o grub 0.93 # grub --version || grub-install --version
o mcelog 0.6 # mcelog --version
o iptables 1.4.2 # iptables -V
-o openssl & libcrypto 1.0.1k # openssl version
+o openssl & libcrypto 1.0.0 # openssl version
Kernel compilation
interrupt.
Required Properties:
-- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc"
- as fallback
+- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc" or
+ "qca,<soctype>-cpu-intc", "qca,ar7240-misc-intc"
- reg: Base address and size of the controllers memory area
- interrupt-parent: phandle of the parent interrupt controller.
- interrupts: Interrupt specifier for the controllers interrupt.
- #interrupt-cells : Specifies the number of cells needed to encode interrupt
source, should be 1
+Compatible fallback depends on the SoC. Use ar7100 for ar71xx and ar913x,
+use ar7240 for all other SoCs.
+
Please refer to interrupts.txt in this directory for details of the common
Interrupt Controllers bindings used by client devices.
interrupt-controller;
#interrupt-cells = <1>;
};
+
+Another example:
+
+ interrupt-controller@18060010 {
+ compatible = "qca,ar9331-misc-intc", qca,ar7240-misc-intc";
+ reg = <0x18060010 0x4>;
+
+ interrupt-parent = <&cpuintc>;
+ interrupts = <6>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
(alternatively, the runtime_suspend() callback will have to check if the
device should really be suspended and return -EAGAIN if that is not the case).
-The runtime PM of PCI devices is disabled by default. It is also blocked by
-pci_pm_init() that runs the pm_runtime_forbid() helper function. If a PCI
-driver implements the runtime PM callbacks and intends to use the runtime PM
-framework provided by the PM core and the PCI subsystem, it should enable this
-feature by executing the pm_runtime_enable() helper function. However, the
-driver should not call the pm_runtime_allow() helper function unblocking
-the runtime PM of the device. Instead, it should allow user space or some
-platform-specific code to do that (user space can do it via sysfs), although
-once it has called pm_runtime_enable(), it must be prepared to handle the
+The runtime PM of PCI devices is enabled by default by the PCI core. PCI
+device drivers do not need to enable it and should not attempt to do so.
+However, it is blocked by pci_pm_init() that runs the pm_runtime_forbid()
+helper function. In addition to that, the runtime PM usage counter of
+each PCI device is incremented by local_pci_probe() before executing the
+probe callback provided by the device's driver.
+
+If a PCI driver implements the runtime PM callbacks and intends to use the
+runtime PM framework provided by the PM core and the PCI subsystem, it needs
+to decrement the device's runtime PM usage counter in its probe callback
+function. If it doesn't do that, the counter will always be different from
+zero for the device and it will never be runtime-suspended. The simplest
+way to do that is by calling pm_runtime_put_noidle(), but if the driver
+wants to schedule an autosuspend right away, for example, it may call
+pm_runtime_put_autosuspend() instead for this purpose. Generally, it
+just needs to call a function that decrements the devices usage counter
+from its probe routine to make runtime PM work for the device.
+
+It is important to remember that the driver's runtime_suspend() callback
+may be executed right after the usage counter has been decremented, because
+user space may already have cuased the pm_runtime_allow() helper function
+unblocking the runtime PM of the device to run via sysfs, so the driver must
+be prepared to cope with that.
+
+The driver itself should not call pm_runtime_allow(), though. Instead, it
+should let user space or some platform-specific code do that (user space can
+do it via sysfs as stated above), but it must be prepared to handle the
runtime PM of the device correctly as soon as pm_runtime_allow() is called
-(which may happen at any time). [It also is possible that user space causes
-pm_runtime_allow() to be called via sysfs before the driver is loaded, so in
-fact the driver has to be prepared to handle the runtime PM of the device as
-soon as it calls pm_runtime_enable().]
+(which may happen at any time, even before the driver is loaded).
+
+When the driver's remove callback runs, it has to balance the decrementation
+of the device's runtime PM usage counter at the probe time. For this reason,
+if it has decremented the counter in its probe callback, it must run
+pm_runtime_get_noresume() in its remove callback. [Since the core carries
+out a runtime resume of the device and bumps up the device's usage counter
+before running the driver's remove callback, the runtime PM of the device
+is effectively disabled for the duration of the remove execution and all
+runtime PM helper functions incrementing the device's usage counter are
+then effectively equivalent to pm_runtime_get_noresume().]
The runtime PM framework works by processing requests to suspend or resume
devices, or to check if they are idle (in which cases it is reasonable to
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
M: Joerg Roedel <joro@8bytes.org>
L: kvm@vger.kernel.org
-W: http://kvm.qumranet.com
+W: http://www.linux-kvm.org/
S: Maintained
F: arch/x86/include/asm/svm.h
F: arch/x86/kvm/svm.c
KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
M: Alexander Graf <agraf@suse.com>
L: kvm-ppc@vger.kernel.org
-W: http://kvm.qumranet.com
+W: http://www.linux-kvm.org/
T: git git://github.com/agraf/linux-2.6.git
S: Supported
F: arch/powerpc/include/asm/kvm*
return 0;
}
-IRQCHIP_DECLARE(ath79_misc_intc, "qca,ar7100-misc-intc",
- ath79_misc_intc_of_init);
+
+static int __init ar7100_misc_intc_of_init(
+ struct device_node *node, struct device_node *parent)
+{
+ ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
+ return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc",
+ ar7100_misc_intc_of_init);
+
+static int __init ar7240_misc_intc_of_init(
+ struct device_node *node, struct device_node *parent)
+{
+ ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
+ return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
+ ar7240_misc_intc_of_init);
static int __init ar79_cpu_intc_of_init(
struct device_node *node, struct device_node *parent)
#ifndef cpu_has_tlb
#define cpu_has_tlb (cpu_data[0].options & MIPS_CPU_TLB)
#endif
+#ifndef cpu_has_ftlb
+#define cpu_has_ftlb (cpu_data[0].options & MIPS_CPU_FTLB)
+#endif
#ifndef cpu_has_tlbinv
#define cpu_has_tlbinv (cpu_data[0].options & MIPS_CPU_TLBINV)
#endif
#define MIPS_CPU_CDMM 0x4000000000ull /* CPU has Common Device Memory Map */
#define MIPS_CPU_BP_GHIST 0x8000000000ull /* R12K+ Branch Prediction Global History */
#define MIPS_CPU_SP 0x10000000000ull /* Small (1KB) page support */
+#define MIPS_CPU_FTLB 0x20000000000ull /* CPU has Fixed-page-size TLB */
/*
* CPU ASE encodings
back_to_back_c0_hazard();
}
+/**
+ * maar_init() - initialise MAARs
+ *
+ * Performs initialisation of MAARs for the current CPU, making use of the
+ * platforms implementation of platform_maar_init where necessary and
+ * duplicating the setup it provides on secondary CPUs.
+ */
+extern void maar_init(void);
+
/**
* struct maar_config - MAAR configuration data
* @lower: The lowest address that the MAAR pair will affect. Must be
BUILD_CM_R_(gic_status, MIPS_CM_GCB_OFS + 0xd0)
BUILD_CM_R_(cpc_status, MIPS_CM_GCB_OFS + 0xf0)
BUILD_CM_RW(l2_config, MIPS_CM_GCB_OFS + 0x130)
+BUILD_CM_RW(sys_config2, MIPS_CM_GCB_OFS + 0x150)
/* Core Local & Core Other register accessor functions */
BUILD_CM_Cx_RW(reset_release, 0x00)
#define CM_GCR_L2_CONFIG_ASSOC_SHF 0
#define CM_GCR_L2_CONFIG_ASSOC_MSK (_ULCAST_(0xff) << 0)
+/* GCR_SYS_CONFIG2 register fields */
+#define CM_GCR_SYS_CONFIG2_MAXVPW_SHF 0
+#define CM_GCR_SYS_CONFIG2_MAXVPW_MSK (_ULCAST_(0xf) << 0)
+
/* GCR_Cx_COHERENCE register fields */
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_SHF 0
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK (_ULCAST_(0xff) << 0)
return read_gcr_rev();
}
+/**
+ * mips_cm_max_vp_width() - return the width in bits of VP indices
+ *
+ * Return: the width, in bits, of VP indices in fields that combine core & VP
+ * indices.
+ */
+static inline unsigned int mips_cm_max_vp_width(void)
+{
+ extern int smp_num_siblings;
+
+ if (mips_cm_revision() >= CM_REV_CM3)
+ return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK;
+
+ return smp_num_siblings;
+}
+
+/**
+ * mips_cm_vp_id() - calculate the hardware VP ID for a CPU
+ * @cpu: the CPU whose VP ID to calculate
+ *
+ * Hardware such as the GIC uses identifiers for VPs which may not match the
+ * CPU numbers used by Linux. This function calculates the hardware VP
+ * identifier corresponding to a given CPU.
+ *
+ * Return: the VP ID for the CPU.
+ */
+static inline unsigned int mips_cm_vp_id(unsigned int cpu)
+{
+ unsigned int core = cpu_data[cpu].core;
+ unsigned int vp = cpu_vpe_id(&cpu_data[cpu]);
+
+ return (core * mips_cm_max_vp_width()) + vp;
+}
+
#endif /* __MIPS_ASM_MIPS_CM_H__ */
/* Bits specific to the MIPS32/64 PRA. */
#define MIPS_CONF_MT (_ULCAST_(7) << 7)
+#define MIPS_CONF_MT_TLB (_ULCAST_(1) << 7)
+#define MIPS_CONF_MT_FTLB (_ULCAST_(4) << 7)
#define MIPS_CONF_AR (_ULCAST_(7) << 10)
#define MIPS_CONF_AT (_ULCAST_(3) << 13)
#define MIPS_CONF_M (_ULCAST_(1) << 31)
static inline unsigned int decode_config0(struct cpuinfo_mips *c)
{
unsigned int config0;
- int isa;
+ int isa, mt;
config0 = read_c0_config();
/*
* Look for Standard TLB or Dual VTLB and FTLB
*/
- if ((((config0 & MIPS_CONF_MT) >> 7) == 1) ||
- (((config0 & MIPS_CONF_MT) >> 7) == 4))
+ mt = config0 & MIPS_CONF_MT;
+ if (mt == MIPS_CONF_MT_TLB)
c->options |= MIPS_CPU_TLB;
+ else if (mt == MIPS_CONF_MT_FTLB)
+ c->options |= MIPS_CPU_TLB | MIPS_CPU_FTLB;
isa = (config0 & MIPS_CONF_AT) >> 13;
switch (isa) {
if (cpu_has_tlb) {
if (((config4 & MIPS_CONF4_IE) >> 29) == 2)
c->options |= MIPS_CPU_TLBINV;
+
/*
- * This is a bit ugly. R6 has dropped that field from
- * config4 and the only valid configuration is VTLB+FTLB so
- * set a good value for mmuextdef for that case.
+ * R6 has dropped the MMUExtDef field from config4.
+ * On R6 the fields always describe the FTLB, and only if it is
+ * present according to Config.MT.
*/
- if (cpu_has_mips_r6)
+ if (!cpu_has_mips_r6)
+ mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+ else if (cpu_has_ftlb)
mmuextdef = MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT;
else
- mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+ mmuextdef = 0;
switch (mmuextdef) {
case MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT:
if (end <= reserved_end)
continue;
#ifdef CONFIG_BLK_DEV_INITRD
- /* mapstart should be after initrd_end */
+ /* Skip zones before initrd and initrd itself */
if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
continue;
#endif
max_low_pfn = PFN_DOWN(HIGHMEM_START);
}
+#ifdef CONFIG_BLK_DEV_INITRD
+ /*
+ * mapstart should be after initrd_end
+ */
+ if (initrd_end)
+ mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
+#endif
+
/*
* Initialize the boot-time allocator with low memory only.
