subsystem (mmcss) inside the FlashSS (available in STiH407 SoC
family).
-- clock-names: Should be "mmc".
+- clock-names: Should be "mmc" and "icn". (NB: The latter is not compulsory)
See: Documentation/devicetree/bindings/resource-names.txt
- clocks: Phandle to the clock.
See: Documentation/devicetree/bindings/clock/clock-bindings.txt
ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
M: Kukjin Kim <kgene@kernel.org>
M: Krzysztof Kozlowski <krzk@kernel.org>
+R: Javier Martinez Canillas <javier@osg.samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
S: Maintained
F: drivers/cpufreq/intel_pstate.c
INTEL FRAMEBUFFER DRIVER (excluding 810 and 815)
-M: Maik Broemme <mbroemme@plusserver.de>
+M: Maik Broemme <mbroemme@libmpq.org>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: Documentation/fb/intelfb.txt
F: net/8021q/
VLYNQ BUS
-M: Florian Fainelli <florian@openwrt.org>
+M: Florian Fainelli <f.fainelli@gmail.com>
L: openwrt-devel@lists.openwrt.org (subscribers-only)
S: Maintained
F: drivers/vlynq/vlynq.c
VERSION = 4
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
return __cu_len;
}
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
- if (__access_ok((unsigned long)validate, len, get_fs()))
- len = __copy_tofrom_user_nocheck(to, from, len);
- return len;
-}
-
#define __copy_to_user(to, from, n) \
({ \
__chk_user_ptr(to); \
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-
extern inline long
copy_to_user(void __user *to, const void *from, long n)
{
- return __copy_tofrom_user((__force void *)to, from, n, to);
+ if (likely(__access_ok((unsigned long)to, n, get_fs())))
+ n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+ return n;
}
extern inline long
copy_from_user(void *to, const void __user *from, long n)
{
- return __copy_tofrom_user(to, (__force void *)from, n, from);
+ if (likely(__access_ok((unsigned long)from, n, get_fs())))
+ n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+ else
+ memset(to, 0, n);
+ return n;
}
extern void __do_clear_user(void);
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
+ " mov %R1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
/ {
memory {
+ device_type = "memory";
reg = <0 0x10000000>;
};
#include <dt-bindings/clock/bcm2835.h>
#include <dt-bindings/clock/bcm2835-aux.h>
#include <dt-bindings/gpio/gpio.h>
-#include "skeleton.dtsi"
/* This include file covers the common peripherals and configuration between
* bcm2835 and bcm2836 implementations, leaving the CPU configuration to
compatible = "brcm,bcm2835";
model = "BCM2835";
interrupt-parent = <&intc>;
+ #address-cells = <1>;
+ #size-cells = <1>;
chosen {
bootargs = "earlyprintk console=ttyAMA0";
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mmc0>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_0>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
bus-width = <8>;
non-removable;
};
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sd1>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_1>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_1>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
resets = <&softreset STIH407_MMC1_SOFTRESET>;
bus-width = <4>;
};
compatible = "st,st-ohci-300x";
reg = <0x9a03c00 0x100>;
interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb0>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
compatible = "st,st-ohci-300x";
reg = <0x9a83c00 0x100>;
interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb1>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
static void locomo_handler(struct irq_desc *desc)
{
- struct locomo *lchip = irq_desc_get_chip_data(desc);
+ struct locomo *lchip = irq_desc_get_handler_data(desc);
int req, i;
/* Acknowledge the parent IRQ */
* Install handler for IRQ_LOCOMO_HW.
*/
irq_set_irq_type(lchip->irq, IRQ_TYPE_EDGE_FALLING);
- irq_set_chip_data(lchip->irq, lchip);
- irq_set_chained_handler(lchip->irq, locomo_handler);
+ irq_set_chained_handler_and_data(lchip->irq, locomo_handler, lchip);
/* Install handlers for IRQ_LOCOMO_* */
for ( ; irq <= lchip->irq_base + 3; irq++) {
* specifies that S0ReadyInt and S1ReadyInt should be '1'.
*/
sa1111_writel(0, irqbase + SA1111_INTPOL0);
- sa1111_writel(SA1111_IRQMASK_HI(IRQ_S0_READY_NINT) |
- SA1111_IRQMASK_HI(IRQ_S1_READY_NINT),
+ sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) |
+ BIT(IRQ_S1_READY_NINT & 31),
irqbase + SA1111_INTPOL1);
/* clear all IRQs */
if (sachip->irq != NO_IRQ) {
ret = sa1111_setup_irq(sachip, pd->irq_base);
if (ret)
- goto err_unmap;
+ goto err_clk;
}
#ifdef CONFIG_ARCH_SA1100
return 0;
+ err_clk:
+ clk_disable(sachip->clk);
err_unmap:
iounmap(sachip->base);
err_clk_unprep:
#ifdef CONFIG_PM
-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags;
unsigned int val;
* restored by their respective drivers, and must be called
* via LDM after this function.
*/
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags, id;
void __iomem *base;
id = sa1111_readl(sachip->base + SA1111_SKID);
if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
__sa1111_remove(sachip);
- platform_set_drvdata(dev, NULL);
+ dev_set_drvdata(dev, NULL);
kfree(save);
return 0;
}
}
#else
-#define sa1111_suspend NULL
-#define sa1111_resume NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq NULL
#endif
static int sa1111_probe(struct platform_device *pdev)
return -EINVAL;
irq = platform_get_irq(pdev, 0);
if (irq < 0)
- return -ENXIO;
+ return irq;
return __sa1111_probe(&pdev->dev, mem, irq);
}
return 0;
}
+static struct dev_pm_ops sa1111_pm_ops = {
+ .suspend_noirq = sa1111_suspend_noirq,
+ .resume_noirq = sa1111_resume_noirq,
+};
+
/*
* Not sure if this should be on the system bus or not yet.
* We really want some way to register a system device at
static struct platform_driver sa1111_device_driver = {
.probe = sa1111_probe,
.remove = sa1111_remove,
- .suspend = sa1111_suspend,
- .resume = sa1111_resume,
.driver = {
.name = "sa1111",
+ .pm = &sa1111_pm_ops,
},
};
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_USB_DWC3=y
+CONFIG_NOP_USB_XCEIV=y
CONFIG_KEYSTONE_USB_PHY=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_DMA_BCM2835=y
CONFIG_DMA_OMAP=y
CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_VDMA=y
+CONFIG_XILINX_DMA=y
CONFIG_DMA_SUN6I=y
CONFIG_STAGING=y
CONFIG_SENSORS_ISL29018=y
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_CACHE_MASK (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2))
/*
#define PMD_SECT_WT (_AT(pmdval_t, 2) << 2) /* normal inner write-through */
#define PMD_SECT_WB (_AT(pmdval_t, 3) << 2) /* normal inner write-back */
#define PMD_SECT_WBWA (_AT(pmdval_t, 7) << 2) /* normal inner write-alloc */
+#define PMD_SECT_CACHE_MASK (_AT(pmdval_t, 7) << 2)
/*
* + Level 3 descriptor (PTE)
{
int i;
- kvm_free_stage2_pgd(kvm);
-
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
- hyp_idmap_start < kern_hyp_va(~0UL)) {
+ hyp_idmap_start < kern_hyp_va(~0UL) &&
+ hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
+ kvm_free_stage2_pgd(kvm);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
return -ENOMEM;
}
+ /*
+ * Clear the OF_POPULATED flag set in of_irq_init so that
+ * later the Exynos PMU platform device won't be skipped.
