* [GIT PULL] x86/apic changes for v4.4
@ 2015-11-03 10:32 Ingo Molnar
2015-11-04 2:14 ` Linus Torvalds
0 siblings, 1 reply; 2+ messages in thread
From: Ingo Molnar @ 2015-11-03 10:32 UTC (permalink / raw)
To: Linus Torvalds
Cc: linux-kernel, Thomas Gleixner, H. Peter Anvin, Andrew Morton,
Peter Zijlstra
Linus,
Please pull the latest x86-apic-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-apic-for-linus
# HEAD: 4faefda97bc1be6ca909ba0fd0927ea78f37f67e x86/io_apic: Make eoi_ioapic_pin() static
The main changes in this cycle were:
- Numachip updates: new hardware support, fixes and cleanups. (Daniel J Blueman)
- misc smaller cleanups and fixlets.
out-of-topic modifications in x86-apic-for-linus:
---------------------------------------------------
drivers/clocksource/Makefile # ce2e572cfe7b: x86/numachip: Introduce Numa
drivers/clocksource/numachip.c # ef34cc3428a7: x86/numachip: Fix timer buil
# ce2e572cfe7b: x86/numachip: Introduce Numa
Thanks,
Ingo
------------------>
Andy Shevchenko (1):
x86/io_apic: Make eoi_ioapic_pin() static
Daniel J Blueman (5):
x86/numachip: Cleanup Numachip support
x86/numachip: Add Numachip2 APIC support
x86/numachip: Add Numachip IPI optimisations
x86/numachip: Introduce Numachip2 timer mechanisms
x86/numachip: Fix timer build conflict
Denys Vlasenko (1):
x86/apic: Deinline various functions
Geliang Tang (1):
x86/irq: Drop unlikely before IS_ERR_OR_NULL
Paolo Bonzini (1):
x86/x2apic: Make stub functions available even if !CONFIG_X86_LOCAL_APIC
arch/x86/include/asm/apic.h | 110 +++++++-------
arch/x86/include/asm/numachip/numachip.h | 1 +
arch/x86/include/asm/numachip/numachip_csr.h | 153 +++++--------------
arch/x86/kernel/apic/apic.c | 8 +-
arch/x86/kernel/apic/apic_numachip.c | 220 +++++++++++++++++++--------
arch/x86/kernel/apic/io_apic.c | 2 +-
arch/x86/kernel/irq_64.c | 2 +-
drivers/clocksource/Makefile | 1 +
drivers/clocksource/numachip.c | 95 ++++++++++++
9 files changed, 360 insertions(+), 232 deletions(-)
create mode 100644 drivers/clocksource/numachip.c
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ebf6d5e5668c..a30316bf801a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -115,6 +115,59 @@ static inline bool apic_is_x2apic_enabled(void)
return msr & X2APIC_ENABLE;
}
+extern void enable_IR_x2apic(void);
+
+extern int get_physical_broadcast(void);
+
+extern int lapic_get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void disconnect_bsp_APIC(int virt_wire_setup);
+extern void disable_local_APIC(void);
+extern void lapic_shutdown(void);
+extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
+extern void setup_local_APIC(void);
+extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
+extern void setup_boot_APIC_clock(void);
+extern void setup_secondary_APIC_clock(void);
+extern int APIC_init_uniprocessor(void);
+
+#ifdef CONFIG_X86_64
+static inline int apic_force_enable(unsigned long addr)
+{
+ return -1;
+}
+#else
+extern int apic_force_enable(unsigned long addr);
+#endif
+
+extern int apic_bsp_setup(bool upmode);
+extern void apic_ap_setup(void);
+
+/*
+ * On 32bit this is mach-xxx local
+ */
+#ifdef CONFIG_X86_64
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+ return 0;
+}
+#endif
+
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
+
+#else /* !CONFIG_X86_LOCAL_APIC */
+static inline void lapic_shutdown(void) { }
+#define local_apic_timer_c2_ok 1
+static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
+# define setup_boot_APIC_clock x86_init_noop
+# define setup_secondary_APIC_clock x86_init_noop
+#endif /* !CONFIG_X86_LOCAL_APIC */
+
#ifdef CONFIG_X86_X2APIC
/*
* Make previous memory operations globally visible before
@@ -186,67 +239,14 @@ static inline int x2apic_enabled(void)
}
#define x2apic_supported() (cpu_has_x2apic)