*/
#include <asm/mmu_context.h>
#include <asm/time.h>
#include <asm/setup.h>
+#include <asm/maar.h>
cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
mips_clockevent_init();
mp_ops->init_secondary();
cpu_report();
+ maar_init();
/*
* XXX parity protection should be folded in here when it's converted
}
if (memsize == 0)
memsize = 256;
+
+ loongson_sysconf.nr_uarts = 1;
+
pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
#else
struct boot_params *boot_p;
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>
+#include <asm/maar.h>
/*
* We have up to 8 empty zeroed pages so we can map one of the right colour
#endif
}
+unsigned __weak platform_maar_init(unsigned num_pairs)
+{
+ struct maar_config cfg[BOOT_MEM_MAP_MAX];
+ unsigned i, num_configured, num_cfg = 0;
+ phys_addr_t skip;
+
+ for (i = 0; i < boot_mem_map.nr_map; i++) {
+ switch (boot_mem_map.map[i].type) {
+ case BOOT_MEM_RAM:
+ case BOOT_MEM_INIT_RAM:
+ break;
+ default:
+ continue;
+ }
+
+ skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
+
+ cfg[num_cfg].lower = boot_mem_map.map[i].addr;
+ cfg[num_cfg].lower += skip;
+
+ cfg[num_cfg].upper = cfg[num_cfg].lower;
+ cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
+ cfg[num_cfg].upper -= skip;
+
+ cfg[num_cfg].attrs = MIPS_MAAR_S;
+ num_cfg++;
+ }
+
+ num_configured = maar_config(cfg, num_cfg, num_pairs);
+ if (num_configured < num_cfg)
+ pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
+ num_pairs, num_cfg);
+
+ return num_configured;
+}
+
+void maar_init(void)
+{
+ unsigned num_maars, used, i;
+ phys_addr_t lower, upper, attr;
+ static struct {
+ struct maar_config cfgs[3];
+ unsigned used;
+ } recorded = { { { 0 } }, 0 };
+
+ if (!cpu_has_maar)
+ return;
+
+ /* Detect the number of MAARs */
+ write_c0_maari(~0);
+ back_to_back_c0_hazard();
+ num_maars = read_c0_maari() + 1;
+
+ /* MAARs should be in pairs */
+ WARN_ON(num_maars % 2);
+
+ /* Set MAARs using values we recorded already */
+ if (recorded.used) {
+ used = maar_config(recorded.cfgs, recorded.used, num_maars / 2);
+ BUG_ON(used != recorded.used);
+ } else {
+ /* Configure the required MAARs */
+ used = platform_maar_init(num_maars / 2);
+ }
+
+ /* Disable any further MAARs */
+ for (i = (used * 2); i < num_maars; i++) {
+ write_c0_maari(i);
+ back_to_back_c0_hazard();
+ write_c0_maar(0);
+ back_to_back_c0_hazard();
+ }
+
+ if (recorded.used)
+ return;
+
+ pr_info("MAAR configuration:\n");
+ for (i = 0; i < num_maars; i += 2) {
+ write_c0_maari(i);
+ back_to_back_c0_hazard();
+ upper = read_c0_maar();
+
+ write_c0_maari(i + 1);
+ back_to_back_c0_hazard();
+ lower = read_c0_maar();
+
+ attr = lower & upper;
+ lower = (lower & MIPS_MAAR_ADDR) << 4;
+ upper = ((upper & MIPS_MAAR_ADDR) << 4) | 0xffff;
+
+ pr_info(" [%d]: ", i / 2);
+ if (!(attr & MIPS_MAAR_V)) {
+ pr_cont("disabled\n");
+ continue;
+ }
+
+ pr_cont("%pa-%pa", &lower, &upper);
+
+ if (attr & MIPS_MAAR_S)
+ pr_cont(" speculate");
+
+ pr_cont("\n");
+
+ /* Record the setup for use on secondary CPUs */
+ if (used <= ARRAY_SIZE(recorded.cfgs)) {
+ recorded.cfgs[recorded.used].lower = lower;
+ recorded.cfgs[recorded.used].upper = upper;
+ recorded.cfgs[recorded.used].attrs = attr;
+ recorded.used++;
+ }
+ }
+}
+
#ifndef CONFIG_NEED_MULTIPLE_NODES
int page_is_ram(unsigned long pagenr)
{
#endif
}
-unsigned __weak platform_maar_init(unsigned num_pairs)
-{
- struct maar_config cfg[BOOT_MEM_MAP_MAX];
- unsigned i, num_configured, num_cfg = 0;
- phys_addr_t skip;
-
- for (i = 0; i < boot_mem_map.nr_map; i++) {
- switch (boot_mem_map.map[i].type) {
- case BOOT_MEM_RAM:
- case BOOT_MEM_INIT_RAM:
- break;
- default:
- continue;
- }
-
- skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
- cfg[num_cfg].lower = boot_mem_map.map[i].addr;
- cfg[num_cfg].lower += skip;
-
- cfg[num_cfg].upper = cfg[num_cfg].lower;
- cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
- cfg[num_cfg].upper -= skip;
-
- cfg[num_cfg].attrs = MIPS_MAAR_S;
- num_cfg++;
- }
-
- num_configured = maar_config(cfg, num_cfg, num_pairs);
- if (num_configured < num_cfg)
- pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
- num_pairs, num_cfg);
-
- return num_configured;
-}
-
-static void maar_init(void)
-{
- unsigned num_maars, used, i;
-
- if (!cpu_has_maar)
- return;
-
- /* Detect the number of MAARs */
- write_c0_maari(~0);
- back_to_back_c0_hazard();
- num_maars = read_c0_maari() + 1;
-
- /* MAARs should be in pairs */
- WARN_ON(num_maars % 2);
-
- /* Configure the required MAARs */
- used = platform_maar_init(num_maars / 2);
-
- /* Disable any further MAARs */
- for (i = (used * 2); i < num_maars; i++) {
- write_c0_maari(i);
- back_to_back_c0_hazard();
- write_c0_maar(0);
- back_to_back_c0_hazard();
- }
-}
-
void __init mem_init(void)
{
#ifdef CONFIG_HIGHMEM
PTR_ADDU t1, $r_skb_data, offset
lw $r_A, 0(t1)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_A
rotr $r_A, t0, 16
+# else
+ sll t0, $r_A, 24
+ srl t1, $r_A, 24
+ srl t2, $r_A, 8
+ or t0, t0, t1
+ andi t2, t2, 0xff00
+ andi t1, $r_A, 0xff00
+ or t0, t0, t2
+ sll t1, t1, 8
+ or $r_A, t0, t1
+# endif
#endif
jr $r_ra
move $r_ret, zero
PTR_ADDU t1, $r_skb_data, offset
lh $r_A, 0(t1)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_A
seh $r_A, t0
+# else
+ sll t0, $r_A, 24
+ andi t1, $r_A, 0xff00
+ sra t0, t0, 16
+ srl t1, t1, 8
+ or $r_A, t0, t1
+# endif
#endif
jr $r_ra
move $r_ret, zero
NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
bpf_slow_path_common(4)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_s0
jr $r_ra
rotr $r_A, t0, 16
-#endif
+# else
+ sll t0, $r_s0, 24
+ srl t1, $r_s0, 24
+ srl t2, $r_s0, 8
+ or t0, t0, t1
+ andi t2, t2, 0xff00
+ andi t1, $r_s0, 0xff00
+ or t0, t0, t2
+ sll t1, t1, 8
+ jr $r_ra
+ or $r_A, t0, t1
+# endif
+#else
jr $r_ra
- move $r_A, $r_s0
+ move $r_A, $r_s0
+#endif
END(bpf_slow_path_word)
NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
bpf_slow_path_common(2)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
jr $r_ra
wsbh $r_A, $r_s0
-#endif
+# else
+ sll t0, $r_s0, 8
+ andi t1, $r_s0, 0xff00
+ andi t0, t0, 0xff00
+ srl t1, t1, 8
+ jr $r_ra
+ or $r_A, t0, t1
+# endif
+#else
jr $r_ra
move $r_A, $r_s0
+#endif
END(bpf_slow_path_half)
#include <linux/platform_device.h>
#include <linux/usb/tilegx.h>
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/types.h>
static u64 ehci_dmamask = DMA_BIT_MASK(32);
extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
u32 type, u64 attribute);
+#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
* only in kernel binary. Since the EFI stub linked into a separate binary it
#undef memcpy
#undef memset
#undef memmove
+#endif
#endif /* CONFIG_X86_32 */
#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
+#define MSR_PEBS_FRONTEND 0x000003f7
+
#define MSR_IA32_POWER_CTL 0x000001fc
#define MSR_IA32_MC0_CTL 0x00000400
#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
#define PVCLOCK_GUEST_STOPPED (1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */
+ EXTRA_REG_FE = 4, /* fe_* */
EXTRA_REG_MAX /* number of entries needed */
};
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ /*
+ * Note the low 8 bits eventsel code is not a continuous field, containing
+ * some #GPing bits. These are masked out.
+ */
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
EVENT_EXTRA_END
};
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
- INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */
+ INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
EVENT_CONSTRAINT_END
};
PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
static struct attribute *intel_arch3_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
NULL,
};
+static struct attribute *skl_format_attr[] = {
+ &format_attr_frontend.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+ skl_format_attr);
WARN_ON(!x86_pmu.format_attrs);
x86_pmu.cpu_events = hsw_events_attrs;
pr_cont("Skylake events, ");
PERF_MSR_EVENT_MAX,
};
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
-bool test_intel(int idx)
+static bool test_intel(int idx)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->vmcb->control.next_rip != 0) {
- WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+ WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
svm->next_rip = svm->vmcb->control.next_rip;
}
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
-#define MTRR_TYPE_UC_MINUS 7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
- /*
- * WT and WP aren't always available in the host PAT. Treat
- * them as UC and UC- respectively. Everything else should be
- * there.
- */
- switch (mtrr)
- {
- case MTRR_TYPE_WRTHROUGH:
- return MTRR_TYPE_UNCACHABLE;
- case MTRR_TYPE_WRPROT:
- return MTRR_TYPE_UC_MINUS;
- default:
- BUG();
- }
-}
-
-static void build_mtrr2protval(void)
-{
- int i;
- u64 pat;
-
- for (i = 0; i < 8; i++)
- mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
- /* Ignore the invalid MTRR types. */
- mtrr2protval[2] = 0;
- mtrr2protval[3] = 0;
-
- /*
- * Use host PAT value to figure out the mapping from guest MTRR
- * values to nested page table PAT/PCD/PWT values. We do not
- * want to change the host PAT value every time we enter the
- * guest.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- for (i = 0; i < 8; i++) {
- u8 mtrr = pat >> (8 * i);
-
- if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
- mtrr2protval[mtrr] = __cm_idx2pte(i);
- }
-
- for (i = 0; i < 8; i++) {
- if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
- u8 fallback = fallback_mtrr_type(i);
- mtrr2protval[i] = mtrr2protval[fallback];
- BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
- }
- }
-}
-
static __init int svm_hardware_setup(void)
{
int cpu;
} else
kvm_disable_tdp();
- build_mtrr2protval();
return 0;
err:
return target_tsc - tsc;
}
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
- struct kvm_vcpu *vcpu = &svm->vcpu;
-
- /* Unlike Intel, AMD takes the guest's CR0.CD into account.
- *
- * AMD does not have IPAT. To emulate it for the case of guests
- * with no assigned devices, just set everything to WB. If guests
- * have assigned devices, however, we cannot force WB for RAM
- * pages only, so use the guest PAT directly.
- */
- if (!kvm_arch_has_assigned_device(vcpu->kvm))
- *g_pat = 0x0606060606060606;
- else
- *g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
- u8 mtrr;
-
- /*
- * 1. MMIO: trust guest MTRR, so same as item 3.
- * 2. No passthrough: always map as WB, and force guest PAT to WB as well
- * 3. Passthrough: can't guarantee the result, try to trust guest.
- */
- if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
- return 0;
-
- if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
- kvm_read_cr0(vcpu) & X86_CR0_CD)
- return _PAGE_NOCACHE;
-
- mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
- return mtrr2protval[mtrr];
-}
-
static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
save->g_pat = svm->vcpu.arch.pat;
- svm_set_guest_pat(svm, &save->g_pat);
save->cr3 = 0;
save->cr4 = 0;
}
if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
-
- /* These are emulated via page tables. */
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+ /*
+ * re-enable caching here because the QEMU bios
+ * does not do it - this results in some delay at
+ * reboot
+ */
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
case MSR_VM_IGNNE:
vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
- case MSR_IA32_CR_PAT:
- if (npt_enabled) {
- if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
- return 1;
- vcpu->arch.pat = data;
- svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
- mark_dirty(svm->vmcb, VMCB_NPT);
- break;
- }
- /* fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
return true;
}
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+ return 0;
+}
+
static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
}
u64 ipat = 0;
/* For VT-d and EPT combination
- * 1. MMIO: guest may want to apply WC, trust it.
+ * 1. MMIO: always map as UC
* 2. EPT with VT-d:
* a. VT-d without snooping control feature: can't guarantee the
- * result, try to trust guest. So the same as item 1.
+ * result, try to trust guest.
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
- if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ if (is_mmio) {
+ cache = MTRR_TYPE_UNCACHABLE;
+ goto exit;
+ }
+
+ if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
ipat = VMX_EPT_IPAT_BIT;
cache = MTRR_TYPE_WRBACK;
goto exit;
vcpu->pvclock_set_guest_stopped_request = false;
}
- pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
/* If the host uses TSC clocksource, then it is stable */
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
&vcpu->requests);
ka->boot_vcpu_runs_old_kvmclock = tmp;
-
- ka->kvmclock_offset = -get_kernel_ns();
}
vcpu->arch.time = data;
return cpu;
}
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
+int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
+ const struct cpumask *online_mask)
{
unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
cpumask_var_t cpus;
cpumask_clear(cpus);
nr_cpus = nr_uniq_cpus = 0;
- for_each_online_cpu(i) {
+ for_each_cpu(i, online_mask) {
nr_cpus++;
first_sibling = get_first_sibling(i);
if (!cpumask_test_cpu(first_sibling, cpus))
queue = 0;
for_each_possible_cpu(i) {
- if (!cpu_online(i)) {
+ if (!cpumask_test_cpu(i, online_mask)) {
map[i] = 0;
continue;
}
if (!map)
return NULL;
- if (!blk_mq_update_queue_map(map, set->nr_hw_queues))
+ if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
return map;
kfree(map);
unsigned int i, first = 1;
ssize_t ret = 0;
- blk_mq_disable_hotplug();
-
for_each_cpu(i, hctx->cpumask) {
if (first)
ret += sprintf(ret + page, "%u", i);
first = 0;
}
- blk_mq_enable_hotplug();
-
ret += sprintf(ret + page, "\n");
return ret;
}
struct blk_mq_ctx *ctx;
int i;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+ if (!hctx->nr_ctx)
return;
hctx_for_each_ctx(hctx, ctx, i)
struct blk_mq_ctx *ctx;
int i, ret;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+ if (!hctx->nr_ctx)
return 0;
ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
struct blk_mq_ctx *ctx;
int i, j;
+ blk_mq_disable_hotplug();
+
queue_for_each_hw_ctx(q, hctx, i) {
blk_mq_unregister_hctx(hctx);
kobject_put(&q->mq_kobj);
kobject_put(&disk_to_dev(disk)->kobj);
+
+ q->mq_sysfs_init_done = false;
+ blk_mq_enable_hotplug();
}
static void blk_mq_sysfs_init(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
int ret, i;
+ blk_mq_disable_hotplug();
+
blk_mq_sysfs_init(q);
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
- return ret;
+ goto out;
kobject_uevent(&q->mq_kobj, KOBJ_ADD);
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->flags |= BLK_MQ_F_SYSFS_UP;
ret = blk_mq_register_hctx(hctx);
if (ret)
break;
}
- if (ret) {
+ if (ret)
blk_mq_unregister_disk(disk);
- return ret;
- }
+ else
+ q->mq_sysfs_init_done = true;
+out:
+ blk_mq_enable_hotplug();
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(blk_mq_register_disk);
struct blk_mq_hw_ctx *hctx;
int i;
+ if (!q->mq_sysfs_init_done)
+ return;
+
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
}
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
+ if (!q->mq_sysfs_init_done)
+ return ret;
+
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
if (ret)
}
EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
-void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
void *priv)
{
- struct blk_mq_tags *tags = hctx->tags;
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ struct blk_mq_tags *tags = hctx->tags;
+
+ /*
+ * If not software queues are currently mapped to this
+ * hardware queue, there's nothing to check
+ */
+ if (!blk_mq_hw_queue_mapped(hctx))
+ continue;
+
+ if (tags->nr_reserved_tags)
+ bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
+ bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+ false);
+ }
- if (tags->nr_reserved_tags)
- bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
- bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
- false);
}
-EXPORT_SYMBOL(blk_mq_tag_busy_iter);
static unsigned int bt_unused_tags(struct blk_mq_bitmap_tags *bt)
{
extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+ void *priv);
enum {
BLK_MQ_TAG_CACHE_MIN = 1,
* Ends all I/O on a request. It does not handle partial completions.
* The actual completion happens out-of-order, through a IPI handler.
**/
-void blk_mq_complete_request(struct request *rq)
+void blk_mq_complete_request(struct request *rq, int error)
{
struct request_queue *q = rq->q;
if (unlikely(blk_should_fake_timeout(q)))
return;
- if (!blk_mark_rq_complete(rq))
+ if (!blk_mark_rq_complete(rq)) {
+ rq->errors = error;
__blk_mq_complete_request(rq);
+ }
}
EXPORT_SYMBOL(blk_mq_complete_request);
* If a request wasn't started before the queue was
* marked dying, kill it here or it'll go unnoticed.
*/
- if (unlikely(blk_queue_dying(rq->q))) {
- rq->errors = -EIO;
- blk_mq_complete_request(rq);
- }
+ if (unlikely(blk_queue_dying(rq->q)))
+ blk_mq_complete_request(rq, -EIO);
return;
}
if (rq->cmd_flags & REQ_NO_TIMEOUT)
.next = 0,
.next_set = 0,
};
- struct blk_mq_hw_ctx *hctx;
int i;
- queue_for_each_hw_ctx(q, hctx, i) {
- /*
- * If not software queues are currently mapped to this
- * hardware queue, there's nothing to check
- */
- if (!blk_mq_hw_queue_mapped(hctx))
- continue;
-
- blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
- }
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
if (data.next_set) {
data.next = blk_rq_timeout(round_jiffies_up(data.next));
mod_timer(&q->timeout, data.next);
} else {
+ struct blk_mq_hw_ctx *hctx;
+
queue_for_each_hw_ctx(q, hctx, i) {
/* the hctx may be unmapped, so check it here */
if (blk_mq_hw_queue_mapped(hctx))
}
}
-static void blk_mq_map_swqueue(struct request_queue *q)
+static void blk_mq_map_swqueue(struct request_queue *q,
+ const struct cpumask *online_mask)
{
unsigned int i;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
+ /*
+ * Avoid others reading imcomplete hctx->cpumask through sysfs
+ */
+ mutex_lock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
*/
queue_for_each_ctx(q, ctx, i) {
/* If the cpu isn't online, the cpu is mapped to first hctx */
- if (!cpu_online(i))
+ if (!cpumask_test_cpu(i, online_mask))
continue;
hctx = q->mq_ops->map_queue(q, i);
cpumask_set_cpu(i, hctx->cpumask);
- cpumask_set_cpu(i, hctx->tags->cpumask);
ctx->index_hw = hctx->nr_ctx;
hctx->ctxs[hctx->nr_ctx++] = ctx;
}
+ mutex_unlock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
struct blk_mq_ctxmap *map = &hctx->ctx_map;
hctx->next_cpu = cpumask_first(hctx->cpumask);
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
}
+
+ queue_for_each_ctx(q, ctx, i) {
+ if (!cpumask_test_cpu(i, online_mask))
+ continue;
+
+ hctx = q->mq_ops->map_queue(q, i);
+ cpumask_set_cpu(i, hctx->tags->cpumask);
+ }
}
static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
kfree(hctx);
}
+ kfree(q->mq_map);
+ q->mq_map = NULL;
+
kfree(q->queue_hw_ctx);
/* ctx kobj stays in queue_ctx */
if (blk_mq_init_hw_queues(q, set))
goto err_hctxs;
+ get_online_cpus();
mutex_lock(&all_q_mutex);
- list_add_tail(&q->all_q_node, &all_q_list);
- mutex_unlock(&all_q_mutex);
+ list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
+ blk_mq_map_swqueue(q, cpu_online_mask);
- blk_mq_map_swqueue(q);
+ mutex_unlock(&all_q_mutex);
+ put_online_cpus();
return q;
{
struct blk_mq_tag_set *set = q->tag_set;
+ mutex_lock(&all_q_mutex);
+ list_del_init(&q->all_q_node);
+ mutex_unlock(&all_q_mutex);
+
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
blk_mq_free_hw_queues(q, set);
percpu_ref_exit(&q->mq_usage_counter);
-
- kfree(q->mq_map);
-
- q->mq_map = NULL;
-
- mutex_lock(&all_q_mutex);
- list_del_init(&q->all_q_node);
- mutex_unlock(&all_q_mutex);
}
/* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q)
+static void blk_mq_queue_reinit(struct request_queue *q,
+ const struct cpumask *online_mask)
{
WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
blk_mq_sysfs_unregister(q);
- blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues);
+ blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask);
/*
* redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
* involves free and re-allocate memory, worthy doing?)