+ */
+ of_node_clear_flag(node, OF_POPULATED);
+
return 0;
}
// no D+ pullup; lubbock can't connect/disconnect in software
};
+static void lubbock_init_pcmcia(void)
+{
+ struct clk *clk;
+
+ /* Add an alias for the SA1111 PCMCIA clock */
+ clk = clk_get_sys("pxa2xx-pcmcia", NULL);
+ if (!IS_ERR(clk)) {
+ clkdev_create(clk, NULL, "1800");
+ clk_put(clk);
+ }
+}
+
static struct resource sa1111_resources[] = {
[0] = {
.start = 0x10000000,
pxa_set_btuart_info(NULL);
pxa_set_stuart_info(NULL);
+ lubbock_init_pcmcia();
+
clk_add_alias("SA1111_CLK", NULL, "GPIO11_CLK", NULL);
pxa_set_udc_info(&udc_info);
pxa_set_fb_info(NULL, &sharp_lm8v31);
#define REGULATOR_IRQ_MASK BIT(2) /* IRQ2, active low */
-static void __iomem *irqc;
-
-static const u8 da9063_mask_regs[] = {
- DA9063_REG_IRQ_MASK_A,
- DA9063_REG_IRQ_MASK_B,
- DA9063_REG_IRQ_MASK_C,
- DA9063_REG_IRQ_MASK_D,
-};
-
-/* DA9210 System Control and Event Registers */
+/* start of DA9210 System Control and Event Registers */
#define DA9210_REG_MASK_A 0x54
-#define DA9210_REG_MASK_B 0x55
-
-static const u8 da9210_mask_regs[] = {
- DA9210_REG_MASK_A,
- DA9210_REG_MASK_B,
-};
-
-static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
- unsigned int nregs)
-{
- unsigned int i;
- dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+static void __iomem *irqc;
- for (i = 0; i < nregs; i++) {
- int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
- if (error) {
- dev_err(&client->dev, "i2c error %d\n", error);
- return;
- }
- }
-}
+/* first byte sets the memory pointer, following are consecutive reg values */
+static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff };
+static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff };
+
+static struct i2c_msg da9xxx_msgs[2] = {
+ {
+ .addr = 0x58,
+ .len = ARRAY_SIZE(da9063_irq_clr),
+ .buf = da9063_irq_clr,
+ }, {
+ .addr = 0x68,
+ .len = ARRAY_SIZE(da9210_irq_clr),
+ .buf = da9210_irq_clr,
+ },
+};
static int regulator_quirk_notify(struct notifier_block *nb,
unsigned long action, void *data)
client = to_i2c_client(dev);
dev_dbg(dev, "Detected %s\n", client->name);
- if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
- da9xxx_mask_irqs(client, da9063_mask_regs,
- ARRAY_SIZE(da9063_mask_regs));
- else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
- da9xxx_mask_irqs(client, da9210_mask_regs,
- ARRAY_SIZE(da9210_mask_regs));
+ if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) ||
+ (client->addr == 0x68 && !strcmp(client->name, "da9210"))) {
+ int ret;
+
+ dev_info(&client->dev, "clearing da9063/da9210 interrupts\n");
+ ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs));
+ if (ret != ARRAY_SIZE(da9xxx_msgs))
+ dev_err(&client->dev, "i2c error %d\n", ret);
+ }
mon = ioread32(irqc + IRQC_MONITOR);
if (mon & REGULATOR_IRQ_MASK)
initial_pmd_value = pmd;
- pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE;
+ pmd &= PMD_SECT_CACHE_MASK;
for (i = 0; i < ARRAY_SIZE(cache_policies); i++)
if (cache_policies[i].pmd == pmd) {
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
- /* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, cpu) = cpu;
-
info.mfn = virt_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
+ int cpu;
if (!xen_domain())
return 0;
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, 0) = 0;
+ for_each_possible_cpu(cpu)
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
/* Local timer */
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
timer0: timer0@ffc03000 {
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>;
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
};
xtal: xtal-clk {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 0 0xff01>, /* Secure Phys IRQ */
- <1 13 0xff01>, /* Non-secure Phys IRQ */
- <1 14 0xff01>, /* Virt IRQ */
- <1 15 0xff01>; /* Hyp IRQ */
+ interrupts = <1 0 0xff08>, /* Secure Phys IRQ */
+ <1 13 0xff08>, /* Non-secure Phys IRQ */
+ <1 14 0xff08>, /* Virt IRQ */
+ <1 15 0xff08>; /* Hyp IRQ */
clock-frequency = <50000000>;
};
--- /dev/null
+../../../../arm/boot/dts/bcm2835-rpi.dtsi
\ No newline at end of file
/dts-v1/;
#include "bcm2837.dtsi"
-#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi"
-#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi"
+#include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
/ {
compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
-#include "../../../../arm/boot/dts/bcm283x.dtsi"
+#include "bcm283x.dtsi"
/ {
compatible = "brcm,bcm2836";
--- /dev/null
+../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
\ No newline at end of file
--- /dev/null
+../../../../arm/boot/dts/bcm283x.dtsi
\ No newline at end of file
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>;
+ IRQ_TYPE_LEVEL_LOW)>;
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 0xff08>,
+ <1 14 0xff08>,
+ <1 11 0xff08>,
+ <1 10 0xff08>;
};
pmu_system_controller: system-controller@105c0000 {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x1>, /* Physical Secure PPI */
- <1 14 0x1>, /* Physical Non-Secure PPI */
- <1 11 0x1>, /* Virtual PPI */
- <1 10 0x1>; /* Hypervisor PPI */
+ interrupts = <1 13 0xf08>, /* Physical Secure PPI */
+ <1 14 0xf08>, /* Physical Non-Secure PPI */
+ <1 11 0xf08>, /* Virtual PPI */
+ <1 10 0xf08>; /* Hypervisor PPI */
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */
- <1 14 0x8>, /* Physical Non-Secure PPI, active-low */
- <1 11 0x8>, /* Virtual PPI, active-low */
- <1 10 0x8>; /* Hypervisor PPI, active-low */
+ interrupts = <1 13 4>, /* Physical Secure PPI, active-low */
+ <1 14 4>, /* Physical Non-Secure PPI, active-low */
+ <1 11 4>, /* Virtual PPI, active-low */
+ <1 10 4>; /* Hypervisor PPI, active-low */
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>;
+ interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
};
odmi: odmi@300000 {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
soc {
timer {
compatible = "arm,armv8-timer";
interrupt-parent = <&gic>;
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
amba_apu {
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
extern __kernel_size_t copy_to_user(void __user *to, const void *from,
__kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
__kernel_size_t n);
static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
{
return __copy_user(to, (const void __force *)from, n);
}
+static inline __kernel_size_t copy_from_user(void *to,
+ const void __user *from,
+ __kernel_size_t n)
+{
+ size_t res = ___copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
/*
* Userspace access stuff.
*/
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
EXPORT_SYMBOL(copy_to_user);
EXPORT_SYMBOL(__copy_user);
EXPORT_SYMBOL(strncpy_from_user);
*/
.text
.align 1
- .global copy_from_user
- .type copy_from_user, @function
-copy_from_user:
+ .global ___copy_from_user
+ .type ___copy_from_user, @function
+___copy_from_user:
branch_if_kernel r8, __copy_user
ret_if_privileged r8, r11, r10, r10
rjmp __copy_user
- .size copy_from_user, . - copy_from_user
+ .size ___copy_from_user, . - ___copy_from_user
.global copy_to_user
.type copy_to_user, @function
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n))) {
memcpy(to, (const void __force *)from, n);
- else
- return n;
- return 0;
+ return 0;
+ }
+ memset(to, 0, n);
+ return n;
}
static inline unsigned long __must_check
extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
extern unsigned long __do_clear_user(void __user *to, unsigned long n);
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- return __copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __do_clear_user(to, n);
- return n;
-}
-
static inline long
__strncpy_from_user(char *dst, const char __user *src, long count)
{
else if (n == 24)
__asm_copy_from_user_24(to, from, ret);
else
- ret = __generic_copy_from_user(to, from, n);
+ ret = __copy_user_zeroing(to, from, n);
return ret;
}
else if (n == 24)
__asm_copy_to_user_24(to, from, ret);
else
- ret = __generic_copy_to_user(to, from, n);
+ ret = __copy_user(to, from, n);
return ret;
}
else if (n == 24)
__asm_clear_24(to, ret);
else
- ret = __generic_clear_user(to, n);
+ ret = __do_clear_user(to, n);
return ret;
}
-#define clear_user(to, n) \
- (__builtin_constant_p(n) ? \
- __constant_clear_user(to, n) : \
- __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_clear_user(to, n);
+ else
+ return __do_clear_user(to, n);
+}
-#define copy_from_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user(to, from, n) : \
- __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+ memset(to, 0, n);
+ return n;
+ }
+ if (__builtin_constant_p(n))
+ return __constant_copy_from_user(to, from, n);
+ else
+ return __copy_user_zeroing(to, from, n);
+}
-#define copy_to_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user(to, from, n) : \
- __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_copy_to_user(to, from, n);
+ else
+ return __copy_user(to, from, n);
+}
/* We let the __ versions of copy_from/to_user inline, because they're often
* used in fast paths and have only a small space overhead.