-#else
+#else /* !CONFIG_X86_X2APIC */
static inline void check_x2apic(void) { }
static inline void x2apic_setup(void) { }
static inline int x2apic_enabled(void) { return 0; }
#define x2apic_mode (0)
#define x2apic_supported() (0)
-#endif
-
-extern void enable_IR_x2apic(void);
-
-extern int get_physical_broadcast(void);
-
-extern int lapic_get_maxlvt(void);
-extern void clear_local_APIC(void);
-extern void disconnect_bsp_APIC(int virt_wire_setup);
-extern void disable_local_APIC(void);
-extern void lapic_shutdown(void);
-extern void sync_Arb_IDs(void);
-extern void init_bsp_APIC(void);
-extern void setup_local_APIC(void);
-extern void init_apic_mappings(void);
-void register_lapic_address(unsigned long address);
-extern void setup_boot_APIC_clock(void);
-extern void setup_secondary_APIC_clock(void);
-extern int APIC_init_uniprocessor(void);
-
-#ifdef CONFIG_X86_64
-static inline int apic_force_enable(unsigned long addr)
-{
- return -1;
-}
-#else
-extern int apic_force_enable(unsigned long addr);
-#endif
-
-extern int apic_bsp_setup(bool upmode);
-extern void apic_ap_setup(void);
-
-/*
- * On 32bit this is mach-xxx local
- */
-#ifdef CONFIG_X86_64
-extern int apic_is_clustered_box(void);
-#else
-static inline int apic_is_clustered_box(void)
-{
- return 0;
-}
-#endif
-
-extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
-
-#else /* !CONFIG_X86_LOCAL_APIC */
-static inline void lapic_shutdown(void) { }
-#define local_apic_timer_c2_ok 1
-static inline void init_apic_mappings(void) { }
-static inline void disable_local_APIC(void) { }
-# define setup_boot_APIC_clock x86_init_noop
-# define setup_secondary_APIC_clock x86_init_noop
-#endif /* !CONFIG_X86_LOCAL_APIC */
+#endif /* !CONFIG_X86_X2APIC */
#ifdef CONFIG_X86_64
#define SET_APIC_ID(x) (apic->set_apic_id(x))
diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h
index 1c6f7f6212c1..c64373a2d731 100644
--- a/arch/x86/include/asm/numachip/numachip.h
+++ b/arch/x86/include/asm/numachip/numachip.h
@@ -14,6 +14,7 @@
#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H
#define _ASM_X86_NUMACHIP_NUMACHIP_H
+extern u8 numachip_system;
extern int __init pci_numachip_init(void);
#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */
diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h
index 660f843df928..29719eecdc2e 100644
--- a/arch/x86/include/asm/numachip/numachip_csr.h
+++ b/arch/x86/include/asm/numachip/numachip_csr.h
@@ -14,12 +14,8 @@
#ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
#define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
-#include <linux/numa.h>
-#include <linux/percpu.h>
+#include <linux/smp.h>
#include <linux/io.h>
-#include <linux/swab.h>
-#include <asm/types.h>
-#include <asm/processor.h>
#define CSR_NODE_SHIFT 16
#define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT)
@@ -27,11 +23,8 @@
/* 32K CSR space, b15 indicates geo/non-geo */
#define CSR_OFFSET_MASK 0x7fffUL
-
-/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */
-#define NUMACHIP_GCSR_BASE 0x3fff00000000ULL
-#define NUMACHIP_GCSR_LIM 0x3fff0fffffffULL
-#define NUMACHIP_GCSR_SIZE (NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1)
+#define CSR_G0_NODE_IDS (0x008 + (0 << 12))
+#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12))
/*
* Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however
@@ -41,12 +34,7 @@
#define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL
#define NUMACHIP_LCSR_LIM 0x3fffffffffffULL
#define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1)
-
-static inline void *gcsr_address(int node, unsigned long offset)
-{
- return __va(NUMACHIP_GCSR_BASE | (1UL << 15) |
- CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK));
-}
+#define NUMACHIP_LAPIC_BITS 8