*/
- blk_mq_map_swqueue(q);
+ blk_mq_map_swqueue(q, online_mask);
blk_mq_sysfs_register(q);
}
unsigned long action, void *hcpu)
{
struct request_queue *q;
+ int cpu = (unsigned long)hcpu;
+ /*
+ * New online cpumask which is going to be set in this hotplug event.
+ * Declare this cpumasks as global as cpu-hotplug operation is invoked
+ * one-by-one and dynamically allocating this could result in a failure.
+ */
+ static struct cpumask online_new;
/*
- * Before new mappings are established, hotadded cpu might already
- * start handling requests. This doesn't break anything as we map
- * offline CPUs to first hardware queue. We will re-init the queue
- * below to get optimal settings.
+ * Before hotadded cpu starts handling requests, new mappings must
+ * be established. Otherwise, these requests in hw queue might
+ * never be dispatched.
+ *
+ * For example, there is a single hw queue (hctx) and two CPU queues
+ * (ctx0 for CPU0, and ctx1 for CPU1).
+ *
+ * Now CPU1 is just onlined and a request is inserted into
+ * ctx1->rq_list and set bit0 in pending bitmap as ctx1->index_hw is
+ * still zero.
+ *
+ * And then while running hw queue, flush_busy_ctxs() finds bit0 is
+ * set in pending bitmap and tries to retrieve requests in
+ * hctx->ctxs[0]->rq_list. But htx->ctxs[0] is a pointer to ctx0,
+ * so the request in ctx1->rq_list is ignored.
*/
- if (action != CPU_DEAD && action != CPU_DEAD_FROZEN &&
- action != CPU_ONLINE && action != CPU_ONLINE_FROZEN)
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ cpumask_copy(&online_new, cpu_online_mask);
+ break;
+ case CPU_UP_PREPARE:
+ cpumask_copy(&online_new, cpu_online_mask);
+ cpumask_set_cpu(cpu, &online_new);
+ break;
+ default:
return NOTIFY_OK;
+ }
mutex_lock(&all_q_mutex);
}
list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_queue_reinit(q);
+ blk_mq_queue_reinit(q, &online_new);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_unfreeze_queue(q);
* CPU -> queue mappings
*/
extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
-extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues);
+extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
+ const struct cpumask *online_mask);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
/*
srlen = cert->raw_serial_size;
q = cert->raw_serial;
}
- if (srlen > 1 && *q == 0) {
- srlen--;
- q++;
- }
ret = -ENOMEM;
desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL);
goto err_exit;
mutex_lock(&ec->mutex);
+ result = -ENODATA;
list_for_each_entry(handler, &ec->list, node) {
if (value == handler->query_bit) {
+ result = 0;
q->handler = acpi_ec_get_query_handler(handler);
ec_dbg_evt("Query(0x%02x) scheduled",
q->handler->query_bit);
/* Interrupt Line values above 0xF are forbidden */
if (dev->irq > 0 && (dev->irq <= 0xF) &&
+ acpi_isa_irq_available(dev->irq) &&
(acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) {
dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n",
pin_name(dev->pin), dev->irq);
PIRQ_PENALTY_PCI_POSSIBLE;
}
}
- /* Add a penalty for the SCI */
- acpi_irq_penalty[acpi_gbl_FADT.sci_interrupt] += PIRQ_PENALTY_PCI_USING;
+
return 0;
}
irq = link->irq.possible[i];
}
}
+ if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) {
+ printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. "
+ "Try pci=noacpi or acpi=off\n",
+ acpi_device_name(link->device),
+ acpi_device_bid(link->device));
+ return -ENODEV;
+ }
/* Attempt to enable the link device at this IRQ. */
if (acpi_pci_link_set(link, irq)) {
}
}
+bool acpi_isa_irq_available(int irq)
+{
+ return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) ||
+ acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS);
+}
+
/*
* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with
* PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for
u32 microvolt[3] = {0};
int count, ret;
- count = of_property_count_u32_elems(opp->np, "opp-microvolt");
- if (!count)
+ /* Missing property isn't a problem, but an invalid entry is */
+ if (!of_find_property(opp->np, "opp-microvolt", NULL))
return 0;
+ count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+ if (count < 0) {
+ dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n",
+ __func__, count);
+ return count;
+ }
+
/* There can be one or three elements here */
if (count != 1 && count != 3) {
dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
* share a common logic which is isolated here.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*
* Locking: The internal device_opp and opp structures are RCU protected.
* mutex locking or synchronize_rcu() blocking calls cannot be used.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*/
int dev_pm_opp_enable(struct device *dev, unsigned long freq)
* mutex locking or synchronize_rcu() blocking calls cannot be used.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*/
int dev_pm_opp_disable(struct device *dev, unsigned long freq)
{
const bool write = cmd->rq->cmd_flags & REQ_WRITE;
struct loop_device *lo = cmd->rq->q->queuedata;
- int ret = -EIO;
+ int ret = 0;
- if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+ if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
+ ret = -EIO;
goto failed;
+ }
ret = do_req_filebacked(lo, cmd->rq);
-
failed:
- if (ret)
- cmd->rq->errors = -EIO;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
}
static void loop_queue_write_work(struct work_struct *work)
case NULL_IRQ_SOFTIRQ:
switch (queue_mode) {
case NULL_Q_MQ:
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(cmd->rq, cmd->rq->errors);
break;
case NULL_Q_RQ:
blk_complete_request(cmd->rq);
spin_unlock_irqrestore(req->q->queue_lock, flags);
return;
}
+
if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
if (cmd_rq->ctx == CMD_CTX_CANCELLED)
- req->errors = -EINTR;
- else
- req->errors = status;
+ status = -EINTR;
} else {
- req->errors = nvme_error_status(status);
+ status = nvme_error_status(status);
}
- } else
- req->errors = 0;
+ }
+
if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
u32 result = le32_to_cpup(&cqe->result);
req->special = (void *)(uintptr_t)result;
}
nvme_free_iod(nvmeq->dev, iod);
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, status);
}
/* length is in bytes. gfp flags indicates whether we may sleep. */
if (ns && ns->ms && !blk_integrity_rq(req)) {
if (!(ns->pi_type && ns->ms == 8) &&
req->cmd_type != REQ_TYPE_DRV_PRIV) {
- req->errors = -EFAULT;
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, -EFAULT);
return BLK_MQ_RQ_QUEUE_OK;
}
}
list_sort(NULL, &dev->namespaces, ns_cmp);
}
+static void nvme_set_irq_hints(struct nvme_dev *dev)
+{
+ struct nvme_queue *nvmeq;
+ int i;
+
+ for (i = 0; i < dev->online_queues; i++) {
+ nvmeq = dev->queues[i];
+
+ if (!nvmeq->tags || !(*nvmeq->tags))
+ continue;
+
+ irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+ blk_mq_tags_cpumask(*nvmeq->tags));
+ }
+}
+
static void nvme_dev_scan(struct work_struct *work)
{
struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work);
return;
nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
kfree(ctrl);
+ nvme_set_irq_hints(dev);
}
/*
.compat_ioctl = nvme_dev_ioctl,
};
-static void nvme_set_irq_hints(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq->tags));
- }
-}
-
static int nvme_dev_start(struct nvme_dev *dev)
{
int result;
if (result)
goto free_tags;
- nvme_set_irq_hints(dev);
-
dev->event_limit = 1;
return result;
} else {
nvme_unfreeze_queues(dev);
nvme_dev_add(dev);
- nvme_set_irq_hints(dev);
}
return 0;
}
do {
virtqueue_disable_cb(vq);
while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
- blk_mq_complete_request(vbr->req);
+ blk_mq_complete_request(vbr->req, vbr->req->errors);
req_done = true;
}
if (unlikely(virtqueue_is_broken(vq)))
static int xen_blkif_disconnect(struct xen_blkif *blkif)
{
+ struct pending_req *req, *n;
+ int i = 0, j;
+
if (blkif->xenblkd) {
kthread_stop(blkif->xenblkd);
wake_up(&blkif->shutdown_wq);
/* Remove all persistent grants and the cache of ballooned pages. */
xen_blkbk_free_caches(blkif);
+ /* Check that there is no request in use */
+ list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
+ list_del(&req->free_list);
+
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
+ kfree(req->segments[j]);
+
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++)
+ kfree(req->indirect_pages[j]);
+
+ kfree(req);
+ i++;
+ }
+
+ WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
+ blkif->nr_ring_pages = 0;
+
return 0;
}
static void xen_blkif_free(struct xen_blkif *blkif)
{
- struct pending_req *req, *n;
- int i = 0, j;
xen_blkif_disconnect(blkif);
xen_vbd_free(&blkif->vbd);
BUG_ON(!list_empty(&blkif->free_pages));
BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
- /* Check that there is no request in use */
- list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
- list_del(&req->free_list);
-
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
- kfree(req->segments[j]);
-
- for (j = 0; j < MAX_INDIRECT_PAGES; j++)
- kfree(req->indirect_pages[j]);
-
- kfree(req);
- i++;
- }
-
- WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
-
kmem_cache_free(xen_blkif_cachep, blkif);
}
RING_IDX i, rp;
unsigned long flags;
struct blkfront_info *info = (struct blkfront_info *)dev_id;
+ int error;
spin_lock_irqsave(&info->io_lock, flags);
continue;
}
- req->errors = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+ error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
case BLKIF_OP_DISCARD:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
}
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, error);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
info->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
}
- if (unlikely(req->errors)) {
- if (req->errors == -EOPNOTSUPP)
- req->errors = 0;
+ if (unlikely(error)) {
+ if (error == -EOPNOTSUPP)
+ error = 0;
info->feature_flush = 0;
xlvbd_flush(info);
}
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, error);
break;
default:
BUG();
return desc;
}
+void at_xdmac_init_used_desc(struct at_xdmac_desc *desc)
+{
+ memset(&desc->lld, 0, sizeof(desc->lld));
+ INIT_LIST_HEAD(&desc->descs_list);
+ desc->direction = DMA_TRANS_NONE;
+ desc->xfer_size = 0;
+ desc->active_xfer = false;
+}
+
/* Call must be protected by lock. */
static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
{
desc = list_first_entry(&atchan->free_descs_list,
struct at_xdmac_desc, desc_node);
list_del(&desc->desc_node);
- desc->active_xfer = false;
+ at_xdmac_init_used_desc(desc);
}
return desc;
if (xt->src_inc) {
if (xt->src_sgl)
- chan_cc |= AT_XDMAC_CC_SAM_UBS_DS_AM;
+ chan_cc |= AT_XDMAC_CC_SAM_UBS_AM;
else
chan_cc |= AT_XDMAC_CC_SAM_INCREMENTED_AM;
}
if (xt->dst_inc) {
if (xt->dst_sgl)
- chan_cc |= AT_XDMAC_CC_DAM_UBS_DS_AM;
+ chan_cc |= AT_XDMAC_CC_DAM_UBS_AM;
else
chan_cc |= AT_XDMAC_CC_DAM_INCREMENTED_AM;
}
mutex_lock(&dma_list_mutex);
if (chan->client_count == 0) {
+ struct dma_device *device = chan->device;
+
+ dma_cap_set(DMA_PRIVATE, device->cap_mask);
+ device->privatecnt++;
err = dma_chan_get(chan);
- if (err)
+ if (err) {
pr_debug("%s: failed to get %s: (%d)\n",
__func__, dma_chan_name(chan), err);
+ chan = NULL;
+ if (--device->privatecnt == 0)
+ dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+ }
} else
chan = NULL;
INIT_LIST_HEAD(&dw->dma.channels);
for (i = 0; i < nr_channels; i++) {
struct dw_dma_chan *dwc = &dw->chan[i];
- int r = nr_channels - i - 1;
dwc->chan.device = &dw->dma;
dma_cookie_init(&dwc->chan);
/* 7 is highest priority & 0 is lowest. */
if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
- dwc->priority = r;
+ dwc->priority = nr_channels - i - 1;
else
dwc->priority = i;
/* Hardware configuration */
if (autocfg) {
unsigned int dwc_params;
+ unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
void __iomem *addr = chip->regs + r * sizeof(u32);
dwc_params = dma_read_byaddr(addr, DWC_PARAMS);
struct idma64_desc *desc = idma64c->desc;
struct idma64_hw_desc *hw;
size_t bytes = desc->length;
- u64 llp;
- u32 ctlhi;
+ u64 llp = channel_readq(idma64c, LLP);
+ u32 ctlhi = channel_readl(idma64c, CTL_HI);
unsigned int i = 0;
- llp = channel_readq(idma64c, LLP);
do {
hw = &desc->hw[i];
- } while ((hw->llp != llp) && (++i < desc->ndesc));
+ if (hw->llp == llp)
+ break;
+ bytes -= hw->len;
+ } while (++i < desc->ndesc);
if (!i)
return bytes;
- do {
- bytes -= desc->hw[--i].len;
- } while (i);
+ /* The current chunk is not fully transfered yet */
+ bytes += desc->hw[--i].len;
- ctlhi = channel_readl(idma64c, CTL_HI);
return bytes - IDMA64C_CTLH_BLOCK_TS(ctlhi);
}
return;
/* clear the channel mapping in DRCMR */
- reg = pxad_drcmr(chan->drcmr);
- writel_relaxed(0, chan->phy->base + reg);
+ if (chan->drcmr <= DRCMR_CHLNUM) {
+ reg = pxad_drcmr(chan->drcmr);
+ writel_relaxed(0, chan->phy->base + reg);
+ }
spin_lock_irqsave(&pdev->phy_lock, flags);
for (i = 0; i < 32; i++)
"%s(); phy=%p(%d) misaligned=%d\n", __func__,
phy, phy->idx, misaligned);
- reg = pxad_drcmr(phy->vchan->drcmr);
- writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+ if (phy->vchan->drcmr <= DRCMR_CHLNUM) {
+ reg = pxad_drcmr(phy->vchan->drcmr);
+ writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+ }
dalgn = phy_readl_relaxed(phy, DALGN);
if (misaligned)
struct dma_async_tx_descriptor *tx;
struct pxad_chan *chan = container_of(vc, struct pxad_chan, vc);
+ INIT_LIST_HEAD(&vd->node);
tx = vchan_tx_prep(vc, vd, tx_flags);
tx->tx_submit = pxad_tx_submit;
dev_dbg(&chan->vc.chan.dev->device,
width = chan->cfg.src_addr_width;
dev_addr = chan->cfg.src_addr;
*dev_src = dev_addr;
- *dcmd |= PXA_DCMD_INCTRGADDR | PXA_DCMD_FLOWSRC;
+ *dcmd |= PXA_DCMD_INCTRGADDR;
+ if (chan->drcmr <= DRCMR_CHLNUM)
+ *dcmd |= PXA_DCMD_FLOWSRC;
}
if (dir == DMA_MEM_TO_DEV) {
maxburst = chan->cfg.dst_maxburst;
width = chan->cfg.dst_addr_width;
dev_addr = chan->cfg.dst_addr;
*dev_dst = dev_addr;
- *dcmd |= PXA_DCMD_INCSRCADDR | PXA_DCMD_FLOWTRG;
+ *dcmd |= PXA_DCMD_INCSRCADDR;
+ if (chan->drcmr <= DRCMR_CHLNUM)
+ *dcmd |= PXA_DCMD_FLOWTRG;
}
if (dir == DMA_MEM_TO_MEM)
*dcmd |= PXA_DCMD_BURST32 | PXA_DCMD_INCTRGADDR |
else
curr = phy_readl_relaxed(chan->phy, DTADR);
+ /*
+ * curr has to be actually read before checking descriptor
+ * completion, so that a curr inside a status updater
+ * descriptor implies the following test returns true, and
+ * preventing reordering of curr load and the test.