extern long __memset_user(void *dst, unsigned long count);
extern long __memcpy_user(void *dst, const void *src, unsigned long count);
-#define clear_user(dst,count) __memset_user(____force(dst), (count))
+#define __clear_user(dst,count) __memset_user(____force(dst), (count))
#define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n))
#define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n))
#else
-#define clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
#define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0)
#define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0)
#endif
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+ if (likely(__access_ok(to, n)))
+ n = __clear_user(to, n);
+ return n;
+}
static inline unsigned long __must_check
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
long res = __strnlen_user(src, n);
- /* return from strnlen can't be zero -- that would be rubbish. */
+ if (unlikely(!res))
+ return -EFAULT;
if (res > n) {
copy_from_user(dst, src, n);
__cu_len; \
})
-#define copy_from_user(to, from, n) \
-({ \
- void *__cu_to = (to); \
- const void __user *__cu_from = (from); \
- long __cu_len = (n); \
- \
- __chk_user_ptr(__cu_from); \
- if (__access_ok(__cu_from, __cu_len, get_fs())) { \
- check_object_size(__cu_to, __cu_len, false); \
- __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \
- } \
- __cu_len; \
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ check_object_size(to, n, false);
+ if (likely(__access_ok(from, n, get_fs())))
+ n = __copy_user((__force void __user *) to, from, n);
+ else
+ memset(to, 0, n);
+ return n;
+}
#define __copy_in_user(to, from, size) __copy_user((to), (from), (size))
#define __get_user_nocheck(x, ptr, size) \
({ \
long __gu_err = 0; \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
might_fault(); \
__get_user_size(__gu_val, (ptr), (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n)))
return __copy_user_zeroing(to, from, n);
+ memset(to, 0, n);
return n;
}
#define __get_user(x, ptr) \
({ \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
/*unsigned long __gu_ptr = (unsigned long)(ptr);*/ \
long __gu_err; \
switch (sizeof(*(ptr))) { \
static inline long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
#define __copy_to_user(to, from, n) \
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/thread_info.h>
+#include <linux/string.h>
#include <asm/asm-eva.h>
/*
__cu_len = __invoke_copy_from_user(__cu_to, \
__cu_from, \
__cu_len); \
+ } else { \
+ memset(__cu_to, 0, __cu_len); \
} \
} \
__cu_len; \
"2:\n" \
" .section .fixup,\"ax\"\n" \
"3:\n\t" \
+ " mov 0,%1\n" \
" mov %3,%0\n" \
" jmp 2b\n" \
" .previous\n" \
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
unsigned long
__generic_copy_to_user(void *to, const void *from, unsigned long n)
{
if (access_ok(VERIFY_READ, from, n))
__copy_user_zeroing(to, from, n);
+ else
+ memset(to, 0, n);
return n;
}
static inline long copy_from_user(void *to, const void __user *from,
unsigned long n)
{
- if (!access_ok(VERIFY_READ, from, n))
- return n;
- return __copy_from_user(to, from, n);
+ unsigned long res = n;
+ if (access_ok(VERIFY_READ, from, n))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to, const void *from,
#define __get_user_unknown(val, size, ptr, err) do { \
err = 0; \
- if (copy_from_user(&(val), ptr, size)) { \
+ if (__copy_from_user(&(val), ptr, size)) { \
err = -EFAULT; \
} \
} while (0)
({ \
long __gu_err = -EFAULT; \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
(x) = (__force __typeof__(x))__gu_val; \
__gu_err; \
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
- return n;
+ unsigned long res = n;
+
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_tofrom_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ n = __copy_tofrom_user(to, from, n);
return n;
}
static inline __must_check unsigned long
clear_user(void *addr, unsigned long size)
{
-
- if (access_ok(VERIFY_WRITE, addr, size))
- return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, addr, size)))
+ size = __clear_user(addr, size);
return size;
}
#include <asm-generic/uaccess-unaligned.h>
#include <linux/bug.h>
+#include <linux/string.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
unsigned long n)
{
int sz = __compiletime_object_size(to);
- int ret = -EFAULT;
+ unsigned long ret = n;
if (likely(sz == -1 || sz >= n))
ret = __copy_from_user(to, from, n);
else
__bad_copy_user();
+ if (unlikely(ret))
+ memset(to + (n - ret), 0, ret);
return ret;
}
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
#include <linux/jump_label.h>
-#define NUM_CPU_FTR_KEYS 64
+#define NUM_CPU_FTR_KEYS BITS_PER_LONG
extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
static inline unsigned long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n)) {
+ if (likely(access_ok(VERIFY_READ, from, n))) {
check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
}
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- check_object_size(to, n - over, false);
- return __copy_tofrom_user((__force void __user *)to, from,
- n - over) + over;
- }
+ memset(to, 0, n);
return n;
}
static inline unsigned long copy_to_user(void __user *to,
const void *from, unsigned long n)
{
- unsigned long over;
-
if (access_ok(VERIFY_WRITE, to, n)) {
check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force void __user *)from, n);
}
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- check_object_size(from, n - over, true);
- return __copy_tofrom_user(to, (__force void __user *)from,
- n - over) + over;
- }
return n;
}
might_fault();
if (likely(access_ok(VERIFY_WRITE, addr, size)))
return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
return size;
}
*
* r13 - PACA
* cr3 - gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
_GLOBAL(pnv_wakeup_tb_loss)
ld r1,PACAR1(r13)
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
* If waking up from sleep, subcore state is not lost. Hence
* skip subcore state restore
*/
- bne cr4,subcore_state_restored
+ blt cr4,subcore_state_restored
/* Restore per-subcore state */
ld r4,_SDR1(r1)
* If waking up from sleep, per core state is not lost, skip to
* clear_lock.
*/
- bne cr4,clear_lock
+ blt cr4,clear_lock
/*
* First thread in the core to wake up and its waking up with
* If waking up from sleep, hypervisor state is not lost. Hence
* skip hypervisor state restore.
*/
- bne cr4,hypervisor_state_restored
+ blt cr4,hypervisor_state_restored
/* Waking up from winkle */
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
return 0;
}
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
}
}
- pnv_ioda_free_pe(pe);
+ /*
+ * The PE for root bus can be removed because of hotplug in EEH
+ * recovery for fenced PHB error. We need to mark the PE dead so
+ * that it can be populated again in PCI hot add path. The PE
+ * shouldn't be destroyed as it's the global reserved resource.
+ */
+ if (phb->ioda.root_pe_populated &&
+ phb->ioda.root_pe_idx == pe->pe_number)
+ phb->ioda.root_pe_populated = false;
+ else
+ pnv_ioda_free_pe(pe);
}
static void pnv_pci_release_device(struct pci_dev *pdev)
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return;
+ /*
+ * PCI hotplug can happen as part of EEH error recovery. The @pdn
+ * isn't removed and added afterwards in this scenario. We should
+ * set the PE number in @pdn to an invalid one. Otherwise, the PE's
+ * device count is decreased on removing devices while failing to
+ * be increased on adding devices. It leads to unbalanced PE's device
+ * count and eventually make normal PCI hotplug path broken.
+ */
pe = &phb->ioda.pe_array[pdn->pe_number];
+ pdn->pe_number = IODA_INVALID_PE;
+
WARN_ON(--pe->device_count < 0);
if (pe->device_count == 0)
pnv_ioda_release_pe(pe);
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: { \
- unsigned char __x; \
+ unsigned char __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
- unsigned short __x; \
+ unsigned short __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
- unsigned int __x; \
+ unsigned int __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
- unsigned long long __x; \
+ unsigned long long __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
return -EINVAL;
current->thread.fpu.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
- convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+ (freg_t *) fpu->fprs);
else
- memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
- convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp((freg_t *) fpu->fprs,
+ (__vector128 *) vcpu->run->s.regs.vrs);
else
- memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = current->thread.fpu.fpc;
return 0;
}
/* Validity 0x0044 will be checked by SIE */
if (rc)
goto unpin;
- scb_s->gvrd = hpa;
+ scb_s->riccbd = hpa;
}
return 0;
unpin:
__get_user_asm(val, "lw", ptr); \
break; \
case 8: \
- if ((copy_from_user((void *)&val, ptr, 8)) == 0) \
+ if (__copy_from_user((void *)&val, ptr, 8) == 0) \
__gu_err = 0; \
else \
__gu_err = -EFAULT; \
\
if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \
__get_user_common((x), size, __gu_ptr); \
+ else \
+ (x) = 0; \
\
__gu_err; \
})
"2:\n" \
".section .fixup,\"ax\"\n" \
"3:li %0, %4\n" \
+ "li %1, 0\n" \
"j 2b\n" \
".previous\n" \
".section __ex_table,\"a\"\n" \
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
+ unsigned long res = len;
- if (access_ok(VERIFY_READ, from, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_READ, from, len)))
+ res = __copy_tofrom_user(to, from, len);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
- return len;
+ if (unlikely(res))
+ memset(to + (len - res), 0, res);
+
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_WRITE, to, len)))
+ len = __copy_tofrom_user(to, from, len);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
return len;
}
-#define __copy_from_user(to, from, len) \
- __copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+ unsigned long left = __copy_tofrom_user(to, from, len);
+ if (unlikely(left))
+ memset(to + (len - left), 0, left);
+ return left;
+}
#define __copy_to_user(to, from, len) \
__copy_tofrom_user((to), (from), (len))
static inline unsigned long
__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
{
- return __copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
-#define __copy_in_user(to, from, len) __copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len)
static inline unsigned long
copy_in_user(void *to, const void *from, unsigned long len)
{
if (access_ok(VERIFY_READ, from, len) &&
access_ok(VERFITY_WRITE, to, len))
- return copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
/*
__kernel_size_t __copy_size = (__kernel_size_t) n;
if (__copy_size && __access_ok(__copy_from, __copy_size))
- return __copy_user(to, from, __copy_size);
+ __copy_size = __copy_user(to, from, __copy_size);
+
+ if (unlikely(__copy_size))
+ memset(to + (n - __copy_size), 0, __copy_size);
return __copy_size;
}
#define __get_user_size(x,ptr,size,retval) \
do { \
retval = 0; \
+ x = 0; \
switch (size) { \
case 1: \
retval = __get_user_asm_b((void *)&x, \
if (n && __access_ok((unsigned long) from, n)) {
check_object_size(to, n, false);
return __copy_user((__force void __user *) to, from, n);
- } else
+ } else {
+ memset(to, 0, n);
return n;
+ }
}
static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
return status;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle, bool is64)
-{
- struct efi_info *efi = &boot_params->efi_info;
- unsigned long map_sz, key, desc_size;
- efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+ struct boot_params *boot_params;
+ struct efi_info *efi;
struct setup_data *e820ext;
- const char *signature;
__u32 e820ext_size;
- __u32 nr_desc, prev_nr_desc;
- efi_status_t status;
- __u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
-
- nr_desc = 0;
- e820ext = NULL;
- e820ext_size = 0;
-
-get_map:
- status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
- &desc_version, &key);
-
- if (status != EFI_SUCCESS)
- return status;
-
- prev_nr_desc = nr_desc;
- nr_desc = map_sz / desc_size;
- if (nr_desc > prev_nr_desc &&
- nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
- u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
- status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ bool is64;
+};
- efi_call_early(free_pool, mem_map);
- goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ static bool first = true;
+ const char *signature;
+ __u32 nr_desc;
+ efi_status_t status;
+ struct exit_boot_struct *p = priv;
+
+ if (first) {
+ nr_desc = *map->buff_size / *map->desc_size;
+ if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc -
+ ARRAY_SIZE(p->boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &p->e820ext,
+ &p->e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+ }
+ first = false;
}
- signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
- memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+ signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = map_sz;
+ p->efi->efi_systab = (unsigned long)sys_table_arg;
+ p->efi->efi_memdesc_size = *map->desc_size;
+ p->efi->efi_memdesc_version = *map->desc_ver;
+ p->efi->efi_memmap = (unsigned long)*map->map;
+ p->efi->efi_memmap_size = *map->map_size;
#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+ p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+ p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
#endif
+ return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+ void *handle, bool is64)
+{
+ unsigned long map_sz, key, desc_size, buff_size;
+ efi_memory_desc_t *mem_map;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
+ efi_status_t status;
+ __u32 desc_version;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &mem_map;
+ map.map_size = &map_sz;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_version;
+ map.key_ptr = &key;
+ map.buff_size = &buff_size;
+ priv.boot_params = boot_params;
+ priv.efi = &boot_params->efi_info;
+ priv.e820ext = NULL;
+ priv.e820ext_size = 0;
+ priv.is64 = is64;
+
/* Might as well exit boot services now */
- status = efi_call_early(exit_boot_services, handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
-
- called_exit = true;
- efi_call_early(free_pool, mem_map);
- goto get_map;
- }
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
+ if (status != EFI_SUCCESS)
+ return status;
+ e820ext = priv.e820ext;
+ e820ext_size = priv.e820ext_size;
/* Historic? */
boot_params->alt_mem_k = 32 * 1024;
return status;
return EFI_SUCCESS;
-
-free_mem_map:
- efi_call_early(free_pool, mem_map);
- return status;
}
/*
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
#define COUNTER_SHIFT 16
+static HLIST_HEAD(uncore_unused_list);
+
struct amd_uncore {
int id;
int refcnt;
cpumask_t *active_mask;
struct pmu *pmu;
struct perf_event *events[MAX_COUNTERS];
- struct amd_uncore *free_when_cpu_online;
+ struct hlist_node node;
};
static struct amd_uncore * __percpu *amd_uncore_nb;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
uncore_nb->pmu = &amd_nb_pmu;
+ uncore_nb->id = -1;
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
+ uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
}
continue;
if (this->id == that->id) {
- that->free_when_cpu_online = this;
+ hlist_add_head(&this->node, &uncore_unused_list);
this = that;
break;
}
return 0;
}
+static void uncore_clean_online(void)
+{
+ struct amd_uncore *uncore;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+ hlist_del(&uncore->node);
+ kfree(uncore);
+ }
+}
+
static void uncore_online(unsigned int cpu,
struct amd_uncore * __percpu *uncores)
{
struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
- kfree(uncore->free_when_cpu_online);
- uncore->free_when_cpu_online = NULL;
+ uncore_clean_online();
if (cpu == uncore->cpu)
cpumask_set_cpu(cpu, uncore->active_mask);
struct bts_ctx {
struct perf_output_handle handle;
struct debug_store ds_back;
- int started;
+ int state;
+};
+
+/* BTS context states: */
+enum {
+ /* no ongoing AUX transactions */
+ BTS_STATE_STOPPED = 0,
+ /* AUX transaction is on, BTS tracing is disabled */
+ BTS_STATE_INACTIVE,
+ /* AUX transaction is on, BTS tracing is running */
+ BTS_STATE_ACTIVE,
};
static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
static int
bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ * - is set when bts::handle::event is valid, that is, between
+ * perf_aux_output_begin() and perf_aux_output_end();
+ * - is zero otherwise;
+ * - is ordered against bts::handle::event with a compiler barrier.