static inline void *lcsr_address(unsigned long offset)
{
@@ -54,114 +42,57 @@ static inline void *lcsr_address(unsigned long offset)
CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK));
}
-static inline unsigned int read_gcsr(int node, unsigned long offset)
+static inline unsigned int read_lcsr(unsigned long offset)
{
- return swab32(readl(gcsr_address(node, offset)));
+ return swab32(readl(lcsr_address(offset)));
}
-static inline void write_gcsr(int node, unsigned long offset, unsigned int val)
+static inline void write_lcsr(unsigned long offset, unsigned int val)
{
- writel(swab32(val), gcsr_address(node, offset));
+ writel(swab32(val), lcsr_address(offset));
}
-static inline unsigned int read_lcsr(unsigned long offset)
+/*
+ * On NumaChip2, local CSR space is 16MB and starts at fixed offset below 4G
+ */
+
+#define NUMACHIP2_LCSR_BASE 0xf0000000UL
+#define NUMACHIP2_LCSR_SIZE 0x1000000UL
+#define NUMACHIP2_APIC_ICR 0x100000
+#define NUMACHIP2_TIMER_DEADLINE 0x200000
+#define NUMACHIP2_TIMER_INT 0x200008
+#define NUMACHIP2_TIMER_NOW 0x200018
+#define NUMACHIP2_TIMER_RESET 0x200020
+
+static inline void __iomem *numachip2_lcsr_address(unsigned long offset)
{
- return swab32(readl(lcsr_address(offset)));
+ return (void __iomem *)__va(NUMACHIP2_LCSR_BASE |
+ (offset & (NUMACHIP2_LCSR_SIZE - 1)));
}
-static inline void write_lcsr(unsigned long offset, unsigned int val)
+static inline u32 numachip2_read32_lcsr(unsigned long offset)
{
- writel(swab32(val), lcsr_address(offset));
+ return readl(numachip2_lcsr_address(offset));
}
-/* ========================================================================= */
-/* CSR_G0_STATE_CLEAR */
-/* ========================================================================= */
-
-#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12))
-union numachip_csr_g0_state_clear {
- unsigned int v;
- struct numachip_csr_g0_state_clear_s {
- unsigned int _state:2;
- unsigned int _rsvd_2_6:5;
- unsigned int _lost:1;
- unsigned int _rsvd_8_31:24;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G0_NODE_IDS */
-/* ========================================================================= */
+static inline u64 numachip2_read64_lcsr(unsigned long offset)
+{
+ return readq(numachip2_lcsr_address(offset));
+}
-#define CSR_G0_NODE_IDS (0x008 + (0 << 12))
-union numachip_csr_g0_node_ids {
- unsigned int v;
- struct numachip_csr_g0_node_ids_s {
- unsigned int _initialid:16;
- unsigned int _nodeid:12;
- unsigned int _rsvd_28_31:4;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G3_EXT_IRQ_GEN */
-/* ========================================================================= */
+static inline void numachip2_write32_lcsr(unsigned long offset, u32 val)
+{
+ writel(val, numachip2_lcsr_address(offset));
+}
-#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12))
-union numachip_csr_g3_ext_irq_gen {
- unsigned int v;
- struct numachip_csr_g3_ext_irq_gen_s {
- unsigned int _vector:8;
- unsigned int _msgtype:3;
- unsigned int _index:5;
- unsigned int _destination_apic_id:16;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G3_EXT_IRQ_STATUS */
-/* ========================================================================= */
-
-#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12))
-union numachip_csr_g3_ext_irq_status {
- unsigned int v;
- struct numachip_csr_g3_ext_irq_status_s {
- unsigned int _result:32;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G3_EXT_IRQ_DEST */
-/* ========================================================================= */
-
-#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12))
-union numachip_csr_g3_ext_irq_dest {
- unsigned int v;
- struct numachip_csr_g3_ext_irq_dest_s {
- unsigned int _irq:8;