+ */
+ rmb();
+ if (is_desc_completed(vd))
+ goto out;
+
for (i = 0; i < sw_desc->nb_desc - 1; i++) {
hw_desc = sw_desc->hw_desc[i];
if (sw_desc->hw_desc[0]->dcmd & PXA_DCMD_INCSRCADDR)
static void sun4i_dma_free_contract(struct virt_dma_desc *vd)
{
struct sun4i_dma_contract *contract = to_sun4i_dma_contract(vd);
- struct sun4i_dma_promise *promise;
+ struct sun4i_dma_promise *promise, *tmp;
/* Free all the demands and completed demands */
- list_for_each_entry(promise, &contract->demands, list)
+ list_for_each_entry_safe(promise, tmp, &contract->demands, list)
kfree(promise);
- list_for_each_entry(promise, &contract->completed_demands, list)
+ list_for_each_entry_safe(promise, tmp, &contract->completed_demands, list)
kfree(promise);
kfree(contract);
#define XGENE_DMA_RING_MEM_RAM_SHUTDOWN 0xD070
#define XGENE_DMA_RING_BLK_MEM_RDY 0xD074
#define XGENE_DMA_RING_BLK_MEM_RDY_VAL 0xFFFFFFFF
-#define XGENE_DMA_RING_DESC_CNT(v) (((v) & 0x0001FFFE) >> 1)
#define XGENE_DMA_RING_ID_GET(owner, num) (((owner) << 6) | (num))
#define XGENE_DMA_RING_DST_ID(v) ((1 << 10) | (v))
#define XGENE_DMA_RING_CMD_OFFSET 0x2C
return flyby_type[src_cnt];
}
-static u32 xgene_dma_ring_desc_cnt(struct xgene_dma_ring *ring)
-{
- u32 __iomem *cmd_base = ring->cmd_base;
- u32 ring_state = ioread32(&cmd_base[1]);
-
- return XGENE_DMA_RING_DESC_CNT(ring_state);
-}
-
static void xgene_dma_set_src_buffer(__le64 *ext8, size_t *len,
dma_addr_t *paddr)
{
dma_pool_free(chan->desc_pool, desc, desc->tx.phys);
}
-static int xgene_chan_xfer_request(struct xgene_dma_ring *ring,
- struct xgene_dma_desc_sw *desc_sw)
+static void xgene_chan_xfer_request(struct xgene_dma_chan *chan,
+ struct xgene_dma_desc_sw *desc_sw)
{
+ struct xgene_dma_ring *ring = &chan->tx_ring;
struct xgene_dma_desc_hw *desc_hw;
- /* Check if can push more descriptor to hw for execution */
- if (xgene_dma_ring_desc_cnt(ring) > (ring->slots - 2))
- return -EBUSY;
-
/* Get hw descriptor from DMA tx ring */
desc_hw = &ring->desc_hw[ring->head];
memcpy(desc_hw, &desc_sw->desc2, sizeof(*desc_hw));
}
+ /* Increment the pending transaction count */
+ chan->pending += ((desc_sw->flags &
+ XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
+
/* Notify the hw that we have descriptor ready for execution */
iowrite32((desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) ?
2 : 1, ring->cmd);
-
- return 0;
}
/**
static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan)
{
struct xgene_dma_desc_sw *desc_sw, *_desc_sw;
- int ret;
/*
* If the list of pending descriptors is empty, then we
if (chan->pending >= chan->max_outstanding)
return;
- ret = xgene_chan_xfer_request(&chan->tx_ring, desc_sw);
- if (ret)
- return;
+ xgene_chan_xfer_request(chan, desc_sw);
/*
* Delete this element from ld pending queue and append it to
* ld running queue
*/
list_move_tail(&desc_sw->node, &chan->ld_running);
-
- /* Increment the pending transaction count */
- chan->pending++;
}
}
* Decrement the pending transaction count
* as we have processed one
*/
- chan->pending--;
+ chan->pending -= ((desc_sw->flags &
+ XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
/*
* Delete this node from ld running queue and append it to
struct xgene_dma_ring *ring,
enum xgene_dma_ring_cfgsize cfgsize)
{
+ int ret;
+
/* Setup DMA ring descriptor variables */
ring->pdma = chan->pdma;
ring->cfgsize = cfgsize;
ring->num = chan->pdma->ring_num++;
ring->id = XGENE_DMA_RING_ID_GET(ring->owner, ring->buf_num);
- ring->size = xgene_dma_get_ring_size(chan, cfgsize);
- if (ring->size <= 0)
- return ring->size;
+ ret = xgene_dma_get_ring_size(chan, cfgsize);
+ if (ret <= 0)
+ return ret;
+ ring->size = ret;
/* Allocate memory for DMA ring descriptor */
ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size,
tx_ring->id, tx_ring->num, tx_ring->desc_vaddr);
/* Set the max outstanding request possible to this channel */
- chan->max_outstanding = rx_ring->slots;
+ chan->max_outstanding = tx_ring->slots;
return ret;
}
struct dma_chan *chan;
struct zx_dma_chan *c;
- if (request > d->dma_requests)
+ if (request >= d->dma_requests)
return NULL;
chan = dma_get_any_slave_channel(&d->slave);
{ .compatible = "stericsson,abx500-temp" },
{},
};
+MODULE_DEVICE_TABLE(of, abx500_temp_match);
#endif
static struct platform_driver abx500_temp_driver = {
{ .compatible = "gpio-fan", },
{},
};
+MODULE_DEVICE_TABLE(of, of_gpio_fan_match);
#endif /* CONFIG_OF_GPIO */
static int gpio_fan_probe(struct platform_device *pdev)
{ .compatible = "pwm-fan", },
{},
};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match);
static struct platform_driver pwm_fan_driver = {
.probe = pwm_fan_probe,
.name = "C6-SKL",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
- .exit_latency = 75,
+ .exit_latency = 85,
.target_residency = 200,
.enter = &intel_idle,
.enter_freeze = intel_idle_freeze, },
.name = "C8-SKL",
.desc = "MWAIT 0x40",
.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
- .exit_latency = 174,
+ .exit_latency = 200,
.target_residency = 800,
.enter = &intel_idle,
.enter_freeze = intel_idle_freeze, },
+ {
+ .name = "C9-SKL",
+ .desc = "MWAIT 0x50",
+ .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 480,
+ .target_residency = 5000,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
{
.name = "C10-SKL",
.desc = "MWAIT 0x60",
props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
if (MLX5_CAP_GEN(mdev, apm))
props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
- props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
if (MLX5_CAP_GEN(mdev, xrc))
props->device_cap_flags |= IB_DEVICE_XRC;
props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
return 0;
}
-static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
-{
- struct mlx5_create_mkey_mbox_in *in;
- struct mlx5_mkey_seg *seg;
- struct mlx5_core_mr mr;
- int err;
-
- in = kzalloc(sizeof(*in), GFP_KERNEL);
- if (!in)
- return -ENOMEM;
-
- seg = &in->seg;
- seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA;
- seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
- seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
- seg->start_addr = 0;
-
- err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in),
- NULL, NULL, NULL);
- if (err) {
- mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
- goto err_in;
- }
-
- kfree(in);
- *key = mr.key;
-
- return 0;
-
-err_in:
- kfree(in);
-
- return err;
-}
-
-static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key)
-{
- struct mlx5_core_mr mr;
- int err;
-
- memset(&mr, 0, sizeof(mr));
- mr.key = key;
- err = mlx5_core_destroy_mkey(dev->mdev, &mr);
- if (err)
- mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key);
-}
-
static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
struct ib_ucontext *context,
struct ib_udata *udata)
kfree(pd);
return ERR_PTR(-EFAULT);
}
- } else {
- err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn);
- if (err) {
- mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn);
- kfree(pd);
- return ERR_PTR(err);
- }
}
return &pd->ibpd;
struct mlx5_ib_dev *mdev = to_mdev(pd->device);
struct mlx5_ib_pd *mpd = to_mpd(pd);
- if (!pd->uobject)
- free_pa_mkey(mdev, mpd->pa_lkey);
-
mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn);
kfree(mpd);
struct ib_srq_init_attr attr;
struct mlx5_ib_dev *dev;
struct ib_cq_init_attr cq_attr = {.cqe = 1};
- u32 rsvd_lkey;
int ret = 0;
dev = container_of(devr, struct mlx5_ib_dev, devr);
- ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey);
- if (ret) {
- pr_err("Failed to query special context %d\n", ret);
- return ret;
- }
- dev->ib_dev.local_dma_lkey = rsvd_lkey;
-
devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
if (IS_ERR(devr->p0)) {
ret = PTR_ERR(devr->p0);
strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
dev->ib_dev.owner = THIS_MODULE;
dev->ib_dev.node_type = RDMA_NODE_IB_CA;
+ dev->ib_dev.local_dma_lkey = 0 /* not supported for now */;
dev->num_ports = MLX5_CAP_GEN(mdev, num_ports);
dev->ib_dev.phys_port_cnt = dev->num_ports;
dev->ib_dev.num_comp_vectors =
struct mlx5_ib_pd {
struct ib_pd ibpd;
u32 pdn;
- u32 pa_lkey;
};
/* Use macros here so that don't have to duplicate
int uuarn;
int create_type;
- u32 pa_lkey;
/* Store signature errors */
bool signature_en;
err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
if (err)
mlx5_ib_dbg(dev, "err %d\n", err);
- else
- qp->pa_lkey = to_mpd(pd)->pa_lkey;
}
if (err)
mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
dseg->addr = cpu_to_be64(mfrpl->map);
dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64));
- dseg->lkey = cpu_to_be32(pd->pa_lkey);
+ dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
}
static __be32 send_ieth(struct ib_send_wr *wr)
IPOIB_NUM_WC = 4,
IPOIB_MAX_PATH_REC_QUEUE = 3,
- IPOIB_MAX_MCAST_QUEUE = 3,
+ IPOIB_MAX_MCAST_QUEUE = 64,
IPOIB_FLAG_OPER_UP = 0,
IPOIB_FLAG_INITIALIZED = 1,
int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
int ipoib_init_qp(struct net_device *dev);
int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
unsigned long dt;
unsigned long flags;
int i;
+ LIST_HEAD(remove_list);
+ struct ipoib_mcast *mcast, *tmcast;
+ struct net_device *dev = priv->dev;
if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
return;
lockdep_is_held(&priv->lock))) != NULL) {
/* was the neigh idle for two GC periods */
if (time_after(neigh_obsolete, neigh->alive)) {
+ u8 *mgid = neigh->daddr + 4;
+
+ /* Is this multicast ? */
+ if (*mgid == 0xff) {
+ mcast = __ipoib_mcast_find(dev, mgid);
+
+ if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+ list_del(&mcast->list);
+ rb_erase(&mcast->rb_node, &priv->multicast_tree);
+ list_add_tail(&mcast->list, &remove_list);
+ }
+ }
+
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
lockdep_is_held(&priv->lock)));
out_unlock:
spin_unlock_irqrestore(&priv->lock, flags);
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+ ipoib_mcast_leave(dev, mcast);
}
static void ipoib_reap_neigh(struct work_struct *work)
return mcast;
}
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct rb_node *n = priv->multicast_tree.rb_node;
rec.hop_limit = priv->broadcast->mcmember.hop_limit;
/*
- * Historically Linux IPoIB has never properly supported SEND
- * ONLY join. It emulated it by not providing all the required
- * attributes, which is enough to prevent group creation and
- * detect if there are full members or not. A major problem
- * with supporting SEND ONLY is detecting when the group is
- * auto-destroyed as IPoIB will cache the MLID..
+ * Send-only IB Multicast joins do not work at the core
+ * IB layer yet, so we can't use them here. However,
+ * we are emulating an Ethernet multicast send, which
+ * does not require a multicast subscription and will
+ * still send properly. The most appropriate thing to
+ * do is to create the group if it doesn't exist as that
+ * most closely emulates the behavior, from a user space
+ * application perspecitive, of Ethernet multicast
+ * operation. For now, we do a full join, maybe later
+ * when the core IB layers support send only joins we
+ * will use them.