+ */
+
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
/*
* local barrier to make sure that ds configuration made it
- * before we enable BTS
+ * before we enable BTS and bts::state goes ACTIVE
*/
wmb();
+ /* INACTIVE/STOPPED -> ACTIVE */
+ WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
intel_pmu_enable_bts(config);
}
__bts_event_start(event);
- /* PMI handler: this counter is running and likely generating PMIs */
- ACCESS_ONCE(bts->started) = 1;
-
return;
fail_end_stop:
event->hw.state = PERF_HES_STOPPED;
}
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
{
+ struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+ /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+ WRITE_ONCE(bts->state, state);
+
/*
* No extra synchronization is mandated by the documentation to have
* BTS data stores globally visible.
*/
intel_pmu_disable_bts();
-
- if (event->hw.state & PERF_HES_STOPPED)
- return;
-
- ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
}
static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *buf = NULL;
+ int state = READ_ONCE(bts->state);
- /* PMI handler: don't restart this counter */
- ACCESS_ONCE(bts->started) = 0;
+ if (state == BTS_STATE_ACTIVE)
+ __bts_event_stop(event, BTS_STATE_STOPPED);
- __bts_event_stop(event);
+ if (state != BTS_STATE_STOPPED)
+ buf = perf_get_aux(&bts->handle);
+
+ event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
+
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
}
void intel_bts_enable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ int state = READ_ONCE(bts->state);
+
+ /*
+ * Here we transition from INACTIVE to ACTIVE;
+ * if we instead are STOPPED from the interrupt handler,
+ * stay that way. Can't be ACTIVE here though.
+ */
+ if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+ return;
+
+ if (state == BTS_STATE_STOPPED)
+ return;
- if (bts->handle.event && bts->started)
+ if (bts->handle.event)
__bts_event_start(bts->handle.event);
}
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ /*
+ * Here we transition from ACTIVE to INACTIVE;
+ * do nothing for STOPPED or INACTIVE.
+ */
+ if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+ return;
+
if (bts->handle.event)
- __bts_event_stop(bts->handle.event);
+ __bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
}
static int
return 0;
head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
- if (WARN_ON_ONCE(head != local_read(&buf->head)))
- return -EINVAL;
phys = &buf->buf[buf->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
int intel_bts_interrupt(void)
{
+ struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct perf_event *event = bts->handle.event;
struct bts_buffer *buf;
s64 old_head;
- int err;
+ int err = -ENOSPC, handled = 0;
- if (!event || !bts->started)
- return 0;
+ /*
+ * The only surefire way of knowing if this NMI is ours is by checking
+ * the write ptr against the PMI threshold.
+ */
+ if (ds->bts_index >= ds->bts_interrupt_threshold)
+ handled = 1;
+
+ /*
+ * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+ * so we can only be INACTIVE or STOPPED
+ */
+ if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+ return handled;
buf = perf_get_aux(&bts->handle);
+ if (!buf)
+ return handled;
+
/*
* Skip snapshot counters: they don't use the interrupt, but
* there's no other way of telling, because the pointer will
* keep moving
*/
- if (!buf || buf->snapshot)
+ if (buf->snapshot)
return 0;
old_head = local_read(&buf->head);
/* no new data */
if (old_head == local_read(&buf->head))
- return 0;
+ return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
buf = perf_aux_output_begin(&bts->handle, event);
- if (!buf)
- return 1;
+ if (buf)
+ err = bts_buffer_reset(buf, &bts->handle);
+
+ if (err) {
+ WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
- err = bts_buffer_reset(buf, &bts->handle);
- if (err)
- perf_aux_output_end(&bts->handle, 0, false);
+ if (buf) {
+ /*
+ * BTS_STATE_STOPPED should be visible before
+ * cleared handle::event
+ */
+ barrier();
+ perf_aux_output_end(&bts->handle, 0, false);
+ }
+ }
return 1;
}
* disabled state if called consecutively.
*
* During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
*/
static void __intel_pmu_disable_all(void)
{
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
- else
- intel_bts_disable_local();
intel_pmu_pebs_disable_all();
}
return;
intel_pmu_enable_bts(event->hw.config);
- } else
- intel_bts_enable_local();
+ }
}
static void intel_pmu_enable_all(int added)
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
if (cpuc->enabled)
__intel_pmu_enable_all(0, true);
+ intel_bts_enable_local();
/*
* Only unmask the NMI after the overflow counters
static void init_mbm_sample(u32 rmid, u32 evt_type);
static void __intel_mbm_event_count(void *info);
+static bool is_cqm_event(int e)
+{
+ return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
static bool is_mbm_event(int e)
{
return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
(event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
return -EINVAL;
+ if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+ (is_mbm_event(event->attr.config) && !mbm_enabled))
+ return -EINVAL;
+
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
struct pebs_record_nhm *p = at;
u64 pebs_status;
- /* PEBS v3 has accurate status bits */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+ /* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&p->status,
- MAX_PEBS_EVENTS)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status,
+ x86_pmu.max_pebs_events)
counts[bit]++;
continue;
}
- pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
/*
* On some CPUs the PEBS status can be zero when PEBS is
* racing with clearing of GLOBAL_STATUS.