- unsigned int _rsvd_8_31:24;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G3_NC_ATT_MAP_SELECT */
-/* ========================================================================= */
-
-#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12))
-union numachip_csr_g3_nc_att_map_select {
- unsigned int v;
- struct numachip_csr_g3_nc_att_map_select_s {
- unsigned int _upper_address_bits:4;
- unsigned int _select_ram:4;
- unsigned int _rsvd_8_31:24;
- } s;
-};
-
-/* ========================================================================= */
-/* CSR_G3_NC_ATT_MAP_SELECT_0-255 */
-/* ========================================================================= */
-
-#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12))
+static inline void numachip2_write64_lcsr(unsigned long offset, u64 val)
+{
+ writeq(val, numachip2_lcsr_address(offset));
+}
-#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */
+static inline unsigned int numachip2_timer(void)
+{
+ return (smp_processor_id() % 48) << 6;
+}
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 24e94ce454e2..2f69e3b184f6 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1431,7 +1431,7 @@ enum {
};
static int x2apic_state;
-static inline void __x2apic_disable(void)
+static void __x2apic_disable(void)
{
u64 msr;
@@ -1447,7 +1447,7 @@ static inline void __x2apic_disable(void)
printk_once(KERN_INFO "x2apic disabled\n");
}
-static inline void __x2apic_enable(void)
+static void __x2apic_enable(void)
{
u64 msr;
@@ -1807,7 +1807,7 @@ int apic_version[MAX_LOCAL_APIC];
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
-static inline void __smp_spurious_interrupt(u8 vector)
+static void __smp_spurious_interrupt(u8 vector)
{
u32 v;
@@ -1848,7 +1848,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
/*
* This interrupt should never happen with our APIC/SMP architecture
*/
-static inline void __smp_error_interrupt(struct pt_regs *regs)
+static void __smp_error_interrupt(struct pt_regs *regs)
{
u32 v;
u32 i = 0;
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index b548fd3b764b..38dd5efdd04c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -11,30 +11,21 @@
*
*/
-#include <linux/errno.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/ctype.h>
#include <linux/init.h>
-#include <linux/hardirq.h>
-#include <linux/delay.h>
#include <asm/numachip/numachip.h>
#include <asm/numachip/numachip_csr.h>
-#include <asm/smp.h>
-#include <asm/apic.h>
#include <asm/ipi.h>
#include <asm/apic_flat_64.h>
#include <asm/pgtable.h>
+#include <asm/pci_x86.h>
-static int numachip_system __read_mostly;
+u8 numachip_system __read_mostly;
+static const struct apic apic_numachip1;
+static const struct apic apic_numachip2;
+static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly;
-static const struct apic apic_numachip;
-
-static unsigned int get_apic_id(unsigned long x)
+static unsigned int numachip1_get_apic_id(unsigned long x)
{
unsigned long value;
unsigned int id = (x >> 24) & 0xff;
@@ -47,7 +38,7 @@ static unsigned int get_apic_id(unsigned long x)
return id;
}
-static unsigned long set_apic_id(unsigned int id)
+static unsigned long numachip1_set_apic_id(unsigned int id)
{
unsigned long x;
@@ -55,9 +46,17 @@ static unsigned long set_apic_id(unsigned int id)
return x;
}
-static unsigned int read_xapic_id(void)
+static unsigned int numachip2_get_apic_id(unsigned long x)
+{
+ u64 mcfg;
+
+ rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg);
+ return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24);
+}
+
+static unsigned long numachip2_set_apic_id(unsigned int id)
{
- return get_apic_id(apic_read(APIC_ID));
+ return id << 24;
}
static int numachip_apic_id_valid(int apicid)
@@ -68,7 +67,7 @@ static int numachip_apic_id_valid(int apicid)