*/
-#if 1
- if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
- comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
rec.join_state = 4;
#endif
return 0;
}
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret = 0;
module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+ "Always register memory, even for continuous memory regions (default:true)");
+
bool iser_pi_enable = false;
module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
extern bool iser_pi_enable;
extern int iser_pi_guard;
extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
int iser_assign_reg_ops(struct iser_device *device);
iser_reg_prot_sg(struct iscsi_iser_task *task,
struct iser_data_buf *mem,
struct iser_fr_desc *desc,
+ bool use_dma_key,
struct iser_mem_reg *reg)
{
struct iser_device *device = task->iser_conn->ib_conn.device;
- if (mem->dma_nents == 1)
+ if (use_dma_key)
return iser_reg_dma(device, mem, reg);
return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
iser_reg_data_sg(struct iscsi_iser_task *task,
struct iser_data_buf *mem,
struct iser_fr_desc *desc,
+ bool use_dma_key,
struct iser_mem_reg *reg)
{
struct iser_device *device = task->iser_conn->ib_conn.device;
- if (mem->dma_nents == 1)
+ if (use_dma_key)
return iser_reg_dma(device, mem, reg);
return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
struct iser_mem_reg *reg = &task->rdma_reg[dir];
struct iser_mem_reg *data_reg;
struct iser_fr_desc *desc = NULL;
+ bool use_dma_key;
int err;
err = iser_handle_unaligned_buf(task, mem, dir);
if (unlikely(err))
return err;
- if (mem->dma_nents != 1 ||
- scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+ use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+ scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+ if (!use_dma_key) {
desc = device->reg_ops->reg_desc_get(ib_conn);
reg->mem_h = desc;
}
else
data_reg = &task->desc.data_reg;
- err = iser_reg_data_sg(task, mem, desc, data_reg);
+ err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
if (unlikely(err))
goto err_reg;
if (unlikely(err))
goto err_reg;
- err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+ err = iser_reg_prot_sg(task, mem, desc,
+ use_dma_key, prot_reg);
if (unlikely(err))
goto err_reg;
}
(unsigned long)comp);
}
- device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_REMOTE_READ);
- if (IS_ERR(device->mr))
- goto dma_mr_err;
+ if (!iser_always_reg) {
+ int access = IB_ACCESS_LOCAL_WRITE |
+ IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_READ;
+
+ device->mr = ib_get_dma_mr(device->pd, access);
+ if (IS_ERR(device->mr))
+ goto dma_mr_err;
+ }
INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
iser_event_handler);
return 0;
handler_err:
- ib_dereg_mr(device->mr);
+ if (device->mr)
+ ib_dereg_mr(device->mr);
dma_mr_err:
for (i = 0; i < device->comps_used; i++)
tasklet_kill(&device->comps[i].tasklet);
static void iser_free_device_ib_res(struct iser_device *device)
{
int i;
- BUG_ON(device->mr == NULL);
for (i = 0; i < device->comps_used; i++) {
struct iser_comp *comp = &device->comps[i];
}
(void)ib_unregister_event_handler(&device->event_handler);
- (void)ib_dereg_mr(device->mr);
+ if (device->mr)
+ (void)ib_dereg_mr(device->mr);
ib_dealloc_pd(device->pd);
kfree(device->comps);
config JOYSTICK_ZHENHUA
tristate "5-byte Zhenhua RC transmitter"
select SERIO
+ select BITREVERSE
help
Say Y here if you have a Zhen Hua PPM-4CH transmitter which is
supplied with a ready to fly micro electric indoor helicopters
endmenu
config IOMMU_IOVA
- bool
+ tristate
config OF_IOMMU
def_bool y
/* Restrict dma_mask to the width that the iommu can handle */
dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+ /* Ensure we reserve the whole size-aligned region */
+ nrpages = __roundup_pow_of_two(nrpages);
if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
/*
static int __init iommu_init_mempool(void)
{
int ret;
- ret = iommu_iova_cache_init();
+ ret = iova_cache_get();
if (ret)
return ret;
kmem_cache_destroy(iommu_domain_cache);
domain_error:
- iommu_iova_cache_destroy();
+ iova_cache_put();
return -ENOMEM;
}
{
kmem_cache_destroy(iommu_devinfo_cache);
kmem_cache_destroy(iommu_domain_cache);
- iommu_iova_cache_destroy();
+ iova_cache_put();
}
static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
*/
#include <linux/iova.h>
+#include <linux/module.h>
#include <linux/slab.h>
-static struct kmem_cache *iommu_iova_cache;
-
-int iommu_iova_cache_init(void)
-{
- int ret = 0;
-
- iommu_iova_cache = kmem_cache_create("iommu_iova",
- sizeof(struct iova),
- 0,
- SLAB_HWCACHE_ALIGN,
- NULL);
- if (!iommu_iova_cache) {
- pr_err("Couldn't create iova cache\n");
- ret = -ENOMEM;
- }
-
- return ret;
-}
-
-void iommu_iova_cache_destroy(void)
-{
- kmem_cache_destroy(iommu_iova_cache);
-}
-
-struct iova *alloc_iova_mem(void)
-{
- return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
- kmem_cache_free(iommu_iova_cache, iova);
-}
-
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
unsigned long start_pfn, unsigned long pfn_32bit)
iovad->start_pfn = start_pfn;
iovad->dma_32bit_pfn = pfn_32bit;
}
+EXPORT_SYMBOL_GPL(init_iova_domain);
static struct rb_node *
__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
}
}
-/* Computes the padding size required, to make the
- * the start address naturally aligned on its size
+/*
+ * Computes the padding size required, to make the start address
+ * naturally aligned on the power-of-two order of its size
*/
-static int
-iova_get_pad_size(int size, unsigned int limit_pfn)
+static unsigned int
+iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
{
- unsigned int pad_size = 0;
- unsigned int order = ilog2(size);
-
- if (order)
- pad_size = (limit_pfn + 1) % (1 << order);
-
- return pad_size;
+ return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1);
}
static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
rb_insert_color(&iova->node, root);
}
+static struct kmem_cache *iova_cache;
+static unsigned int iova_cache_users;
+static DEFINE_MUTEX(iova_cache_mutex);
+
+struct iova *alloc_iova_mem(void)
+{
+ return kmem_cache_alloc(iova_cache, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(alloc_iova_mem);
+
+void free_iova_mem(struct iova *iova)
+{
+ kmem_cache_free(iova_cache, iova);
+}
+EXPORT_SYMBOL(free_iova_mem);
+
+int iova_cache_get(void)
+{
+ mutex_lock(&iova_cache_mutex);
+ if (!iova_cache_users) {
+ iova_cache = kmem_cache_create(
+ "iommu_iova", sizeof(struct iova), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!iova_cache) {
+ mutex_unlock(&iova_cache_mutex);
+ printk(KERN_ERR "Couldn't create iova cache\n");
+ return -ENOMEM;
+ }
+ }
+
+ iova_cache_users++;
+ mutex_unlock(&iova_cache_mutex);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iova_cache_get);
+
+void iova_cache_put(void)
+{
+ mutex_lock(&iova_cache_mutex);
+ if (WARN_ON(!iova_cache_users)) {
+ mutex_unlock(&iova_cache_mutex);
+ return;
+ }
+ iova_cache_users--;
+ if (!iova_cache_users)
+ kmem_cache_destroy(iova_cache);
+ mutex_unlock(&iova_cache_mutex);
+}
+EXPORT_SYMBOL_GPL(iova_cache_put);
+
/**
* alloc_iova - allocates an iova
* @iovad: - iova domain in question
if (!new_iova)
return NULL;
- /* If size aligned is set then round the size to
- * to next power of two.
- */
- if (size_aligned)
- size = __roundup_pow_of_two(size);
-
ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
new_iova, size_aligned);
return new_iova;
}
+EXPORT_SYMBOL_GPL(alloc_iova);
/**
* find_iova - find's an iova for a given pfn
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return NULL;
}
+EXPORT_SYMBOL_GPL(find_iova);
/**
* __free_iova - frees the given iova
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
free_iova_mem(iova);
}
+EXPORT_SYMBOL_GPL(__free_iova);
/**
* free_iova - finds and frees the iova for a given pfn
__free_iova(iovad, iova);
}
+EXPORT_SYMBOL_GPL(free_iova);
/**
* put_iova_domain - destroys the iova doamin
}
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
}
+EXPORT_SYMBOL_GPL(put_iova_domain);
static int
__is_range_overlap(struct rb_node *node,
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return iova;
}
+EXPORT_SYMBOL_GPL(reserve_iova);
/**
* copy_reserved_iova - copies the reserved between domains
}
spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
}
+EXPORT_SYMBOL_GPL(copy_reserved_iova);
struct iova *
split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
free_iova_mem(prev);
return NULL;
}
+
+MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
+MODULE_LICENSE("GPL");
intrmask[i] = gic_read(intrmask_reg);
pending_reg += gic_reg_step;
intrmask_reg += gic_reg_step;
+
+ if (!config_enabled(CONFIG_64BIT) || mips_cm_is64)
+ continue;
+
+ pending[i] |= (u64)gic_read(pending_reg) << 32;
+ intrmask[i] |= (u64)gic_read(intrmask_reg) << 32;
+ pending_reg += gic_reg_step;
+ intrmask_reg += gic_reg_step;
}
bitmap_and(pending, pending, intrmask, gic_shared_intrs);
spin_lock_irqsave(&gic_lock, flags);
/* Re-route this IRQ */
- gic_map_to_vpe(irq, cpumask_first(&tmp));
+ gic_map_to_vpe(irq, mips_cm_vp_id(cpumask_first(&tmp)));
/* Update the pcpu_masks */
for (i = 0; i < NR_CPUS; i++)
GIC_SHARED_TO_HWIRQ(intr));
int i;
- gic_map_to_vpe(intr, cpu);
+ gic_map_to_vpe(intr, mips_cm_vp_id(cpu));
for (i = 0; i < NR_CPUS; i++)
clear_bit(intr, pcpu_masks[i].pcpu_mask);
set_bit(intr, pcpu_masks[cpu].pcpu_mask);
int err = cmd->error;
/* Flag re-tuning needed on CRC errors */
- if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+ if ((cmd->opcode != MMC_SEND_TUNING_BLOCK &&
+ cmd->opcode != MMC_SEND_TUNING_BLOCK_HS200) &&
+ (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
(mrq->data && mrq->data->error == -EILSEQ) ||
- (mrq->stop && mrq->stop->error == -EILSEQ))
+ (mrq->stop && mrq->stop->error == -EILSEQ)))
mmc_retune_needed(host);
if (err && cmd->retries && mmc_host_is_spi(host)) {
0, &cd_gpio_invert);
if (!ret)
dev_info(host->parent, "Got CD GPIO\n");
- else if (ret != -ENOENT)
+ else if (ret != -ENOENT && ret != -ENOSYS)
return ret;
/*
ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert);
if (!ret)
dev_info(host->parent, "Got WP GPIO\n");
- else if (ret != -ENOENT)
+ else if (ret != -ENOENT && ret != -ENOSYS)
return ret;
if (of_property_read_bool(np, "disable-wp"))
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/mmc/host.h>
+#include <linux/mmc/slot-gpio.h>
#include <linux/io.h>
#include <linux/regulator/consumer.h>
#include <linux/gpio.h>
{
struct pxamci_host *host = mmc_priv(mmc);
- if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro)) {
- if (host->pdata->gpio_card_ro_invert)
- return !gpio_get_value(host->pdata->gpio_card_ro);
- else
- return gpio_get_value(host->pdata->gpio_card_ro);
- }
+ if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro))
+ return mmc_gpio_get_ro(mmc);
if (host->pdata && host->pdata->get_ro)
return !!host->pdata->get_ro(mmc_dev(mmc));
/*
static const struct mmc_host_ops pxamci_ops = {
.request = pxamci_request,
+ .get_cd = mmc_gpio_get_cd,
.get_ro = pxamci_get_ro,
.set_ios = pxamci_set_ios,
.enable_sdio_irq = pxamci_enable_sdio_irq,
gpio_power = host->pdata->gpio_power;
}
if (gpio_is_valid(gpio_power)) {
- ret = gpio_request(gpio_power, "mmc card power");
+ ret = devm_gpio_request(&pdev->dev, gpio_power,
+ "mmc card power");
if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_power %d\n", gpio_power);
+ dev_err(&pdev->dev, "Failed requesting gpio_power %d\n",
+ gpio_power);
goto out;
}
gpio_direction_output(gpio_power,
host->pdata->gpio_power_invert);
}
- if (gpio_is_valid(gpio_ro)) {
- ret = gpio_request(gpio_ro, "mmc card read only");
- if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
- goto err_gpio_ro;
- }
- gpio_direction_input(gpio_ro);
+ if (gpio_is_valid(gpio_ro))
+ ret = mmc_gpio_request_ro(mmc, gpio_ro);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
+ goto out;
+ } else {
+ mmc->caps |= host->pdata->gpio_card_ro_invert ?
+ MMC_CAP2_RO_ACTIVE_HIGH : 0;
}
- if (gpio_is_valid(gpio_cd)) {
- ret = gpio_request(gpio_cd, "mmc card detect");
- if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
- goto err_gpio_cd;
- }
- gpio_direction_input(gpio_cd);
- ret = request_irq(gpio_to_irq(gpio_cd), pxamci_detect_irq,
- IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
- "mmc card detect", mmc);
- if (ret) {
- dev_err(&pdev->dev, "failed to request card detect IRQ\n");
- goto err_request_irq;
- }
+ if (gpio_is_valid(gpio_cd))
+ ret = mmc_gpio_request_cd(mmc, gpio_cd, 0);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
+ goto out;
}
if (host->pdata && host->pdata->init)
return 0;
-err_request_irq:
- gpio_free(gpio_cd);
-err_gpio_cd:
- gpio_free(gpio_ro);
-err_gpio_ro:
- gpio_free(gpio_power);
- out:
+out:
if (host) {
if (host->dma_chan_rx)
dma_release_channel(host->dma_chan_rx);
gpio_ro = host->pdata->gpio_card_ro;
gpio_power = host->pdata->gpio_power;
}
- if (gpio_is_valid(gpio_cd)) {
- free_irq(gpio_to_irq(gpio_cd), mmc);
- gpio_free(gpio_cd);
- }
- if (gpio_is_valid(gpio_ro))
- gpio_free(gpio_ro);
- if (gpio_is_valid(gpio_power))
- gpio_free(gpio_power);
if (host->vcc)
regulator_put(host->vcc);
#define SDXC_IDMAC_DES0_CES BIT(30) /* card error summary */
#define SDXC_IDMAC_DES0_OWN BIT(31) /* 1-idma owns it, 0-host owns it */
+#define SDXC_CLK_400K 0
+#define SDXC_CLK_25M 1
+#define SDXC_CLK_50M 2
+#define SDXC_CLK_50M_DDR 3
+
+struct sunxi_mmc_clk_delay {
+ u32 output;
+ u32 sample;
+};
+
struct sunxi_idma_des {
u32 config;
u32 buf_size;
struct clk *clk_mmc;
struct clk *clk_sample;
struct clk *clk_output;
+ const struct sunxi_mmc_clk_delay *clk_delays;
/* irq */
spinlock_t lock;
/* determine delays */
if (rate <= 400000) {
- oclk_dly = 180;
- sclk_dly = 42;
+ oclk_dly = host->clk_delays[SDXC_CLK_400K].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_400K].sample;
} else if (rate <= 25000000) {
- oclk_dly = 180;
- sclk_dly = 75;
+ oclk_dly = host->clk_delays[SDXC_CLK_25M].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_25M].sample;
} else if (rate <= 50000000) {
if (ios->timing == MMC_TIMING_UHS_DDR50) {
- oclk_dly = 60;
- sclk_dly = 120;
+ oclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].sample;
} else {
- oclk_dly = 90;
- sclk_dly = 150;
+ oclk_dly = host->clk_delays[SDXC_CLK_50M].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_50M].sample;
}
- } else if (rate <= 100000000) {
- oclk_dly = 6;
- sclk_dly = 24;
- } else if (rate <= 200000000) {
- oclk_dly = 3;
- sclk_dly = 12;
} else {
return -EINVAL;
}
static const struct of_device_id sunxi_mmc_of_match[] = {
{ .compatible = "allwinner,sun4i-a10-mmc", },
{ .compatible = "allwinner,sun5i-a13-mmc", },
+ { .compatible = "allwinner,sun9i-a80-mmc", },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
.hw_reset = sunxi_mmc_hw_reset,
};
+static const struct sunxi_mmc_clk_delay sunxi_mmc_clk_delays[] = {
+ [SDXC_CLK_400K] = { .output = 180, .sample = 180 },
+ [SDXC_CLK_25M] = { .output = 180, .sample = 75 },
+ [SDXC_CLK_50M] = { .output = 90, .sample = 120 },
+ [SDXC_CLK_50M_DDR] = { .output = 60, .sample = 120 },
+};
+
+static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
+ [SDXC_CLK_400K] = { .output = 180, .sample = 180 },
+ [SDXC_CLK_25M] = { .output = 180, .sample = 75 },
+ [SDXC_CLK_50M] = { .output = 150, .sample = 120 },
+ [SDXC_CLK_50M_DDR] = { .output = 90, .sample = 120 },
+};
+
static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
struct platform_device *pdev)
{
else
host->idma_des_size_bits = 16;
+ if (of_device_is_compatible(np, "allwinner,sun9i-a80-mmc"))
+ host->clk_delays = sun9i_mmc_clk_delays;
+ else
+ host->clk_delays = sunxi_mmc_clk_delays;
+
ret = mmc_regulator_get_supply(host->mmc);
if (ret) {
if (ret != -EPROBE_DEFER)
goto bad;
}
+ if (data_size > ubi->leb_size) {
+ ubi_err(ubi, "bad data_size");
+ goto bad;
+ }
+
if (vol_type == UBI_VID_STATIC) {
/*
* Although from high-level point of view static volumes may
if (ubi->corr_peb_count)
ubi_err(ubi, "%d PEBs are corrupted and not used",
ubi->corr_peb_count);
+ return -ENOSPC;
}
ubi->rsvd_pebs += reserved_pebs;
ubi->avail_pebs -= reserved_pebs;
if (ubi->corr_peb_count)
ubi_err(ubi, "%d PEBs are corrupted and not used",
ubi->corr_peb_count);
+ err = -ENOSPC;
goto out_free;
}
ubi->avail_pebs -= reserved_pebs;
reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA;
else
reg |= PORT_CONTROL_FRAME_MODE_DSA;
+ reg |= PORT_CONTROL_FORWARD_UNKNOWN |
+ PORT_CONTROL_FORWARD_UNKNOWN_MC;
}
if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
}
/* Flush FLI data fifo. */
-static u32
+static int
bfa_flash_fifo_flush(void __iomem *pci_bar)
{
u32 i;
}
/* Read flash status. */
-static u32
+static int
bfa_flash_status_read(void __iomem *pci_bar)
{
union bfa_flash_dev_status_reg dev_status;
- u32 status;
+ int status;
u32 ret_status;
int i;
}
/* Start flash read operation. */
-static u32
+static int
bfa_flash_read_start(void __iomem *pci_bar, u32 offset, u32 len,
char *buf)
{
- u32 status;
+ int status;
/* len must be mutiple of 4 and not exceeding fifo size */
if (len == 0 || len > BFA_FLASH_FIFO_SIZE || (len & 0x03) != 0)
bfa_flash_raw_read(void __iomem *pci_bar, u32 offset, char *buf,
u32 len)
{
- u32 n, status;
+ u32 n;
+ int status;
u32 off, l, s, residue, fifo_sz;
residue = len;
struct net_device *ndev;
struct hip04_priv *priv;
struct resource *res;
- unsigned int irq;
+ int irq;
int ret;
ndev = alloc_etherdev(sizeof(struct hip04_priv));
u32 index;
};
-#define EMAC_ETHTOOL_REGS_VER 0
-#define EMAC4_ETHTOOL_REGS_VER 1
-#define EMAC4SYNC_ETHTOOL_REGS_VER 2
+#define EMAC_ETHTOOL_REGS_VER 3
+#define EMAC4_ETHTOOL_REGS_VER 4
+#define EMAC4SYNC_ETHTOOL_REGS_VER 5
#endif /* __IBM_NEWEMAC_CORE_H */
/* take the lock before we start messing with the ring */
mutex_lock(&hw->aq.arq_mutex);
+ if (hw->aq.arq.count == 0) {
+ i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Admin queue not initialized.\n");
+ ret_code = I40E_ERR_QUEUE_EMPTY;
+ goto clean_arq_element_err;
+ }
+
/* set next_to_use to head */
ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK);
if (ntu == ntc) {
/* Set pending if needed, unlock and return */
if (pending != NULL)
*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
mutex_unlock(&hw->aq.arq_mutex);
if (i40e_is_nvm_update_op(&e->desc)) {
rx_ctx.lrxqthresh = 2;
rx_ctx.crcstrip = 1;
rx_ctx.l2tsel = 1;
- rx_ctx.showiv = 1;
+ /* this controls whether VLAN is stripped from inner headers */
+ rx_ctx.showiv = 0;
#ifdef I40E_FCOE
rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
#endif
/* take the lock before we start messing with the ring */
mutex_lock(&hw->aq.arq_mutex);
+ if (hw->aq.arq.count == 0) {
+ i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Admin queue not initialized.\n");
+ ret_code = I40E_ERR_QUEUE_EMPTY;
+ goto clean_arq_element_err;
+ }
+
/* set next_to_use to head */
ntu = (rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK);
if (ntu == ntc) {
/* Set pending if needed, unlock and return */
if (pending != NULL)
*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
mutex_unlock(&hw->aq.arq_mutex);
return ret_code;
if (prot == MLX4_PROT_ETH) {
/* manage the steering entry for promisc mode */
if (new_entry)
- new_steering_entry(dev, port, steer, index, qp->qpn);
+ err = new_steering_entry(dev, port, steer,
+ index, qp->qpn);
else
- existing_steering_entry(dev, port, steer,
- index, qp->qpn);
+ err = existing_steering_entry(dev, port, steer,
+ index, qp->qpn);
}
if (err && link && index != -1) {
if (index < dev->caps.num_mgms)
return err;
}
-
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey)
-{
- struct mlx5_cmd_query_special_contexts_mbox_in in;
- struct mlx5_cmd_query_special_contexts_mbox_out out;
- int err;
-
- memset(&in, 0, sizeof(in));
- memset(&out, 0, sizeof(out));
- in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
- err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
- if (err)
- return err;
-
- if (out.hdr.status)
- err = mlx5_cmd_status_to_err(&out.hdr);
-
- *rsvd_lkey = be32_to_cpu(out.resd_lkey);
-
- return err;
-}
-EXPORT_SYMBOL(mlx5_core_query_special_context);
{
void __iomem *ioaddr = tp->mmio_addr;
struct pci_dev *pdev = tp->pci_dev;
- u16 rg_saw_cnt;
+ int rg_saw_cnt;
u32 data;
static const struct ephy_info e_info_8168h_1[] = {
{ 0x1e, 0x0800, 0x0001 },
* Unbound PCI devices are always put in D0, regardless of
* runtime PM status. During probe, the device is set to
* active and the usage count is incremented. If the driver
- * supports runtime PM, it should call pm_runtime_put_noidle()
- * in its probe routine and pm_runtime_get_noresume() in its
- * remove routine.