continue;
event = cpuc->events[bit];
- WARN_ON_ONCE(!event);
- WARN_ON_ONCE(!event->attr.precise_ip);
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
/* log dropped samples number */
if (error[bit])
event->hw.addr_filters = NULL;
}
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+ return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
static int pt_event_addr_filters_validate(struct list_head *filters)
{
struct perf_addr_filter *filter;
list_for_each_entry(filter, filters, entry) {
/* PT doesn't support single address triggers */
- if (!filter->range)
+ if (!filter->range || !filter->size)
return -EOPNOTSUPP;
- if (!filter->inode && !kernel_ip(filter->offset))
- return -EINVAL;
+ if (!filter->inode) {
+ if (!valid_kernel_ip(filter->offset))
+ return -EINVAL;
+
+ if (!valid_kernel_ip(filter->offset + filter->size))
+ return -EINVAL;
+ }
if (++range > pt_cap_get(PT_CAP_num_address_ranges))
return -EOPNOTSUPP;
} else {
/* apply the offset */
msr_a = filter->offset + offs[range];
- msr_b = filter->size + msr_a;
+ msr_b = filter->size + msr_a - 1;
}
filters->filter[range].msr_a = msr_a;
#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
- _ASM_EXTABLE_EX(1b, 2b) \
+ ".section .fixup,\"ax\"\n" \
+ "3:xor"itype" %"rtype"0,%"rtype"0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_EX(1b, 3b) \
: ltype(x) : "m" (__m(addr)))
#define __put_user_nocheck(x, ptr, size) \
return -EINVAL;
}
- num_processors++;
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
+
disabled_cpus++;
return -ENOSPC;
}
+ num_processors++;
+
/*
* Validate version
*/
*/
static u8 *container;
static size_t container_size;
+static bool ucode_builtin;
static u32 ucode_new_rev;
static u8 amd_ucode_patch[PATCH_MAX_SIZE];
void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
+ bool *builtin;
void **data;
size_t *size;
#ifdef CONFIG_X86_32
data = (void **)__pa_nodebug(&ucode_cpio.data);
size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+ builtin = (bool *)__pa_nodebug(&ucode_builtin);
#else
data = &ucode_cpio.data;
size = &ucode_cpio.size;
+ builtin = &ucode_builtin;
#endif
- if (!load_builtin_amd_microcode(&cp, family))
+ *builtin = load_builtin_amd_microcode(&cp, family);
+ if (!*builtin)
cp = find_ucode_in_initrd();
if (!(cp.data && cp.size))
return;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
container = cont_va;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+ x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
{
bool new_val, old_val;
struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
union kvm_ioapic_redirect_entry *e;
e = &ioapic->redirtbl[RTC_GSI];
return;
new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
- old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ old_val = test_bit(vcpu->vcpu_id, dest_map->map);
if (new_val == old_val)
return;
if (new_val) {
- __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
ioapic->rtc_status.pending_eoi++;
} else {
- __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __clear_bit(vcpu->vcpu_id, dest_map->map);
ioapic->rtc_status.pending_eoi--;
rtc_status_pending_eoi_check_valid(ioapic);
}
static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
- [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
- [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+ [2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+ [3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_lapic_hv_timer_in_use(vcpu) &&
- kvm_x86_ops->set_hv_timer(vcpu,
- kvm_get_lapic_tscdeadline_msr(vcpu)))
- kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
/*
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
/*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
*
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
*/
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
{
dev->non_compliant_bars = 1;
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
return blkcipher_walk_done(desc, walk, -EINVAL);
}
+ bsize = min(walk->walk_blocksize, n);
+
walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
BLKCIPHER_WALK_DIFF);
if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
}
}
- bsize = min(walk->walk_blocksize, n);
n = scatterwalk_clamp(&walk->in, n);
n = scatterwalk_clamp(&walk->out, n);
static int cryptd_hash_import(struct ahash_request *req, const void *in)
{
- struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct shash_desc *desc = cryptd_shash_desc(req);
+
+ desc->tfm = ctx->child;
+ desc->flags = req->base.flags;
- return crypto_shash_import(&rctx->desc, in);
+ return crypto_shash_import(desc, in);
}
static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
/*
* echainiv: Encrypted Chain IV Generator
*
- * This generator generates an IV based on a sequence number by xoring it
- * with a salt and then encrypting it with the same key as used to encrypt
+ * This generator generates an IV based on a sequence number by multiplying
+ * it with a salt and then encrypting it with the same key as used to encrypt
* the plain text. This algorithm requires that the block size be equal
* to the IV size. It is mainly useful for CBC.
*
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
-#include <linux/mm.h>
#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/string.h>
-#define MAX_IV_SIZE 16
-
-static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
-
-/* We don't care if we get preempted and read/write IVs from the next CPU. */
-static void echainiv_read_iv(u8 *dst, unsigned size)
-{
- u32 *a = (u32 *)dst;
- u32 __percpu *b = echainiv_iv;
-
- for (; size >= 4; size -= 4) {
- *a++ = this_cpu_read(*b);
- b++;
- }
-}
-
-static void echainiv_write_iv(const u8 *src, unsigned size)
-{
- const u32 *a = (const u32 *)src;
- u32 __percpu *b = echainiv_iv;
-
- for (; size >= 4; size -= 4) {
- this_cpu_write(*b, *a);
- a++;
- b++;
- }
-}
-
-static void echainiv_encrypt_complete2(struct aead_request *req, int err)
-{
- struct aead_request *subreq = aead_request_ctx(req);
- struct crypto_aead *geniv;
- unsigned int ivsize;
-
- if (err == -EINPROGRESS)
- return;
-
- if (err)
- goto out;
-
- geniv = crypto_aead_reqtfm(req);
- ivsize = crypto_aead_ivsize(geniv);
-
- echainiv_write_iv(subreq->iv, ivsize);
-
- if (req->iv != subreq->iv)
- memcpy(req->iv, subreq->iv, ivsize);
-
-out:
- if (req->iv != subreq->iv)
- kzfree(subreq->iv);
-}
-
-static void echainiv_encrypt_complete(struct crypto_async_request *base,
- int err)
-{
- struct aead_request *req = base->data;
-
- echainiv_encrypt_complete2(req, err);
- aead_request_complete(req, err);
-}
-
static int echainiv_encrypt(struct aead_request *req)
{
struct crypto_aead *geniv = crypto_aead_reqtfm(req);
struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
struct aead_request *subreq = aead_request_ctx(req);
- crypto_completion_t compl;
- void *data;
+ __be64 nseqno;
+ u64 seqno;
u8 *info;
unsigned int ivsize = crypto_aead_ivsize(geniv);
int err;
aead_request_set_tfm(subreq, ctx->child);
- compl = echainiv_encrypt_complete;
- data = req;
info = req->iv;
if (req->src != req->dst) {
return err;
}
- if (unlikely(!IS_ALIGNED((unsigned long)info,
- crypto_aead_alignmask(geniv) + 1))) {
- info = kmalloc(ivsize, req->base.flags &
- CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
- GFP_ATOMIC);
- if (!info)
- return -ENOMEM;
-
- memcpy(info, req->iv, ivsize);
- }
-
- aead_request_set_callback(subreq, req->base.flags, compl, data);
+ aead_request_set_callback(subreq, req->base.flags,
+ req->base.complete, req->base.data);
aead_request_set_crypt(subreq, req->dst, req->dst,
req->cryptlen, info);
aead_request_set_ad(subreq, req->assoclen);
- crypto_xor(info, ctx->salt, ivsize);
+ memcpy(&nseqno, info + ivsize - 8, 8);
+ seqno = be64_to_cpu(nseqno);
+ memset(info, 0, ivsize);
+
scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
- echainiv_read_iv(info, ivsize);
- err = crypto_aead_encrypt(subreq);
- echainiv_encrypt_complete2(req, err);
- return err;
+ do {
+ u64 a;
+
+ memcpy(&a, ctx->salt + ivsize - 8, 8);
+
+ a |= 1;
+ a *= seqno;
+
+ memcpy(info + ivsize - 8, &a, 8);
+ } while ((ivsize -= 8));
+
+ return crypto_aead_encrypt(subreq);
}
static int echainiv_decrypt(struct aead_request *req)
alg = crypto_spawn_aead_alg(spawn);
err = -EINVAL;
- if (inst->alg.ivsize & (sizeof(u32) - 1) ||
- inst->alg.ivsize > MAX_IV_SIZE)
+ if (inst->alg.ivsize & (sizeof(u64) - 1) || !inst->alg.ivsize)
goto free_inst;
inst->alg.encrypt = echainiv_encrypt;
inst->alg.init = aead_init_geniv;
inst->alg.exit = aead_exit_geniv;
- inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
inst->alg.base.cra_ctxsize += inst->alg.ivsize;
struct device *parent = NULL;
int retval;
- trace_rpm_suspend(dev, rpmflags);
+ trace_rpm_suspend_rcuidle(dev, rpmflags);
repeat:
retval = rpm_check_suspend_allowed(dev);
}
out:
- trace_rpm_return_int(dev, _THIS_IP_, retval);
+ trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
return retval;
[RST_BUS_I2S1] = { 0x2d0, BIT(13) },
[RST_BUS_I2S2] = { 0x2d0, BIT(14) },
- [RST_BUS_I2C0] = { 0x2d4, BIT(0) },
- [RST_BUS_I2C1] = { 0x2d4, BIT(1) },
- [RST_BUS_I2C2] = { 0x2d4, BIT(2) },
- [RST_BUS_UART0] = { 0x2d4, BIT(16) },
- [RST_BUS_UART1] = { 0x2d4, BIT(17) },
- [RST_BUS_UART2] = { 0x2d4, BIT(18) },
- [RST_BUS_UART3] = { 0x2d4, BIT(19) },
- [RST_BUS_SCR] = { 0x2d4, BIT(20) },
+ [RST_BUS_I2C0] = { 0x2d8, BIT(0) },
+ [RST_BUS_I2C1] = { 0x2d8, BIT(1) },
+ [RST_BUS_I2C2] = { 0x2d8, BIT(2) },
+ [RST_BUS_UART0] = { 0x2d8, BIT(16) },
+ [RST_BUS_UART1] = { 0x2d8, BIT(17) },
+ [RST_BUS_UART2] = { 0x2d8, BIT(18) },
+ [RST_BUS_UART3] = { 0x2d8, BIT(19) },
+ [RST_BUS_SCR] = { 0x2d8, BIT(20) },
};
static const struct sunxi_ccu_desc sun8i_h3_ccu_desc = {
#include "ccu_gate.h"
#include "ccu_nk.h"
-void ccu_nk_find_best(unsigned long parent, unsigned long rate,
- unsigned int max_n, unsigned int max_k,
- unsigned int *n, unsigned int *k)
+static void ccu_nk_find_best(unsigned long parent, unsigned long rate,
+ unsigned int max_n, unsigned int max_k,
+ unsigned int *n, unsigned int *k)
{
unsigned long best_rate = 0;
unsigned int best_k = 0, best_n = 0;
SUN4I_PLL2_PRE_DIV_WIDTH,
CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
&sun4i_a10_pll2_lock);
- if (!prediv_clk) {
+ if (IS_ERR(prediv_clk)) {
pr_err("Couldn't register the prediv clock\n");
goto err_free_array;
}
&mult->hw, &clk_multiplier_ops,
&gate->hw, &clk_gate_ops,
CLK_SET_RATE_PARENT);
- if (!base_clk) {
+ if (IS_ERR(base_clk)) {
pr_err("Couldn't register the base multiplier clock\n");
goto err_free_multiplier;
}
return;
reg = of_io_request_and_map(node, 0, of_node_full_name(node));
- if (!reg) {
+ if (IS_ERR(reg)) {
pr_err("Could not get registers for sun8i-mbus-clk\n");
goto err_free_parents;
}
}
if (subnode) {
- node = of_get_flat_dt_subnode_by_name(node, subnode);
- if (node < 0)
+ int err = of_get_flat_dt_subnode_by_name(node, subnode);
+
+ if (err < 0)
return 0;
+
+ node = err;
}
return __find_uefi_params(node, info, dt_params[i].params);
#define EFI_ALLOC_ALIGN EFI_PAGE_SIZE
#endif
+#define EFI_MMAP_NR_SLACK_SLOTS 8
+
struct file_info {
efi_file_handle_t *handle;
u64 size;
}
}
+static inline bool mmap_has_headroom(unsigned long buff_size,
+ unsigned long map_size,
+ unsigned long desc_size)
+{
+ unsigned long slack = buff_size - map_size;
+
+ return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS;
+}
+
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr)
+ struct efi_boot_memmap *map)
{
efi_memory_desc_t *m = NULL;
efi_status_t status;
unsigned long key;
u32 desc_version;
- *map_size = sizeof(*m) * 32;
+ *map->desc_size = sizeof(*m);
+ *map->map_size = *map->desc_size * 32;
+ *map->buff_size = *map->map_size;
again:
- /*
- * Add an additional efi_memory_desc_t because we're doing an
- * allocation which may be in a new descriptor region.