static int numachip_apic_id_registered(void)
{
- return physid_isset(read_xapic_id(), phys_cpu_present_map);
+ return 1;
}
static int numachip_phys_pkg_id(int initial_apic_id, int index_msb)
@@ -76,36 +75,48 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb)
return initial_apic_id >> index_msb;
}
-static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static void numachip1_apic_icr_write(int apicid, unsigned int val)
{
- union numachip_csr_g3_ext_irq_gen int_gen;
-
- int_gen.s._destination_apic_id = phys_apicid;
- int_gen.s._vector = 0;
- int_gen.s._msgtype = APIC_DM_INIT >> 8;
- int_gen.s._index = 0;
-
- write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+ write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val);
+}
- int_gen.s._msgtype = APIC_DM_STARTUP >> 8;
- int_gen.s._vector = start_rip >> 12;
+static void numachip2_apic_icr_write(int apicid, unsigned int val)
+{
+ numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val);
+}
- write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+{
+ numachip_apic_icr_write(phys_apicid, APIC_DM_INIT);
+ numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP |
+ (start_rip >> 12));
return 0;
}
static void numachip_send_IPI_one(int cpu, int vector)
{
- union numachip_csr_g3_ext_irq_gen int_gen;
- int apicid = per_cpu(x86_cpu_to_apicid, cpu);
-
- int_gen.s._destination_apic_id = apicid;
- int_gen.s._vector = vector;
- int_gen.s._msgtype = (vector == NMI_VECTOR ? APIC_DM_NMI : APIC_DM_FIXED) >> 8;
- int_gen.s._index = 0;
+ int local_apicid, apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ unsigned int dmode;
+
+ preempt_disable();
+ local_apicid = __this_cpu_read(x86_cpu_to_apicid);
+
+ /* Send via local APIC where non-local part matches */
+ if (!((apicid ^ local_apicid) >> NUMACHIP_LAPIC_BITS)) {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __default_send_IPI_dest_field(apicid, vector,
+ APIC_DEST_PHYSICAL);
+ local_irq_restore(flags);
+ preempt_enable();
+ return;
+ }
+ preempt_enable();
- write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+ dmode = (vector == NMI_VECTOR) ? APIC_DM_NMI : APIC_DM_FIXED;
+ numachip_apic_icr_write(apicid, dmode | vector);
}
static void numachip_send_IPI_mask(const struct cpumask *mask, int vector)
@@ -149,9 +160,14 @@ static void numachip_send_IPI_self(int vector)
apic_write(APIC_SELF_IPI, vector);
}
-static int __init numachip_probe(void)
+static int __init numachip1_probe(void)
{
- return apic == &apic_numachip;
+ return apic == &apic_numachip1;
+}
+
+static int __init numachip2_probe(void)
+{
+ return apic == &apic_numachip2;
}
static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
@@ -172,34 +188,118 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
static int __init numachip_system_init(void)
{
- if (!numachip_system)
+ /* Map the LCSR area and set up the apic_icr_write function */
+ switch (numachip_system) {
+ case 1:
+ init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
+ numachip_apic_icr_write = numachip1_apic_icr_write;
+ x86_init.pci.arch_init = pci_numachip_init;
+ break;
+ case 2:
+ init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE);
+ numachip_apic_icr_write = numachip2_apic_icr_write;
+
+ /* Use MCFG config cycles rather than locked CF8 cycles */
+ raw_pci_ops = &pci_mmcfg;
+ break;
+ default:
return 0;
-
- init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
- init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE);
+ }
x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
- x86_init.pci.arch_init = pci_numachip_init;
return 0;
}
early_initcall(numachip_system_init);
-static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int numachip1_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
- if (!strncmp(oem_id, "NUMASC", 6)) {