+ * supports runtime PM, it should call pm_runtime_put_noidle(),
+ * or any other runtime PM helper function decrementing the usage
+ * count, in its probe routine and pm_runtime_get_noresume() in
+ * its remove routine.
*/
pm_runtime_get_sync(dev);
pci_dev->driver = pci_drv;
static void scsi_mq_done(struct scsi_cmnd *cmd)
{
trace_scsi_dispatch_cmd_done(cmd);
- blk_mq_complete_request(cmd->request);
+ blk_mq_complete_request(cmd->request, cmd->request->errors);
}
static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
switch_on_temp = 0;
temperature_threshold = control_temp - switch_on_temp;
+ /*
+ * estimate_pid_constants() tries to find appropriate default
+ * values for thermal zones that don't provide them. If a
+ * system integrator has configured a thermal zone with two
+ * passive trip points at the same temperature, that person
+ * hasn't put any effort to set up the thermal zone properly
+ * so just give up.
+ */
+ if (!temperature_threshold)
+ return;
if (!tz->tzp->k_po || force)
tz->tzp->k_po = int_to_frac(sustainable_power) /
tristate "Intel TCO Timer/Watchdog"
depends on (X86 || IA64) && PCI
select WATCHDOG_CORE
+ depends on I2C || I2C=n
select LPC_ICH if !EXPERT
- select I2C_I801 if !EXPERT
+ select I2C_I801 if !EXPERT && I2C
---help---
Hardware driver for the intel TCO timer based watchdog devices.
These drivers are included in the Intel 82801 I/O Controller
#define PM_RSTC_WRCFG_FULL_RESET 0x00000020
#define PM_RSTC_RESET 0x00000102
+/*
+ * The Raspberry Pi firmware uses the RSTS register to know which partiton
+ * to boot from. The partiton value is spread into bits 0, 2, 4, 6, 8, 10.
+ * Partiton 63 is a special partition used by the firmware to indicate halt.
+ */
+#define PM_RSTS_RASPBERRYPI_HALT 0x555
+
#define SECS_TO_WDOG_TICKS(x) ((x) << 16)
#define WDOG_TICKS_TO_SECS(x) ((x) >> 16)
* hard reset.
*/
val = readl_relaxed(wdt->base + PM_RSTS);
- val &= PM_RSTC_WRCFG_CLR;
- val |= PM_PASSWORD | PM_RSTS_HADWRH_SET;
+ val |= PM_PASSWORD | PM_RSTS_RASPBERRYPI_HALT;
writel_relaxed(val, wdt->base + PM_RSTS);
/* Continue with normal reset mechanism */
},
{},
};
+MODULE_DEVICE_TABLE(of, gef_wdt_ids);
static struct platform_driver gef_wdt_driver = {
.driver = {
{ .compatible = "men,a021-wdt" },
{ },
};
+MODULE_DEVICE_TABLE(of, a21_wdt_ids);
static struct platform_driver a21_wdt_driver = {
.probe = a21_wdt_probe,
{ .compatible = "moxa,moxart-watchdog" },
{ },
};
+MODULE_DEVICE_TABLE(of, moxart_watchdog_match);
static struct platform_driver moxart_wdt_driver = {
.probe = moxart_wdt_probe,
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
goto fallback;
+ sector = bh.b_blocknr << (blkbits - 9);
+
if (buffer_unwritten(&bh) || buffer_new(&bh)) {
int i;
+
+ length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+ bh.b_size);
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+ goto fallback;
+
for (i = 0; i < PTRS_PER_PMD; i++)
clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
wmb_pmem();
result = VM_FAULT_NOPAGE;
spin_unlock(ptl);
} else {
- sector = bh.b_blocknr << (blkbits - 9);
length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
bh.b_size);
if (length < 0) {
{
int err;
- mutex_lock(&inode->i_mutex);
err = security_inode_init_security(inode, dentry, qstr,
&init_xattrs, 0);
- mutex_unlock(&inode->i_mutex);
-
if (err) {
struct ubifs_info *c = dentry->i_sb->s_fs_info;
ubifs_err(c, "cannot initialize security for inode %lu, error %d",
int acpi_pci_irq_enable (struct pci_dev *dev);
void acpi_penalize_isa_irq(int irq, int active);
+bool acpi_isa_irq_available(int irq);
void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
void acpi_pci_irq_disable (struct pci_dev *dev);
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
- BLK_MQ_F_SYSFS_UP = 1 << 3,
BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_F_ALLOC_POLICY_BITS = 1,
void blk_mq_cancel_requeue_work(struct request_queue *q);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_abort_requeue_list(struct request_queue *q);
-void blk_mq_complete_request(struct request *rq);
+void blk_mq_complete_request(struct request *rq, int error);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
- void *priv);
void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
void *priv);
void blk_mq_freeze_queue(struct request_queue *q);
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set *bio_split;
+
+ bool mq_sysfs_init_done;
};
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */
return iova >> iova_shift(iovad);
}
-int iommu_iova_cache_init(void);
-void iommu_iova_cache_destroy(void);
+int iova_cache_get(void);
+void iova_cache_put(void);
struct iova *alloc_iova_mem(void);
void free_iova_mem(struct iova *iova);
* percpu counter.
*/
struct mem_cgroup_stat_cpu __percpu *stat;
- spinlock_t pcp_counter_lock;
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
struct cg_proto tcp_mem;
u8 rsvd[8];
};
-struct mlx5_cmd_query_special_contexts_mbox_in {
- struct mlx5_inbox_hdr hdr;
- u8 rsvd[8];
-};
-
-struct mlx5_cmd_query_special_contexts_mbox_out {
- struct mlx5_outbox_hdr hdr;
- __be32 dump_fill_mkey;
- __be32 resd_lkey;
-};
-
struct mlx5_cmd_layout {
u8 type;
u8 rsvd0[3];
int mlx5_register_interface(struct mlx5_interface *intf);
void mlx5_unregister_interface(struct mlx5_interface *intf);
int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey);
struct mlx5_profile {
u64 mask;
#endif
}
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+ return page->mem_cgroup;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+ page->mem_cgroup = memcg;
+}
+#else
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+ return NULL;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+}
+#endif
+
/*
* Some inline functions in vmstat.h depend on page_zone()
*/
struct rcu_synchronize *rs_array);
#define _wait_rcu_gp(checktiny, ...) \
-do { \
- call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
- const int __n = ARRAY_SIZE(__crcu_array); \
- struct rcu_synchronize __rs_array[__n]; \
- \
- __wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \
+do { \
+ call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
+ struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \
+ __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \
+ __crcu_array, __rs_array); \
} while (0)
#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_start_offset(skb) <= len)
+ skb_checksum_start_offset(skb) < 0)
skb->ip_summed = CHECKSUM_NONE;
}
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
};
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+ return (struct unix_sock *)sk;
+}
#define peer_wait peer_wq.wait
#include <linux/types.h>
-#include <linux/compiler.h>
-
#define UFFD_API ((__u64)0xAA)
/*
* After implementing the respective features it will become:
return retval;
}
- /* ipc_addid() locks msq upon success. */
- id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
- if (id < 0) {
- ipc_rcu_putref(msq, msg_rcu_free);
- return id;
- }
-
msq->q_stime = msq->q_rtime = 0;
msq->q_ctime = get_seconds();
msq->q_cbytes = msq->q_qnum = 0;
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
+ /* ipc_addid() locks msq upon success. */
+ id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+ if (id < 0) {
+ ipc_rcu_putref(msq, msg_rcu_free);
+ return id;
+ }
+
ipc_unlock_object(&msq->q_perm);
rcu_read_unlock();
if (IS_ERR(file))
goto no_file;
- id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
- if (id < 0) {
- error = id;
- goto no_id;
- }
-
shp->shm_cprid = task_tgid_vnr(current);
shp->shm_lprid = 0;
shp->shm_atim = shp->shm_dtim = 0;
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
+
+ id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+ if (id < 0) {
+ error = id;
+ goto no_id;
+ }
+
list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist);
/*
rcu_read_lock();
spin_lock(&new->lock);
+ current_euid_egid(&euid, &egid);
+ new->cuid = new->uid = euid;
+ new->gid = new->cgid = egid;
+
id = idr_alloc(&ids->ipcs_idr, new,
(next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
GFP_NOWAIT);
ids->in_use++;
- current_euid_egid(&euid, &egid);
- new->cuid = new->uid = euid;
- new->gid = new->cgid = egid;
-
if (next_id < 0) {
new->seq = ids->seq++;
if (ids->seq > IPCID_SEQ_MAX)
PERF_EVENT_STATE_INACTIVE;
}
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
{
int entry = sizeof(u64); /* value */
int size = 0;
entry += sizeof(u64);
if (event->attr.read_format & PERF_FORMAT_GROUP) {
- nr += event->group_leader->nr_siblings;
+ nr += nr_siblings;
size += sizeof(u64);
}
event->read_size = size;
}
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
{
struct perf_sample_data *data;
- u64 sample_type = event->attr.sample_type;
u16 size = 0;
- perf_event__read_size(event);
-
if (sample_type & PERF_SAMPLE_IP)
size += sizeof(data->ip);
event->header_size = size;
}
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+ __perf_event_read_size(event,
+ event->group_leader->nr_siblings);
+ __perf_event_header_size(event, event->attr.sample_type);
+}
+
static void perf_event__id_header_size(struct perf_event *event)
{
struct perf_sample_data *data;
event->id_header_size = size;
}
+static bool perf_event_validate_size(struct perf_event *event)
+{
+ /*
+ * The values computed here will be over-written when we actually
+ * attach the event.
+ */
+ __perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+ __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+ perf_event__id_header_size(event);
+
+ /*
+ * Sum the lot; should not exceed the 64k limit we have on records.
+ * Conservative limit to allow for callchains and other variable fields.
+ */
+ if (event->read_size + event->header_size +
+ event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+ return false;
+
+ return true;
+}
+
static void perf_group_attach(struct perf_event *event)
{
struct perf_event *group_leader = event->group_leader, *pos;
if (move_group) {
gctx = group_leader->ctx;
+ mutex_lock_double(&gctx->mutex, &ctx->mutex);
+ } else {
+ mutex_lock(&ctx->mutex);
+ }
+ if (!perf_event_validate_size(event)) {
+ err = -E2BIG;
+ goto err_locked;
+ }
+
+ /*
+ * Must be under the same ctx::mutex as perf_install_in_context(),
+ * because we need to serialize with concurrent event creation.
+ */
+ if (!exclusive_event_installable(event, ctx)) {
+ /* exclusive and group stuff are assumed mutually exclusive */
+ WARN_ON_ONCE(move_group);
+
+ err = -EBUSY;
+ goto err_locked;
+ }
+
+ WARN_ON_ONCE(ctx->parent_ctx);
+
+ if (move_group) {
/*
* See perf_event_ctx_lock() for comments on the details
* of swizzling perf_event::ctx.
*/
- mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
perf_remove_from_context(group_leader, false);
list_for_each_entry(sibling, &group_leader->sibling_list,
perf_remove_from_context(sibling, false);
put_ctx(gctx);
}
- } else {
- mutex_lock(&ctx->mutex);
- }
- WARN_ON_ONCE(ctx->parent_ctx);
-
- if (move_group) {
/*
* Wait for everybody to stop referencing the events through
* the old lists, before installing it on new lists.
perf_event__state_init(group_leader);
perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx);
- }
- if (!exclusive_event_installable(event, ctx)) {
- err = -EBUSY;
- mutex_unlock(&ctx->mutex);
- fput(event_file);
- goto err_context;
+ /*
+ * Now that all events are installed in @ctx, nothing
+ * references @gctx anymore, so drop the last reference we have
+ * on it.
+ */
+ put_ctx(gctx);
}
+ /*
+ * Precalculate sample_data sizes; do while holding ctx::mutex such
+ * that we're serialized against further additions and before
+ * perf_install_in_context() which is the point the event is active and
+ * can use these values.