- */
- *map_size += sizeof(*m);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- *map_size, (void **)&m);
+ *map->map_size, (void **)&m);
if (status != EFI_SUCCESS)
goto fail;
- *desc_size = 0;
+ *map->desc_size = 0;
key = 0;
- status = efi_call_early(get_memory_map, map_size, m,
- &key, desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
+ status = efi_call_early(get_memory_map, map->map_size, m,
+ &key, map->desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL ||
+ !mmap_has_headroom(*map->buff_size, *map->map_size,
+ *map->desc_size)) {
efi_call_early(free_pool, m);
+ /*
+ * Make sure there is some entries of headroom so that the
+ * buffer can be reused for a new map after allocations are
+ * no longer permitted. Its unlikely that the map will grow to
+ * exceed this headroom once we are ready to trigger
+ * ExitBootServices()
+ */
+ *map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS;
+ *map->buff_size = *map->map_size;
goto again;
}
if (status != EFI_SUCCESS)
efi_call_early(free_pool, m);
- if (key_ptr && status == EFI_SUCCESS)
- *key_ptr = key;
- if (desc_ver && status == EFI_SUCCESS)
- *desc_ver = desc_version;
+ if (map->key_ptr && status == EFI_SUCCESS)
+ *map->key_ptr = key;
+ if (map->desc_ver && status == EFI_SUCCESS)
+ *map->desc_ver = desc_version;
fail:
- *map = m;
+ *map->map = m;
return status;
}
unsigned long get_dram_base(efi_system_table_t *sys_table_arg)
{
efi_status_t status;
- unsigned long map_size;
+ unsigned long map_size, buff_size;
unsigned long membase = EFI_ERROR;
struct efi_memory_map map;
efi_memory_desc_t *md;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
- &map_size, &map.desc_size, NULL, NULL);
+ boot_map.map = (efi_memory_desc_t **)&map.map;
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &map.desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
return membase;
unsigned long size, unsigned long align,
unsigned long *addr, unsigned long max)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
u64 max_addr = 0;
int i;
+ struct efi_boot_memmap boot_map;
+
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
unsigned long size, unsigned long align,
unsigned long *addr)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
int i;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
*cmd_line_len = options_bytes;
return (char *)cmdline_addr;
}
+
+/*
+ * Handle calling ExitBootServices according to the requirements set out by the
+ * spec. Obtains the current memory map, and returns that info after calling
+ * ExitBootServices. The client must specify a function to perform any
+ * processing of the memory map data prior to ExitBootServices. A client
+ * specific structure may be passed to the function via priv. The client
+ * function may be called multiple times.
+ */
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func)
+{
+ efi_status_t status;
+
+ status = efi_get_memory_map(sys_table_arg, map);
+
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ if (status != EFI_SUCCESS)
+ goto free_map;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+
+ if (status == EFI_INVALID_PARAMETER) {
+ /*
+ * The memory map changed between efi_get_memory_map() and
+ * exit_boot_services(). Per the UEFI Spec v2.6, Section 6.4:
+ * EFI_BOOT_SERVICES.ExitBootServices we need to get the
+ * updated map, and try again. The spec implies one retry
+ * should be sufficent, which is confirmed against the EDK2
+ * implementation. Per the spec, we can only invoke
+ * get_memory_map() and exit_boot_services() - we cannot alloc
+ * so efi_get_memory_map() cannot be used, and we must reuse
+ * the buffer. For all practical purposes, the headroom in the
+ * buffer should account for any changes in the map so the call
+ * to get_memory_map() is expected to succeed here.
+ */
+ *map->map_size = *map->buff_size;
+ status = efi_call_early(get_memory_map,
+ map->map_size,
+ *map->map,
+ map->key_ptr,
+ map->desc_size,
+ map->desc_ver);
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+ }
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ return EFI_SUCCESS;
+
+free_map:
+ efi_call_early(free_pool, *map->map);
+fail:
+ return status;
+}
#define EFI_FDT_ALIGN EFI_PAGE_SIZE
#endif
+struct exit_boot_struct {
+ efi_memory_desc_t *runtime_map;
+ int *runtime_entry_count;
+};
+
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ struct exit_boot_struct *p = priv;
+ /*
+ * Update the memory map with virtual addresses. The function will also
+ * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
+ * entries so that we can pass it straight to SetVirtualAddressMap()
+ */
+ efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
+ p->runtime_map, p->runtime_entry_count);
+
+ return EFI_SUCCESS;
+}
+
/*
* Allocate memory for a new FDT, then add EFI, commandline, and
* initrd related fields to the FDT. This routine increases the
unsigned long fdt_addr,
unsigned long fdt_size)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
u32 desc_ver;
unsigned long mmap_key;
efi_memory_desc_t *memory_map, *runtime_map;
unsigned long new_fdt_size;
efi_status_t status;
int runtime_entry_count = 0;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &runtime_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_ver;
+ map.key_ptr = &mmap_key;
+ map.buff_size = &buff_size;
/*
* Get a copy of the current memory map that we will use to prepare
* subsequent allocations adding entries, since they could not affect
* the number of EFI_MEMORY_RUNTIME regions.
*/
- status = efi_get_memory_map(sys_table, &runtime_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS) {
pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n");
return status;
pr_efi(sys_table,
"Exiting boot services and installing virtual address map...\n");
+ map.map = &memory_map;
/*
* Estimate size of new FDT, and allocate memory for it. We
* will allocate a bigger buffer if this ends up being too
* we can get the memory map key needed for
* exit_boot_services().
*/
- status = efi_get_memory_map(sys_table, &memory_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS)
goto fail_free_new_fdt;
}
}
- /*
- * Update the memory map with virtual addresses. The function will also
- * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
- * entries so that we can pass it straight into SetVirtualAddressMap()
- */
- efi_get_virtmap(memory_map, map_size, desc_size, runtime_map,
- &runtime_entry_count);
-
- /* Now we are ready to exit_boot_services.*/
- status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+ sys_table->boottime->free_pool(memory_map);
+ priv.runtime_map = runtime_map;
+ priv.runtime_entry_count = &runtime_entry_count;
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
if (status == EFI_SUCCESS) {
efi_set_virtual_address_map_t *svam;
unsigned long random_seed)
{
unsigned long map_size, desc_size, total_slots = 0, target_slot;
+ unsigned long buff_size;
efi_status_t status;
efi_memory_desc_t *memory_map;
int map_offset;
+ struct efi_boot_memmap map;
- status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size,
- &desc_size, NULL, NULL);
+ map.map = &memory_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = NULL;
+ map.key_ptr = NULL;
+ map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &map);
if (status != EFI_SUCCESS)
return status;
atmel_hlcdc_crtc_finish_page_flip(drm_crtc_to_atmel_hlcdc_crtc(c));
}
-void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
+static void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
{
struct atmel_hlcdc_crtc_state *state;
u32 *coeff_tab = heo_upscaling_ycoef;
u32 max_memsize;
- if (state->crtc_w < state->src_w)
+ if (state->crtc_h < state->src_h)
coeff_tab = heo_downscaling_ycoef;
for (i = 0; i < ARRAY_SIZE(heo_upscaling_ycoef); i++)
atmel_hlcdc_layer_update_cfg(&plane->layer,
33 + i,
0xffffffff,
coeff_tab[i]);
- factor = ((8 * 256 * state->src_w) - (256 * 4)) /
- state->crtc_w;
+ factor = ((8 * 256 * state->src_h) - (256 * 4)) /
+ state->crtc_h;
factor++;
- max_memsize = ((factor * state->crtc_w) + (256 * 4)) /
+ max_memsize = ((factor * state->crtc_h) + (256 * 4)) /
2048;
- if (max_memsize > state->src_w)
+ if (max_memsize > state->src_h)
factor--;
factor_reg |= (factor << 16) | 0x80000000;
}
return 0;
}
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
typedef struct drm_mode_fb_cmd232 {
u32 fb_id;
u32 width;
return 0;
}
+#endif
static drm_ioctl_compat_t *drm_compat_ioctls[] = {
[DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version,
[DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw,
#endif
[DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank,
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
[DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2,
+#endif
};
/**
flags = exynos_gem->flags;
/*
- * without iommu support, not support physically non-continuous memory
- * for framebuffer.
+ * Physically non-contiguous memory type for framebuffer is not
+ * supported without IOMMU.