- numachip_system = 1;
- return 1;
- }
+ if ((strncmp(oem_id, "NUMASC", 6) != 0) ||
+ (strncmp(oem_table_id, "NCONNECT", 8) != 0))
+ return 0;
- return 0;
+ numachip_system = 1;
+
+ return 1;
+}
+
+static int numachip2_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ if ((strncmp(oem_id, "NUMASC", 6) != 0) ||
+ (strncmp(oem_table_id, "NCONECT2", 8) != 0))
+ return 0;
+
+ numachip_system = 2;
+
+ return 1;
+}
+
+/* APIC IPIs are queued */
+static void numachip_apic_wait_icr_idle(void)
+{
}
-static const struct apic apic_numachip __refconst = {
+/* APIC NMI IPIs are queued */
+static u32 numachip_safe_apic_wait_icr_idle(void)
+{
+ return 0;
+}
+static const struct apic apic_numachip1 __refconst = {
.name = "NumaConnect system",
- .probe = numachip_probe,
- .acpi_madt_oem_check = numachip_acpi_madt_oem_check,
+ .probe = numachip1_probe,
+ .acpi_madt_oem_check = numachip1_acpi_madt_oem_check,
+ .apic_id_valid = numachip_apic_id_valid,
+ .apic_id_registered = numachip_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 0, /* physical */
+
+ .target_cpus = online_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = 0,
+ .check_apicid_used = NULL,
+
+ .vector_allocation_domain = default_vector_allocation_domain,
+ .init_apic_ldr = flat_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .phys_pkg_id = numachip_phys_pkg_id,
+
+ .get_apic_id = numachip1_get_apic_id,
+ .set_apic_id = numachip1_set_apic_id,
+ .apic_id_mask = 0xffU << 24,
+
+ .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = numachip_send_IPI_mask,
+ .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = numachip_send_IPI_allbutself,
+ .send_IPI_all = numachip_send_IPI_all,
+ .send_IPI_self = numachip_send_IPI_self,
+
+ .wakeup_secondary_cpu = numachip_wakeup_secondary,
+ .inquire_remote_apic = NULL, /* REMRD not supported */
+
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .eoi_write = native_apic_mem_write,
+ .icr_read = native_apic_icr_read,
+ .icr_write = native_apic_icr_write,
+ .wait_icr_idle = numachip_apic_wait_icr_idle,
+ .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle,
+};
+
+apic_driver(apic_numachip1);
+
+static const struct apic apic_numachip2 __refconst = {
+ .name = "NumaConnect2 system",
+ .probe = numachip2_probe,
+ .acpi_madt_oem_check = numachip2_acpi_madt_oem_check,
.apic_id_valid = numachip_apic_id_valid,
.apic_id_registered = numachip_apic_id_registered,
@@ -221,8 +321,8 @@ static const struct apic apic_numachip __refconst = {
.check_phys_apicid_present = default_check_phys_apicid_present,
.phys_pkg_id = numachip_phys_pkg_id,
- .get_apic_id = get_apic_id,
- .set_apic_id = set_apic_id,
+ .get_apic_id = numachip2_get_apic_id,
+ .set_apic_id = numachip2_set_apic_id,
.apic_id_mask = 0xffU << 24,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
@@ -241,8 +341,8 @@ static const struct apic apic_numachip __refconst = {
.eoi_write = native_apic_mem_write,
.icr_read = native_apic_icr_read,
.icr_write = native_apic_icr_write,
- .wait_icr_idle = native_apic_wait_icr_idle,
- .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+ .wait_icr_idle = numachip_apic_wait_icr_idle,
+ .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle,
};
-apic_driver(apic_numachip);
+apic_driver(apic_numachip2);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c60bb162622..b5a0e3c5e930 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -529,7 +529,7 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector)
}
}
-void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
+static void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
{
unsigned long flags;
struct irq_pin_list *entry;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index c767cf2bc80a..206d0b90a3ab 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -72,7 +72,7 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