+ */
+ perf_event__header_size(event);
+ perf_event__id_header_size(event);
+
perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
- if (move_group) {
+ if (move_group)
mutex_unlock(&gctx->mutex);
- put_ctx(gctx);
- }
mutex_unlock(&ctx->mutex);
put_online_cpus();
list_add_tail(&event->owner_entry, ¤t->perf_event_list);
mutex_unlock(¤t->perf_event_mutex);
- /*
- * Precalculate sample_data sizes
- */
- perf_event__header_size(event);
- perf_event__id_header_size(event);
-
/*
* Drop the reference on the group_event after placing the
* new event on the sibling_list. This ensures destruction
fd_install(event_fd, event_file);
return event_fd;
+err_locked:
+ if (move_group)
+ mutex_unlock(&gctx->mutex);
+ mutex_unlock(&ctx->mutex);
+/* err_file: */
+ fput(event_file);
err_context:
perf_unpin_context(ctx);
put_ctx(ctx);
static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int trylock, int read, int check, int hardirqs_off,
struct lockdep_map *nest_lock, unsigned long ip,
- int references)
+ int references, int pin_count)
{
struct task_struct *curr = current;
struct lock_class *class = NULL;
hlock->waittime_stamp = 0;
hlock->holdtime_stamp = lockstat_clock();
#endif
- hlock->pin_count = 0;
+ hlock->pin_count = pin_count;
if (check && !mark_irqflags(curr, hlock))
return 0;
hlock_class(hlock)->subclass, hlock->trylock,
hlock->read, hlock->check, hlock->hardirqs_off,
hlock->nest_lock, hlock->acquire_ip,
- hlock->references))
+ hlock->references, hlock->pin_count))
return 0;
}
hlock_class(hlock)->subclass, hlock->trylock,
hlock->read, hlock->check, hlock->hardirqs_off,
hlock->nest_lock, hlock->acquire_ip,
- hlock->references))
+ hlock->references, hlock->pin_count))
return 0;
}
current->lockdep_recursion = 1;
trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
__lock_acquire(lock, subclass, trylock, read, check,
- irqs_disabled_flags(flags), nest_lock, ip, 0);
+ irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
current->lockdep_recursion = 0;
raw_local_irq_restore(flags);
}
static void __init
rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
{
+ static struct lock_class_key rcu_exp_sched_rdp_class;
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
mutex_init(&rdp->exp_funnel_mutex);
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ if (rsp == &rcu_sched_state)
+ lockdep_set_class_and_name(&rdp->exp_funnel_mutex,
+ &rcu_exp_sched_rdp_class,
+ "rcu_data_exp_sched");
}
/*
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
- do_set_cpus_allowed(idle, cpumask_of(cpu));
+#ifdef CONFIG_SMP
+ /*
+ * Its possible that init_idle() gets called multiple times on a task,
+ * in that case do_set_cpus_allowed() will not do the right thing.
+ *
+ * And since this is boot we can forgo the serialization.
+ */
+ set_cpus_allowed_common(idle, cpumask_of(cpu));
+#endif
/*
* We're having a chicken and egg problem, even though we are
* holding rq->lock, the cpu isn't yet set to this cpu so the
rq->curr = rq->idle = idle;
idle->on_rq = TASK_ON_RQ_QUEUED;
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
idle->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
vtime_init_idle(idle, cpu);
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}
list_for_each_entry(page, &pool->page_list, page_list) {
if (dma < page->dma)
continue;
- if (dma < (page->dma + pool->allocation))
+ if ((dma - page->dma) < pool->allocation)
return page;
}
return NULL;
if (iter_vma == vma)
continue;
+ /*
+ * Shared VMAs have their own reserves and do not affect
+ * MAP_PRIVATE accounting but it is possible that a shared
+ * VMA is using the same page so check and skip such VMAs.
+ */
+ if (iter_vma->vm_flags & VM_MAYSHARE)
+ continue;
+
/*
* Unmap the page from other VMAs without their own reserves.
* They get marked to be SIGKILLed if they fault in these
}
/*
+ * Return page count for single (non recursive) @memcg.
+ *
* Implementation Note: reading percpu statistics for memcg.
*
* Both of vmstat[] and percpu_counter has threshold and do periodic
* synchronization to implement "quick" read. There are trade-off between
* reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
*
* But this _read() function is used for user interface now. The user accounts
* memory usage by memory cgroup and he _always_ requires exact value because
*
* If there are kernel internal actions which can make use of some not-exact
* value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
* implemented.
*/
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
- enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
{
long val = 0;
int cpu;
+ /* Per-cpu values can be negative, use a signed accumulator */
for_each_possible_cpu(cpu)
val += per_cpu(memcg->stat->count[idx], cpu);
+ /*
+ * Summing races with updates, so val may be negative. Avoid exposing
+ * transient negative values.
+ */
+ if (val < 0)
+ val = 0;
return val;
}
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+ pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
}
enum mem_cgroup_stat_index idx)
{
struct mem_cgroup *iter;
- long val = 0;
+ unsigned long val = 0;
- /* Per-cpu values can be negative, use a signed accumulator */
for_each_mem_cgroup_tree(iter, memcg)
val += mem_cgroup_read_stat(iter, idx);
- if (val < 0) /* race ? */
- val = 0;
return val;
}
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+ seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
}
(u64)memsw * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- long long val = 0;
+ unsigned long long val = 0;
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
- seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+ seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
}
for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
if (memcg_wb_domain_init(memcg, GFP_KERNEL))
goto out_free_stat;
- spin_lock_init(&memcg->pcp_counter_lock);
return memcg;
out_free_stat:
if (PageSwapBacked(page))
SetPageSwapBacked(newpage);
+ /*
+ * Indirectly called below, migrate_page_copy() copies PG_dirty and thus
+ * needs newpage's memcg set to transfer memcg dirty page accounting.
+ * So perform memcg migration in two steps:
+ * 1. set newpage->mem_cgroup (here)
+ * 2. clear page->mem_cgroup (below)
+ */
+ set_page_memcg(newpage, page_memcg(page));
+
mapping = page_mapping(page);
if (!mapping)
rc = migrate_page(mapping, newpage, page, mode);
rc = fallback_migrate_page(mapping, newpage, page, mode);
if (rc != MIGRATEPAGE_SUCCESS) {
+ set_page_memcg(newpage, NULL);
newpage->mapping = NULL;
} else {
- mem_cgroup_migrate(page, newpage, false);
+ set_page_memcg(page, NULL);
if (page_was_mapped)
remove_migration_ptes(page, newpage);
page->mapping = NULL;
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
- if (size >= kmalloc_size(INDEX_NODE + 1)
- && cachep->object_size > cache_line_size()
- && ALIGN(size, cachep->align) < PAGE_SIZE) {
+ /*
+ * To activate debug pagealloc, off-slab management is necessary
+ * requirement. In early phase of initialization, small sized slab
+ * doesn't get initialized so it would not be possible. So, we need
+ * to check size >= 256. It guarantees that all necessary small
+ * sized slab is initialized in current slab initialization sequence.
+ */
+ if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+ size >= 256 && cachep->object_size > cache_line_size() &&
+ ALIGN(size, cachep->align) < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
size = PAGE_SIZE;
}
static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
-static const char fmt_udec[] = "%u\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!__ethtool_get_settings(netdev, &cmd))
- ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
+ ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
return ret;
*/
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
+ unsigned char *data = skb->data;
+
BUG_ON(len > skb->len);
- skb->len -= len;
- BUG_ON(skb->len < skb->data_len);
- skb_postpull_rcsum(skb, skb->data, len);
- return skb->data += len;
+ __skb_pull(skb, len);
+ skb_postpull_rcsum(skb, data, len);
+ return skb->data;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
static int dsa_slave_port_attr_set(struct net_device *dev,
struct switchdev_attr *attr)
{
- int ret = 0;
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+ int ret;
switch (attr->id) {
case SWITCHDEV_ATTR_PORT_STP_STATE:
- if (attr->trans == SWITCHDEV_TRANS_COMMIT)
- ret = dsa_slave_stp_update(dev, attr->u.stp_state);
+ if (attr->trans == SWITCHDEV_TRANS_PREPARE)
+ ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP;
+ else
+ ret = ds->drv->port_stp_update(ds, p->port,
+ attr->u.stp_state);
break;
default:
ret = -EOPNOTSUPP;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_tun_key.tun_id = 0;
+ fl4.flowi4_flags = 0;
no_addr = idev->ifa_list == NULL;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+ fl4.flowi4_flags = 0;
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res, 0);
fl6->flowi6_iif = LOOPBACK_IFINDEX;
- if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
+ if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
+ fl6->flowi6_oif)
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl6->saddr))
tunnel = container_of(work, struct l2tp_tunnel, del_work);
sk = l2tp_tunnel_sock_lookup(tunnel);
if (!sk)
- return;
+ goto out;
sock = sk->sk_socket;
}
l2tp_tunnel_sock_put(sk);
+out:
+ l2tp_tunnel_dec_refcount(tunnel);
}
/* Create a socket for the tunnel, if one isn't set up by
*/
int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
{
+ l2tp_tunnel_inc_refcount(tunnel);
l2tp_tunnel_closeall(tunnel);
- return (false == queue_work(l2tp_wq, &tunnel->del_work));
+ if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+ l2tp_tunnel_dec_refcount(tunnel);
+ return 1;
+ }
+ return 0;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
* within this document.
*
* Our basic strategy is to round-robin transports in priorities
- * according to sctp_state_prio_map[] e.g., if no such
+ * according to sctp_trans_score() e.g., if no such
* transport with state SCTP_ACTIVE exists, round-robin through
* SCTP_UNKNOWN, etc. You get the picture.
*/
-static const u8 sctp_trans_state_to_prio_map[] = {
- [SCTP_ACTIVE] = 3, /* best case */
- [SCTP_UNKNOWN] = 2,
- [SCTP_PF] = 1,
- [SCTP_INACTIVE] = 0, /* worst case */
-};
-
static u8 sctp_trans_score(const struct sctp_transport *trans)
{
- return sctp_trans_state_to_prio_map[trans->state];
+ switch (trans->state) {
+ case SCTP_ACTIVE:
+ return 3; /* best case */
+ case SCTP_UNKNOWN:
+ return 2;
+ case SCTP_PF:
+ return 1;
+ default: /* case SCTP_INACTIVE */
+ return 0; /* worst case */
+ }
}
static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
int error;
struct sctp_transport *transport = (struct sctp_transport *) peer;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
/* Check whether a task is in the sock. */
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
transport, GFP_ATOMIC);
if (error)
- asoc->base.sk->sk_err = -error;
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_transport_put(transport);
}
static void sctp_generate_timeout_event(struct sctp_association *asoc,
sctp_event_timeout_t timeout_type)
{
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
int error = 0;
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy: timer %d\n", __func__,
timeout_type);
(void *)timeout_type, GFP_ATOMIC);
if (error)
- asoc->base.sk->sk_err = -error;
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_association_put(asoc);
}
int error = 0;
struct sctp_transport *transport = (struct sctp_transport *) data;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
asoc->state, asoc->ep, asoc,
transport, GFP_ATOMIC);
- if (error)
- asoc->base.sk->sk_err = -error;
+ if (error)
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_transport_put(transport);
}
{
struct sctp_transport *transport = (struct sctp_transport *) data;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_association_put(asoc);
}
fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
struct rpcrdma_create_data_internal *cdata)
{
- struct ib_device_attr *devattr = &ia->ri_devattr;
- struct ib_mr *mr;
-
- /* Obtain an lkey to use for the regbufs, which are
- * protected from remote access.
- */
- if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
- } else {
- mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE);
- if (IS_ERR(mr)) {
- pr_err("%s: ib_get_dma_mr for failed with %lX\n",
- __func__, PTR_ERR(mr));
- return -ENOMEM;
- }
- ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
- ia->ri_dma_mr = mr;
- }
-
return 0;
}
struct ib_device_attr *devattr = &ia->ri_devattr;
int depth, delta;
- /* Obtain an lkey to use for the regbufs, which are
- * protected from remote access.
- */
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
-
ia->ri_max_frmr_depth =
min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
devattr->max_fast_reg_page_list_len);
physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
struct rpcrdma_create_data_internal *cdata)
{
- struct ib_device_attr *devattr = &ia->ri_devattr;
struct ib_mr *mr;
/* Obtain an rkey to use for RPC data payloads.
__func__, PTR_ERR(mr));
return -ENOMEM;
}
- ia->ri_dma_mr = mr;
-
- /* Obtain an lkey to use for regbufs.
- */
- if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
- else
- ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
+ ia->ri_dma_mr = mr;
return 0;
}
goto out_free;
iov->length = size;
- iov->lkey = ia->ri_dma_lkey;
+ iov->lkey = ia->ri_pd->local_dma_lkey;
rb->rg_size = size;
rb->rg_owner = NULL;
return rb;
struct rdma_cm_id *ri_id;
struct ib_pd *ri_pd;
struct ib_mr *ri_dma_mr;
- u32 ri_dma_lkey;
struct completion ri_done;
int ri_async_rc;
unsigned int ri_max_frmr_depth;
if (UNIXCB(skb).fp)
scm.fp = scm_fp_dup(UNIXCB(skb).fp);
- sk_peek_offset_fwd(sk, chunk);
+ if (skip) {
+ sk_peek_offset_fwd(sk, chunk);
+ skip -= chunk;
+ }
+ if (UNIXCB(skb).fp)
+ break;
+
+ last = skb;
+ last_len = skb->len;
+ unix_state_lock(sk);
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ if (skb)
+ goto again;
+ unix_state_unlock(sk);
break;
}
} while (size);
/*
* Here's a sample kernel module showing the use of jprobes to dump
- * the arguments of do_fork().
+ * the arguments of _do_fork().
*
* For more information on theory of operation of jprobes, see
* Documentation/kprobes.txt
*
* Build and insert the kernel module as done in the kprobe example.
* You will see the trace data in /var/log/messages and on the
- * console whenever do_fork() is invoked to create a new process.
+ * console whenever _do_fork() is invoked to create a new process.
* (Some messages may be suppressed if syslogd is configured to
* eliminate duplicate messages.)
*/
#include <linux/kprobes.h>
/*
- * Jumper probe for do_fork.
+ * Jumper probe for _do_fork.
* Mirror principle enables access to arguments of the probed routine
* from the probe handler.
*/
-/* Proxy routine having the same arguments as actual do_fork() routine */
-static long jdo_fork(unsigned long clone_flags, unsigned long stack_start,
+/* Proxy routine having the same arguments as actual _do_fork() routine */
+static long j_do_fork(unsigned long clone_flags, unsigned long stack_start,
unsigned long stack_size, int __user *parent_tidptr,
int __user *child_tidptr)
{
}
static struct jprobe my_jprobe = {
- .entry = jdo_fork,
+ .entry = j_do_fork,
.kp = {
- .symbol_name = "do_fork",
+ .symbol_name = "_do_fork",
},
};
/*
* NOTE: This example is works on x86 and powerpc.
* Here's a sample kernel module showing the use of kprobes to dump a
- * stack trace and selected registers when do_fork() is called.
+ * stack trace and selected registers when _do_fork() is called.
*
* For more information on theory of operation of kprobes, see
* Documentation/kprobes.txt
*
* You will see the trace data in /var/log/messages and on the console
- * whenever do_fork() is invoked to create a new process.
+ * whenever _do_fork() is invoked to create a new process.
*/
#include <linux/kernel.h>
/* For each probe you need to allocate a kprobe structure */
static struct kprobe kp = {
- .symbol_name = "do_fork",
+ .symbol_name = "_do_fork",
};
/* kprobe pre_handler: called just before the probed instruction is executed */
*
* usage: insmod kretprobe_example.ko func=<func_name>
*
- * If no func_name is specified, do_fork is instrumented
+ * If no func_name is specified, _do_fork is instrumented
*
* For more information on theory of operation of kretprobes, see
* Documentation/kprobes.txt
#include <linux/limits.h>
#include <linux/sched.h>
-static char func_name[NAME_MAX] = "do_fork";
+static char func_name[NAME_MAX] = "_do_fork";
module_param_string(func, func_name, NAME_MAX, S_IRUGO);
MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the"
" function's execution time");
#include <stdint.h>
#include <stdbool.h>
#include <string.h>
-#include <getopt.h>
#include <err.h>
-#include <arpa/inet.h>
#include <openssl/bio.h>
-#include <openssl/evp.h>
#include <openssl/pem.h>
-#include <openssl/pkcs7.h>
#include <openssl/err.h>
#include <openssl/engine.h>
#include <getopt.h>
#include <err.h>
#include <arpa/inet.h>
+#include <openssl/opensslv.h>
#include <openssl/bio.h>
#include <openssl/evp.h>
#include <openssl/pem.h>
-#include <openssl/cms.h>
#include <openssl/err.h>
#include <openssl/engine.h>
+/*
+ * Use CMS if we have openssl-1.0.0 or newer available - otherwise we have to
+ * assume that it's not available and its header file is missing and that we
+ * should use PKCS#7 instead. Switching to the older PKCS#7 format restricts
+ * the options we have on specifying the X.509 certificate we want.