*/
if (IS_NONCONTIG_BUFFER(flags)) {
- DRM_ERROR("cannot use this gem memory type for fb.\n");
+ DRM_ERROR("Non-contiguous GEM memory is not supported.\n");
return -EINVAL;
}
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int fimc_suspend(struct device *dev)
-{
- struct fimc_context *ctx = get_fimc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return fimc_clk_ctrl(ctx, false);
-}
-
-static int fimc_resume(struct device *dev)
-{
- struct fimc_context *ctx = get_fimc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (!pm_runtime_suspended(dev))
- return fimc_clk_ctrl(ctx, true);
-
- return 0;
-}
-#endif
-
static int fimc_runtime_suspend(struct device *dev)
{
struct fimc_context *ctx = get_fimc_context(dev);
#endif
static const struct dev_pm_ops fimc_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(fimc_suspend, fimc_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(fimc_runtime_suspend, fimc_runtime_resume, NULL)
};
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int g2d_suspend(struct device *dev)
+#ifdef CONFIG_PM
+static int g2d_runtime_suspend(struct device *dev)
{
struct g2d_data *g2d = dev_get_drvdata(dev);
flush_work(&g2d->runqueue_work);
- return 0;
-}
-
-static int g2d_resume(struct device *dev)
-{
- struct g2d_data *g2d = dev_get_drvdata(dev);
-
- g2d->suspended = false;
- g2d_exec_runqueue(g2d);
-
- return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int g2d_runtime_suspend(struct device *dev)
-{
- struct g2d_data *g2d = dev_get_drvdata(dev);
-
clk_disable_unprepare(g2d->gate_clk);
return 0;
if (ret < 0)
dev_warn(dev, "failed to enable clock.\n");
+ g2d->suspended = false;
+ g2d_exec_runqueue(g2d);
+
return ret;
}
#endif
static const struct dev_pm_ops g2d_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(g2d_suspend, g2d_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(g2d_runtime_suspend, g2d_runtime_resume, NULL)
};
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int gsc_suspend(struct device *dev)
-{
- struct gsc_context *ctx = get_gsc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return gsc_clk_ctrl(ctx, false);
-}
-
-static int gsc_resume(struct device *dev)
-{
- struct gsc_context *ctx = get_gsc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (!pm_runtime_suspended(dev))
- return gsc_clk_ctrl(ctx, true);
-
- return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int gsc_runtime_suspend(struct device *dev)
+static int __maybe_unused gsc_runtime_suspend(struct device *dev)
{
struct gsc_context *ctx = get_gsc_context(dev);
return gsc_clk_ctrl(ctx, false);
}
-static int gsc_runtime_resume(struct device *dev)
+static int __maybe_unused gsc_runtime_resume(struct device *dev)
{
struct gsc_context *ctx = get_gsc_context(dev);
return gsc_clk_ctrl(ctx, true);
}
-#endif
static const struct dev_pm_ops gsc_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(gsc_suspend, gsc_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(gsc_runtime_suspend, gsc_runtime_resume, NULL)
};
return 0;
}
-
-#ifdef CONFIG_PM_SLEEP
-static int rotator_suspend(struct device *dev)
-{
- struct rot_context *rot = dev_get_drvdata(dev);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return rotator_clk_crtl(rot, false);
-}
-
-static int rotator_resume(struct device *dev)
-{
- struct rot_context *rot = dev_get_drvdata(dev);
-
- if (!pm_runtime_suspended(dev))
- return rotator_clk_crtl(rot, true);
-
- return 0;
-}
-#endif
-
static int rotator_runtime_suspend(struct device *dev)
{
struct rot_context *rot = dev_get_drvdata(dev);
#endif
static const struct dev_pm_ops rotator_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(rotator_suspend, rotator_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(rotator_runtime_suspend, rotator_runtime_resume,
NULL)
};
intel_runtime_pm_enable(dev_priv);
+ /* Everything is in place, we can now relax! */
+ DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n",
+ driver.name, driver.major, driver.minor, driver.patchlevel,
+ driver.date, pci_name(pdev), dev_priv->drm.primary->index);
+
intel_runtime_pm_put(dev_priv);
return 0;
has_full_48bit_ppgtt =
IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9;
- if (intel_vgpu_active(dev_priv))
- has_full_ppgtt = false; /* emulation is too hard */
+ if (intel_vgpu_active(dev_priv)) {
+ /* emulation is too hard */
+ has_full_ppgtt = false;
+ has_full_48bit_ppgtt = false;
+ }
if (!has_aliasing_ppgtt)
return 0;
return 0;
}
- if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists)
+ if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists && has_full_ppgtt)
return has_full_48bit_ppgtt ? 3 : 2;
else
return has_aliasing_ppgtt ? 1 : 0;
BUILD_BUG_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
- if (!IS_HASWELL(dev_priv))
- return;
-
magic = __raw_i915_read64(dev_priv, vgtif_reg(magic));
if (magic != VGT_MAGIC)
return;
return;
}
- drm_encoder_cleanup(&intel_encoder->base);
kfree(intel_dvo);
kfree(intel_connector);
}
return err;
}
+static int intel_use_opregion_panel_type_callback(const struct dmi_system_id *id)
+{
+ DRM_INFO("Using panel type from OpRegion on %s\n", id->ident);
+ return 1;
+}
+
+static const struct dmi_system_id intel_use_opregion_panel_type[] = {
+ {
+ .callback = intel_use_opregion_panel_type_callback,
+ .ident = "Conrac GmbH IX45GM2",
+ .matches = {DMI_MATCH(DMI_SYS_VENDOR, "Conrac GmbH"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "IX45GM2"),
+ },
+ },
+ { }
+};
+
int
intel_opregion_get_panel_type(struct drm_i915_private *dev_priv)
{
return -ENODEV;
}
+ /*
+ * So far we know that some machined must use it, others must not use it.
+ * There doesn't seem to be any way to determine which way to go, except
+ * via a quirk list :(
+ */
+ if (!dmi_check_system(intel_use_opregion_panel_type)) {
+ DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1);
+ return -ENODEV;
+ }
+
/*
* FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us
* low vswing for eDP, whereas the VBT panel type (2) gives us normal
case GEN6_PCODE_ILLEGAL_CMD:
return -ENXIO;
case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
return -EOVERFLOW;
case GEN6_PCODE_TIMEOUT:
return -ETIMEDOUT;
struct drm_i915_private *dev_priv = to_i915(dev);
uint32_t max_sleep_time = 0x1f;
- /* Lately it was identified that depending on panel idle frame count
- * calculated at HW can be off by 1. So let's use what came
- * from VBT + 1.
- * There are also other cases where panel demands at least 4
- * but VBT is not being set. To cover these 2 cases lets use
- * at least 5 when VBT isn't set to be on the safest side.
+ /*
+ * Let's respect VBT in case VBT asks a higher idle_frame value.
+ * Let's use 6 as the minimum to cover all known cases including
+ * the off-by-one issue that HW has in some cases. Also there are
+ * cases where sink should be able to train
+ * with the 5 or 6 idle patterns.
*/
- uint32_t idle_frames = dev_priv->vbt.psr.idle_frames + 1;
+ uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
uint32_t val = EDP_PSR_ENABLE;
val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
return &vc4->bo_cache.size_list[page_index];
}
-void vc4_bo_cache_purge(struct drm_device *dev)
+static void vc4_bo_cache_purge(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
* of uniforms on each side. However, this scheme is easy to
* validate so it's all we allow for now.