stack_overflow_check(regs);
- if (unlikely(IS_ERR_OR_NULL(desc)))
+ if (IS_ERR_OR_NULL(desc))
return false;
generic_handle_irq_desc(desc);
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 5c00863c3e33..57dfad312341 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -62,3 +62,4 @@ obj-$(CONFIG_H8300) += h8300_timer8.o
obj-$(CONFIG_H8300_TMR16) += h8300_timer16.o
obj-$(CONFIG_H8300_TPU) += h8300_tpu.o
obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o
+obj-$(CONFIG_X86_NUMACHIP) += numachip.o
diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c
new file mode 100644
index 000000000000..4e0f11fd2617
--- /dev/null
+++ b/drivers/clocksource/numachip.c
@@ -0,0 +1,95 @@
+/*
+ *
+ * Copyright (C) 2015 Numascale AS. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ *
+ */
+
+#include <linux/clockchips.h>
+
+#include <asm/irq.h>
+#include <asm/numachip/numachip.h>
+#include <asm/numachip/numachip_csr.h>
+
+static DEFINE_PER_CPU(struct clock_event_device, numachip2_ced);
+
+static cycles_t numachip2_timer_read(struct clocksource *cs)
+{
+ return numachip2_read64_lcsr(NUMACHIP2_TIMER_NOW);
+}
+
+static struct clocksource numachip2_clocksource = {
+ .name = "numachip2",
+ .rating = 295,
+ .read = numachip2_timer_read,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .mult = 1,
+ .shift = 0,
+};
+
+static int numachip2_set_next_event(unsigned long delta, struct clock_event_device *ced)
+{
+ numachip2_write64_lcsr(NUMACHIP2_TIMER_DEADLINE + numachip2_timer(),
+ delta);
+ return 0;
+}
+
+static struct clock_event_device numachip2_clockevent = {
+ .name = "numachip2",
+ .rating = 400,
+ .set_next_event = numachip2_set_next_event,
+ .features = CLOCK_EVT_FEAT_ONESHOT,
+ .mult = 1,
+ .shift = 0,
+ .min_delta_ns = 1250,
+ .max_delta_ns = LONG_MAX,
+};
+
+static void numachip_timer_interrupt(void)
+{
+ struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+ ced->event_handler(ced);
+}
+
+static __init void numachip_timer_each(struct work_struct *work)
+{
+ unsigned local_apicid = __this_cpu_read(x86_cpu_to_apicid) & 0xff;
+ struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+ /* Setup IPI vector to local core and relative timing mode */
+ numachip2_write64_lcsr(NUMACHIP2_TIMER_INT + numachip2_timer(),
+ (3 << 22) | (X86_PLATFORM_IPI_VECTOR << 14) |
+ (local_apicid << 6));
+
+ *ced = numachip2_clockevent;
+ ced->cpumask = cpumask_of(smp_processor_id());
+ clockevents_register_device(ced);
+}
+
+static int __init numachip_timer_init(void)
+{
+ if (numachip_system != 2)
+ return -ENODEV;
+
+ /* Reset timer */
+ numachip2_write64_lcsr(NUMACHIP2_TIMER_RESET, 0);
+ clocksource_register_hz(&numachip2_clocksource, NSEC_PER_SEC);
+
+ /* Setup per-cpu clockevents */
+ x86_platform_ipi_callback = numachip_timer_interrupt;
+ schedule_on_each_cpu(&numachip_timer_each);
+
+ return 0;
+}
+
+arch_initcall(numachip_timer_init);
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [GIT PULL] x86/apic changes for v4.4
2015-11-03 10:32 [GIT PULL] x86/apic changes for v4.4 Ingo Molnar
@ 2015-11-04 2:14 ` Linus Torvalds
0 siblings, 0 replies; 2+ messages in thread
From: Linus Torvalds @ 2015-11-04 2:14 UTC (permalink / raw)
To: Ingo Molnar
Cc: Linux Kernel Mailing List, Thomas Gleixner, H. Peter Anvin,
Andrew Morton, Peter Zijlstra
[-- Attachment #1: Type: text/plain, Size: 661 bytes --]
On Tue, Nov 3, 2015 at 2:32 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> Please pull the latest x86-apic-for-linus git tree from:
Side note, I have an *old* patch that I think simplifies the
(reasonably common) case of sending IPI's to individual CPU's. That's
done by the "reschedule ipi" in particular.