+ *
+ * Further, older versions of OpenSSL don't support manually adding signers to
+ * the PKCS#7 message so have to accept that we get a certificate included in
+ * the signature message. Nor do such older versions of OpenSSL support
+ * signing with anything other than SHA1 - so we're stuck with that if such is
+ * the case.
+ */
+#if OPENSSL_VERSION_NUMBER < 0x10000000L
+#define USE_PKCS7
+#endif
+#ifndef USE_PKCS7
+#include <openssl/cms.h>
+#else
+#include <openssl/pkcs7.h>
+#endif
+
struct module_signature {
uint8_t algo; /* Public-key crypto algorithm [0] */
uint8_t hash; /* Digest algorithm [0] */
struct module_signature sig_info = { .id_type = PKEY_ID_PKCS7 };
char *hash_algo = NULL;
char *private_key_name, *x509_name, *module_name, *dest_name;
- bool save_cms = false, replace_orig;
+ bool save_sig = false, replace_orig;
bool sign_only = false;
unsigned char buf[4096];
- unsigned long module_size, cms_size;
- unsigned int use_keyid = 0, use_signed_attrs = CMS_NOATTR;
+ unsigned long module_size, sig_size;
+ unsigned int use_signed_attrs;
const EVP_MD *digest_algo;
EVP_PKEY *private_key;
+#ifndef USE_PKCS7
CMS_ContentInfo *cms;
+ unsigned int use_keyid = 0;
+#else
+ PKCS7 *pkcs7;
+#endif
X509 *x509;
BIO *b, *bd = NULL, *bm;
int opt, n;
-
OpenSSL_add_all_algorithms();
ERR_load_crypto_strings();
ERR_clear_error();
key_pass = getenv("KBUILD_SIGN_PIN");
+#ifndef USE_PKCS7
+ use_signed_attrs = CMS_NOATTR;
+#else
+ use_signed_attrs = PKCS7_NOATTR;
+#endif
+
do {
opt = getopt(argc, argv, "dpk");
switch (opt) {
- case 'p': save_cms = true; break;
- case 'd': sign_only = true; save_cms = true; break;
+ case 'p': save_sig = true; break;
+ case 'd': sign_only = true; save_sig = true; break;
+#ifndef USE_PKCS7
case 'k': use_keyid = CMS_USE_KEYID; break;
+#endif
case -1: break;
default: format();
}
replace_orig = true;
}
+#ifdef USE_PKCS7
+ if (strcmp(hash_algo, "sha1") != 0) {
+ fprintf(stderr, "sign-file: %s only supports SHA1 signing\n",
+ OPENSSL_VERSION_TEXT);
+ exit(3);
+ }
+#endif
+
/* Read the private key and the X.509 cert the PKCS#7 message
* will point to.
*/
bm = BIO_new_file(module_name, "rb");
ERR(!bm, "%s", module_name);
- /* Load the CMS message from the digest buffer. */
+#ifndef USE_PKCS7
+ /* Load the signature message from the digest buffer. */
cms = CMS_sign(NULL, NULL, NULL, NULL,
CMS_NOCERTS | CMS_PARTIAL | CMS_BINARY | CMS_DETACHED | CMS_STREAM);
ERR(!cms, "CMS_sign");
ERR(!CMS_add1_signer(cms, x509, private_key, digest_algo,
CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP |
use_keyid | use_signed_attrs),
- "CMS_sign_add_signer");
+ "CMS_add1_signer");
ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
"CMS_final");
- if (save_cms) {
- char *cms_name;
+#else
+ pkcs7 = PKCS7_sign(x509, private_key, NULL, bm,
+ PKCS7_NOCERTS | PKCS7_BINARY |
+ PKCS7_DETACHED | use_signed_attrs);
+ ERR(!pkcs7, "PKCS7_sign");
+#endif
- ERR(asprintf(&cms_name, "%s.p7s", module_name) < 0, "asprintf");
- b = BIO_new_file(cms_name, "wb");
- ERR(!b, "%s", cms_name);
- ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, "%s", cms_name);
+ if (save_sig) {
+ char *sig_file_name;
+
+ ERR(asprintf(&sig_file_name, "%s.p7s", module_name) < 0,
+ "asprintf");
+ b = BIO_new_file(sig_file_name, "wb");
+ ERR(!b, "%s", sig_file_name);
+#ifndef USE_PKCS7
+ ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+ "%s", sig_file_name);
+#else
+ ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+ "%s", sig_file_name);
+#endif
BIO_free(b);
}
ERR(n < 0, "%s", module_name);
module_size = BIO_number_written(bd);
+#ifndef USE_PKCS7
ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
- cms_size = BIO_number_written(bd) - module_size;
- sig_info.sig_len = htonl(cms_size);
+#else
+ ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+#endif
+ sig_size = BIO_number_written(bd) - module_size;
+ sig_info.sig_len = htonl(sig_size);
ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
kdebug("- %u", key->serial);
key_check(key);
+ /* Throw away the key data */
+ if (key->type->destroy)
+ key->type->destroy(key);
+
security_key_free(key);
/* deal with the user's key tracking and quota */
if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
atomic_dec(&key->user->nikeys);
- /* now throw away the key memory */
- if (key->type->destroy)
- key->type->destroy(key);
-
key_user_put(key->user);
kfree(key->description);
libelf-getphdrnum \
libelf-mmap \
libnuma \
+ numa_num_possible_cpus \
libperl \
libpython \
libpython-version \
timerfd \
libdw-dwarf-unwind \
zlib \
- lzma
+ lzma \
+ get_cpuid
FEATURE_DISPLAY ?= \
dwarf \
libbfd \
libelf \
libnuma \
+ numa_num_possible_cpus \
libperl \
libpython \
libslang \
libunwind \
libdw-dwarf-unwind \
zlib \
- lzma
+ lzma \
+ get_cpuid
# Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
# If in the future we need per-feature checks/flags for features not
test-libelf-getphdrnum.bin \
test-libelf-mmap.bin \
test-libnuma.bin \
+ test-numa_num_possible_cpus.bin \
test-libperl.bin \
test-libpython.bin \
test-libpython-version.bin \
test-compile-x32.bin \
test-zlib.bin \
test-lzma.bin \
- test-bpf.bin
+ test-bpf.bin \
+ test-get_cpuid.bin
CC := $(CROSS_COMPILE)gcc -MD
PKG_CONFIG := $(CROSS_COMPILE)pkg-config
test-libnuma.bin:
$(BUILD) -lnuma
+test-numa_num_possible_cpus.bin:
+ $(BUILD) -lnuma
+
test-libunwind.bin:
$(BUILD) -lelf
test-lzma.bin:
$(BUILD) -llzma
+test-get_cpuid.bin:
+ $(BUILD)
+
test-bpf.bin:
$(BUILD)
# include "test-libnuma.c"
#undef main
+#define main main_test_numa_num_possible_cpus
+# include "test-numa_num_possible_cpus.c"
+#undef main
+
#define main main_test_timerfd
# include "test-timerfd.c"
#undef main
# include "test-lzma.c"
#undef main
+#define main main_test_get_cpuid
+# include "test-get_cpuid.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
main_test_libbfd();
main_test_backtrace();
main_test_libnuma();
+ main_test_numa_num_possible_cpus();
main_test_timerfd();
main_test_stackprotector_all();
main_test_libdw_dwarf_unwind();
main_test_zlib();
main_test_pthread_attr_setaffinity_np();
main_test_lzma();
+ main_test_get_cpuid();
return 0;
}
--- /dev/null
+#include <cpuid.h>
+
+int main(void)
+{
+ unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+ return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx);
+}
--- /dev/null
+#include <numa.h>
+
+int main(void)
+{
+ return numa_num_possible_cpus();
+}
struct format_field *field;
struct printk_map *printk;
long long val, fval;
- unsigned long addr;
+ unsigned long long addr;
char *str;
unsigned char *hex;
int print;
*/
if (!(field->flags & FIELD_IS_ARRAY) &&
field->size == pevent->long_size) {
- addr = *(unsigned long *)(data + field->offset);
+
+ /* Handle heterogeneous recording and processing
+ * architectures
+ *
+ * CASE I:
+ * Traces recorded on 32-bit devices (32-bit
+ * addressing) and processed on 64-bit devices:
+ * In this case, only 32 bits should be read.
+ *
+ * CASE II:
+ * Traces recorded on 64 bit devices and processed
+ * on 32-bit devices:
+ * In this case, 64 bits must be read.
+ */
+ addr = (pevent->long_size == 8) ?
+ *(unsigned long long *)(data + field->offset) :
+ (unsigned long long)*(unsigned int *)(data + field->offset);
+
/* Check if it matches a print format */
printk = find_printk(pevent, addr);
if (printk)
trace_seq_puts(s, printk->printk);
else
- trace_seq_printf(s, "%lx", addr);
+ trace_seq_printf(s, "%llx", addr);
break;
}
str = malloc(len + 1);
CYC packets are not requested by default.
-no_force_psb This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
- It stops the driver resetting the byte count to zero whenever
- enabling the trace (for example on context switches) which in
- turn results in no PSB being forced. However some processors
- will produce a PSB anyway.
-
- In any case, there is still a PSB when the trace is enabled for
- the first time.
-
- no_force_psb can be used to slightly decrease the trace size but
- may make it harder for the decoder to recover from errors.
-
- no_force_psb is not selected by default.
-
new snapshot option
-------------------
msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
NO_LIBNUMA := 1
else
- CFLAGS += -DHAVE_LIBNUMA_SUPPORT
- EXTLIBS += -lnuma
- $(call detected,CONFIG_NUMA)
+ ifeq ($(feature-numa_num_possible_cpus), 0)
+ msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+ NO_LIBNUMA := 1
+ else
+ CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+ EXTLIBS += -lnuma
+ $(call detected,CONFIG_NUMA)
+ endif
endif
endif
endif
ifndef NO_AUXTRACE
- $(call detected,CONFIG_AUXTRACE)
- CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+ ifeq ($(feature-get_cpuid), 0)
+ msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+ NO_AUXTRACE := 1
+ else
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+ endif
endif
# Among the variables below, these:
int ret = 0;
if (module) {
- list_for_each_entry(dso, &host_machine->dsos.head, node) {
- if (!dso->kernel)
- continue;
- if (strncmp(dso->short_name + 1, module,
- dso->short_name_len - 2) == 0)
- goto found;
+ char module_name[128];
+
+ snprintf(module_name, sizeof(module_name), "[%s]", module);
+ map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+ if (map) {
+ dso = map->dso;
+ goto found;
}
pr_debug("Failed to find module %s.\n", module);
return -ENOENT;
file_offset = page_offset;
head = data_offset - page_offset;
- if (data_size && (data_offset + data_size < file_size))
+ if (data_size == 0)
+ goto out;
+
+ if (data_offset + data_size < file_size)
file_size = data_offset + data_size;
ui_progress__init(&prog, file_size, "Processing events...");
memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
}
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+ struct perf_counts_values *vals, int cpu, bool *skip)
{
unsigned long *mask = counter->per_pkg_mask;
struct cpu_map *cpus = perf_evsel__cpus(counter);
counter->per_pkg_mask = mask;
}
+ /*
+ * we do not consider an event that has not run as a good
+ * instance to mark a package as used (skip=1). Otherwise
+ * we may run into a situation where the first CPU in a package
+ * is not running anything, yet the second is, and this function
+ * would mark the package as used after the first CPU and would
+ * not read the values from the second CPU.
+ */
+ if (!(vals->run && vals->ena))
+ return 0;
+
s = cpu_map__get_socket(cpus, cpu);
if (s < 0)
return -1;
static struct perf_counts_values zero;
bool skip = false;
- if (check_per_pkg(evsel, cpu, &skip)) {
+ if (check_per_pkg(evsel, count, cpu, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
#endif
#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
{
GElf_Ehdr gehdr;
GElf_Ehdr *ehdr;
static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
bool temp)
{
- GElf_Ehdr *ehdr;
-
kcore->elfclass = elfclass;
if (temp)
if (!gelf_newehdr(kcore->elf, elfclass))
goto out_end;
- ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
- if (!ehdr)
- goto out_end;
+ memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
return 0;
static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
u64 addr, u64 len)
{
- GElf_Phdr gphdr;
- GElf_Phdr *phdr;
-
- phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
- if (!phdr)
- return -1;
-
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R | PF_W | PF_X;
- phdr->p_offset = offset;
- phdr->p_vaddr = addr;
- phdr->p_paddr = 0;
- phdr->p_filesz = len;
- phdr->p_memsz = len;
- phdr->p_align = page_size;
-
- if (!gelf_update_phdr(kcore->elf, idx, phdr))
+ GElf_Phdr phdr = {
+ .p_type = PT_LOAD,
+ .p_flags = PF_R | PF_W | PF_X,
+ .p_offset = offset,
+ .p_vaddr = addr,
+ .p_paddr = 0,
+ .p_filesz = len,
+ .p_memsz = len,
+ .p_align = page_size,
+ };
+
+ if (!gelf_update_phdr(kcore->elf, idx, &phdr))
return -1;
return 0;
dir = opendir(procfs__mountpoint());
if (!dir)
- return -1;
+ return false;
/* Walk through the directory. */
while (ret && (d = readdir(dir)) != NULL) {
unsigned int extra_msr_offset64;
unsigned int extra_delta_offset32;
unsigned int extra_delta_offset64;
+unsigned int aperf_mperf_multiplier = 1;
int do_smi;
double bclk;
+double base_hz;
+double tsc_tweak = 1.0;
unsigned int show_pkg;
unsigned int show_core;
unsigned int show_cpu;
/* %Busy */
if (has_aperf) {
if (!skip_c0)
- outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
+ outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
else
outp += sprintf(outp, "********");
}
/* Bzy_MHz */
if (has_aperf)
outp += sprintf(outp, "%8.0f",
- 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+ 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
/* TSC_MHz */
outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
return -3;
if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
return -4;
+ t->aperf = t->aperf * aperf_mperf_multiplier;
+ t->mperf = t->mperf * aperf_mperf_multiplier;
}
if (do_smi) {
int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+
+static void
+calculate_tsc_tweak()
+{
+ unsigned long long msr;
+ unsigned int base_ratio;
+
+ get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+ base_ratio = (msr >> 8) & 0xFF;
+ base_hz = base_ratio * bclk * 1000000;
+ tsc_tweak = base_hz / tsc_hz;
+}
+
static void
dump_nhm_platform_info(void)
{
switch (model) {
case 0x3A: /* IVB */
- case 0x3E: /* IVB Xeon */
-
case 0x3C: /* HSW */
case 0x3F: /* HSX */
case 0x45: /* HSW */
return 0;
}
+unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
+{
+ if (is_knl(family, model))
+ return 1024;
+ return 1;
+}
+
#define SLM_BCLK_FREQS 5
double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
}
}
+ if (has_aperf)
+ aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+
do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
do_snb_cstates = has_snb_msrs(family, model);
do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
if (debug)
dump_cstate_pstate_config_info();
+ if (has_skl_msrs(family, model))
+ calculate_tsc_tweak();
+
return;
}
}
void print_version() {
- fprintf(stderr, "turbostat version 4.7 17-June, 2015"
+ fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
" - Len Brown <lenb@kernel.org>\n");
}
projects / linux-drm-fsl-dcu.git / commitdiff