible void smp_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void __irq_entry
+smp_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_thermal_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void __irq_entry
+smp_trace_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index 9beb092d68a5..bb0e75eed10a 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -23,14 +23,14 @@ static inline void __smp_threshold_interrupt(void)
 	mce_threshold_vector();
 }
 
-asmlinkage __visible void smp_threshold_interrupt(void)
+asmlinkage __visible void __irq_entry smp_threshold_interrupt(void)
 {
 	entering_irq();
 	__smp_threshold_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage __visible void smp_trace_threshold_interrupt(void)
+asmlinkage __visible void __irq_entry smp_trace_threshold_interrupt(void)
 {
 	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7c6e9ffe4424..4d8183b5f113 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -264,7 +264,7 @@ void __smp_x86_platform_ipi(void)
 		x86_platform_ipi_callback();
 }
 
-__visible void smp_x86_platform_ipi(struct pt_regs *regs)
+__visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -315,7 +315,7 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
 }
 #endif
 
-__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 3512ba607361..275487872be2 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -9,6 +9,7 @@
 #include <linux/hardirq.h>
 #include <asm/apic.h>
 #include <asm/trace/irq_vectors.h>
+#include <linux/interrupt.h>
 
 static inline void __smp_irq_work_interrupt(void)
 {
@@ -16,14 +17,14 @@ static inline void __smp_irq_work_interrupt(void)
 	irq_work_run();
 }
 
-__visible void smp_irq_work_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	__smp_irq_work_interrupt();
 	exiting_irq();
 }
 
-__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_irq_work_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	trace_irq_work_entry(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 69780edf0dde..4bf0c8926a1c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -575,7 +575,9 @@ static void __init reserve_crashkernel(void)
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
 		/*
-		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
+		 * Set CRASH_ADDR_LOW_MAX upper bound for crash memory,
+		 * as old kexec-tools loads bzImage below that, unless
+		 * "crashkernel=size[KMG],high" is specified.
 		 */
 		crash_base = memblock_find_in_range(CRASH_ALIGN,
 						    high ? CRASH_ADDR_HIGH_MAX
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 68f8cc222f25..d3c66a15bbde 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -259,7 +259,7 @@ static inline void __smp_reschedule_interrupt(void)
 	scheduler_ipi();
 }
 
-__visible void smp_reschedule_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	__smp_reschedule_interrupt();
@@ -268,7 +268,7 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs)
 	 */
 }
 
-__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs)
 {
 	/*
 	 * Need to call irq_enter() before calling the trace point.
@@ -292,14 +292,15 @@ static inline void __smp_call_function_interrupt(void)
 	inc_irq_stat(irq_call_count);
 }
 
-__visible void smp_call_function_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	__smp_call_function_interrupt();
 	exiting_irq();
 }
 
-__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
+__visible void __irq_entry
+smp_trace_call_function_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
@@ -314,14 +315,16 @@ static inline void __smp_call_function_single_interrupt(void)
 	inc_irq_stat(irq_call_count);
 }
 
-__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
+__visible void __irq_entry
+smp_call_function_single_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	__smp_call_function_single_interrupt();
 	exiting_irq();
 }
 
-__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+__visible void __irq_entry
+smp_trace_call_function_single_interrupt(struct pt_regs *regs)
 {
 	ipi_entering_ack_irq();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);