That's something that is trivially done on the x2apic, but that the
mask-based interfaces makes insanely complicated.
I have *not* rebased this on top of modern kernels so it may not
actually work as a patch any more, because I'm just sending this out
as a "Hmm, what do you guys think" rather than a real submission.
Comments?
Linus
[-- Attachment #2: 0001-x86-add-a-single-target-IPI-function-to-the-apic.patch --]
[-- Type: text/x-patch, Size: 3305 bytes --]
From 9f09a8b2a1fa58f2e692af4a7283fd1674749d39 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 20 Feb 2015 11:06:02 -0800
Subject: [PATCH] x86: add a single-target IPI function to the apic
We still fall back on the "send mask" versions if an apic definition
doesn't have the single-target version, but at least this allows the
(trivial) case for the common clustered x2apic case.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/x86/include/asm/apic.h | 1 +
arch/x86/kernel/apic/x2apic_cluster.c | 9 +++++++++
arch/x86/kernel/smp.c | 16 ++++++++++++++--
3 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 92003f3c8a42..5d47ffcfa65d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -296,6 +296,7 @@ struct apic {
unsigned int *apicid);
/* ipi */
+ void (*send_IPI)(int cpu, int vector);
void (*send_IPI_mask)(const struct cpumask *mask, int vector);
void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
int vector);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index e658f21681c8..177c4fb027a1 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu)
return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16;
}
+static void x2apic_send_IPI(int cpu, int vector)
+{
+ u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+ x2apic_wrmsr_fence();
+ __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
+}
+
static void
__x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
{
@@ -266,6 +274,7 @@ static struct apic apic_x2apic_cluster = {
.cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
+ .send_IPI = x2apic_send_IPI,
.send_IPI_mask = x2apic_send_IPI_mask,
.send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index be8e1bde07aa..78c9b12d892a 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -114,6 +114,18 @@ static atomic_t stopping_cpu = ATOMIC_INIT(-1);
static bool smp_no_nmi_ipi = false;
/*
+ * Helper wrapper: not all apic definitions support sending to
+ * a single CPU, so we fall back to sending to a mask.
+ */
+static void send_IPI_cpu(int cpu, int vector)
+{
+ if (apic->send_IPI)
+ apic->send_IPI(cpu, vector);
+ else
+ apic->send_IPI_mask(cpumask_of(cpu), vector);
+}
+
+/*
* this function sends a 'reschedule' IPI to another CPU.
* it goes straight through and wastes no time serializing
* anything. Worst case is that we lose a reschedule ...
@@ -124,12 +136,12 @@ static void native_smp_send_reschedule(int cpu)
WARN_ON(1);
return;
}
- apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
+ send_IPI_cpu(cpu, RESCHEDULE_VECTOR);
}
void native_send_call_func_single_ipi(int cpu)
{
- apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
+ send_IPI_cpu(cpu, CALL_FUNCTION_SINGLE_VECTOR);
}
void native_send_call_func_ipi(const struct cpumask *mask)
--
2.6.2.402.g2635c2b
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2015-11-04 2:14 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-11-03 10:32 [GIT PULL] x86/apic changes for v4.4 Ingo Molnar
2015-11-04 2:14 ` Linus Torvalds
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).