*/
-
- if (QPU_GET_FIELD(inst, QPU_SIG) != QPU_SIG_NONE) {
+ switch (QPU_GET_FIELD(inst, QPU_SIG)) {
+ case QPU_SIG_NONE:
+ case QPU_SIG_SCOREBOARD_UNLOCK:
+ case QPU_SIG_COLOR_LOAD:
+ case QPU_SIG_LOAD_TMU0:
+ case QPU_SIG_LOAD_TMU1:
+ break;
+ default:
DRM_ERROR("uniforms address change must be "
"normal math\n");
return false;
spin_lock_irqsave(&ep->com.dev->lock, flags);
_remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid, 0);
+ if (idr_is_empty(&ep->com.dev->hwtid_idr))
+ wake_up(&ep->com.dev->wait);
spin_unlock_irqrestore(&ep->com.dev->lock, flags);
}
}
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, rt_tos2priority(tos));
- if (!ep->l2t)
+ if (!ep->l2t) {
+ dev_put(pdev);
goto out;
+ }
ep->mtu = pdev->mtu;
ep->tx_chan = cxgb4_port_chan(pdev);
ep->smac_idx = cxgb4_tp_smt_idx(adapter_type,
static void c4iw_dealloc(struct uld_ctx *ctx)
{
c4iw_rdev_close(&ctx->dev->rdev);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->cqidr));
idr_destroy(&ctx->dev->cqidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->qpidr));
idr_destroy(&ctx->dev->qpidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->mmidr));
idr_destroy(&ctx->dev->mmidr);
+ wait_event(ctx->dev->wait, idr_is_empty(&ctx->dev->hwtid_idr));
idr_destroy(&ctx->dev->hwtid_idr);
idr_destroy(&ctx->dev->stid_idr);
idr_destroy(&ctx->dev->atid_idr);
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
INIT_LIST_HEAD(&devp->db_fc_list);
+ init_waitqueue_head(&devp->wait);
devp->avail_ird = devp->rdev.lldi.max_ird_adapter;
if (c4iw_debugfs_root) {
struct idr stid_idr;
struct list_head db_fc_list;
u32 avail_ird;
+ wait_queue_head_t wait;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
/* Generate GUID changed event */
if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) {
+ if (mlx4_is_master(dev->dev)) {
+ union ib_gid gid;
+ int err = 0;
+
+ if (!eqe->event.port_mgmt_change.params.port_info.gid_prefix)
+ err = __mlx4_ib_query_gid(&dev->ib_dev, port, 0, &gid, 1);
+ else
+ gid.global.subnet_prefix =
+ eqe->event.port_mgmt_change.params.port_info.gid_prefix;
+ if (err) {
+ pr_warn("Could not change QP1 subnet prefix for port %d: query_gid error (%d)\n",
+ port, err);
+ } else {
+ pr_debug("Changing QP1 subnet prefix for port %d. old=0x%llx. new=0x%llx\n",
+ port,
+ (u64)atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix),
+ be64_to_cpu(gid.global.subnet_prefix));
+ atomic64_set(&dev->sriov.demux[port - 1].subnet_prefix,
+ be64_to_cpu(gid.global.subnet_prefix));
+ }
+ }
mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
/*if master, notify all slaves*/
if (mlx4_is_master(dev->dev))
if (err)
goto demux_err;
dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id;
+ atomic64_set(&dev->sriov.demux[i].subnet_prefix,
+ be64_to_cpu(gid.global.subnet_prefix));
err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1,
&dev->sriov.sqps[i]);
if (err)
bool per_port = !!(ibdev->dev->caps.flags2 &
MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT);
+ if (mlx4_is_slave(ibdev->dev))
+ return 0;
+
for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
/* i == 1 means we are building port counters */
if (i && !per_port)
if (!group->members[i])
leave_state |= (1 << i);
- return leave_state & (group->rec.scope_join_state & 7);
+ return leave_state & (group->rec.scope_join_state & 0xf);
}
static int join_group(struct mcast_group *group, int slave, u8 join_mask)
} else
mcg_warn_group(group, "DRIVER BUG\n");
} else if (group->state == MCAST_LEAVE_SENT) {
- if (group->rec.scope_join_state & 7)
- group->rec.scope_join_state &= 0xf8;
+ if (group->rec.scope_join_state & 0xf)
+ group->rec.scope_join_state &= 0xf0;
group->state = MCAST_IDLE;
mutex_unlock(&group->lock);
if (release_group(group, 1))
static int handle_join_req(struct mcast_group *group, u8 join_mask,
struct mcast_req *req)
{
- u8 group_join_state = group->rec.scope_join_state & 7;
+ u8 group_join_state = group->rec.scope_join_state & 0xf;
int ref = 0;
u16 status;
struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
u8 cur_join_state;
resp_join_state = ((struct ib_sa_mcmember_data *)
- group->response_sa_mad.data)->scope_join_state & 7;
- cur_join_state = group->rec.scope_join_state & 7;
+ group->response_sa_mad.data)->scope_join_state & 0xf;
+ cur_join_state = group->rec.scope_join_state & 0xf;
if (method == IB_MGMT_METHOD_GET_RESP) {
/* successfull join */
req = list_first_entry(&group->pending_list, struct mcast_req,
group_list);
sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
- req_join_state = sa_data->scope_join_state & 0x7;
+ req_join_state = sa_data->scope_join_state & 0xf;
/* For a leave request, we will immediately answer the VF, and
* update our internal counters. The actual leave will be sent
struct workqueue_struct *wq;
struct workqueue_struct *ud_wq;
spinlock_t ud_lock;
- __be64 subnet_prefix;
+ atomic64_t subnet_prefix;
__be64 guid_cache[128];
struct mlx4_ib_dev *dev;
/* the following lock protects both mcg_table and mcg_mgid0_list */
sqp->ud_header.grh.flow_label =
ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit;
- if (is_eth)
+ if (is_eth) {
memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
- else {
- if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
- /* When multi-function is enabled, the ib_core gid
- * indexes don't necessarily match the hw ones, so
- * we must use our own cache */
- sqp->ud_header.grh.source_gid.global.subnet_prefix =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- subnet_prefix;
- sqp->ud_header.grh.source_gid.global.interface_id =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- guid_cache[ah->av.ib.gid_index];
- } else
- ib_get_cached_gid(ib_dev,
- be32_to_cpu(ah->av.ib.port_pd) >> 24,
- ah->av.ib.gid_index,
- &sqp->ud_header.grh.source_gid, NULL);
+ } else {
+ if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
+ /* When multi-function is enabled, the ib_core gid
+ * indexes don't necessarily match the hw ones, so
+ * we must use our own cache
+ */
+ sqp->ud_header.grh.source_gid.global.subnet_prefix =
+ cpu_to_be64(atomic64_read(&(to_mdev(ib_dev)->sriov.
+ demux[sqp->qp.port - 1].
+ subnet_prefix)));
+ sqp->ud_header.grh.source_gid.global.interface_id =
+ to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
+ guid_cache[ah->av.ib.gid_index];
+ } else {
+ ib_get_cached_gid(ib_dev,
+ be32_to_cpu(ah->av.ib.port_pd) >> 24,
+ ah->av.ib.gid_index,
+ &sqp->ud_header.grh.source_gid, NULL);
+ }
}
memcpy(sqp->ud_header.grh.destination_gid.raw,
ah->av.ib.dgid, 16);
static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
{
- return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
+ return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ return 0;
}
enum {
dmac_47_16),
ib_spec->eth.val.dst_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ smac_47_16),
+ ib_spec->eth.mask.src_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ smac_47_16),
+ ib_spec->eth.val.src_mac);
+
if (ib_spec->eth.mask.vlan_tag) {
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
vlan_tag, 1);
{
rvt_deinit_mregion(&mr->mr);
rvt_free_lkey(&mr->mr);
- vfree(mr);
+ kfree(mr);
}
/**
return err;
}
- err = rxe_net_init();
+ err = rxe_net_ipv4_init();
if (err) {
- pr_err("rxe: unable to init\n");
+ pr_err("rxe: unable to init ipv4 tunnel\n");
rxe_cache_exit();
- return err;
+ goto exit;
+ }
+
+ err = rxe_net_ipv6_init();
+ if (err) {
+ pr_err("rxe: unable to init ipv6 tunnel\n");
+ rxe_cache_exit();
+ goto exit;
}
+
+ err = register_netdevice_notifier(&rxe_net_notifier);
+ if (err) {
+ pr_err("rxe: Failed to rigister netdev notifier\n");
+ goto exit;
+ }
+
pr_info("rxe: loaded\n");
return 0;
+
+exit:
+ rxe_release_udp_tunnel(recv_sockets.sk4);
+ rxe_release_udp_tunnel(recv_sockets.sk6);
+ return err;
}
static void __exit rxe_module_exit(void)
qp->req.need_retry = 1;
rxe_run_task(&qp->req.task, 1);
}
+
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ }
+
goto exit;
+
} else {
wqe->status = IB_WC_RETRY_EXC_ERR;
state = COMPST_ERROR;
case COMPST_ERROR:
do_complete(qp, wqe);
rxe_qp_error(qp);
+
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ }
+
goto exit;
}
}
return sock;
}
-static void rxe_release_udp_tunnel(struct socket *sk)
+void rxe_release_udp_tunnel(struct socket *sk)
{
- udp_tunnel_sock_release(sk);
+ if (sk)
+ udp_tunnel_sock_release(sk);
}
static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port,
return NOTIFY_OK;
}
-static struct notifier_block rxe_net_notifier = {
+struct notifier_block rxe_net_notifier = {
.notifier_call = rxe_notify,
};
-int rxe_net_init(void)
+int rxe_net_ipv4_init(void)
{
- int err;
-
spin_lock_init(&dev_list_lock);
- recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
- htons(ROCE_V2_UDP_DPORT), true);
- if (IS_ERR(recv_sockets.sk6)) {
- recv_sockets.sk6 = NULL;
- pr_err("rxe: Failed to create IPv6 UDP tunnel\n");
- return -1;
- }
-
recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
- htons(ROCE_V2_UDP_DPORT), false);
+ htons(ROCE_V2_UDP_DPORT), false);
if (IS_ERR(recv_sockets.sk4)) {
- rxe_release_udp_tunnel(recv_sockets.sk6);
recv_sockets.sk4 = NULL;
- recv_sockets.sk6 = NULL;
pr_err("rxe: Failed to create IPv4 UDP tunnel\n");
return -1;
}
- err = register_netdevice_notifier(&rxe_net_notifier);
- if (err) {
- rxe_release_udp_tunnel(recv_sockets.sk6);
- rxe_release_udp_tunnel(recv_sockets.sk4);
- pr_err("rxe: Failed to rigister netdev notifier\n");
- }
-
- return err;
+ return 0;
}
-void rxe_net_exit(void)
+int rxe_net_ipv6_init(void)
{
- if (recv_sockets.sk6)
- rxe_release_udp_tunnel(recv_sockets.sk6);
+#if IS_ENABLED(CONFIG_IPV6)
- if (recv_sockets.sk4)
- rxe_release_udp_tunnel(recv_sockets.sk4);
+ spin_lock_init(&dev_list_lock);
+ recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
+ htons(ROCE_V2_UDP_DPORT), true);
+ if (IS_ERR(recv_sockets.sk6)) {
+ recv_sockets.sk6 = NULL;
+ pr_err("rxe: Failed to create IPv6 UDP tunnel\n");
+ return -1;
+ }
+#endif
+ return 0;
+}
+
+void rxe_net_exit(void)
+{
+ rxe_release_udp_tunnel(recv_sockets.sk6);
+ rxe_release_udp_tunnel(recv_sockets.sk4);
unregister_netdevice_notifier(&rxe_net_notifier);
}
};
extern struct rxe_recv_sockets recv_sockets;
+extern struct notifier_block rxe_net_notifier;
+void rxe_release_udp_tunnel(struct socket *sk);
struct rxe_dev *rxe_net_add(struct net_device *ndev);
-int rxe_net_init(void);
+int rxe_net_ipv4_init(void);
+int rxe_net_ipv6_init(void);
void rxe_net_exit(void);
#endif /* RXE_NET_H */
* make a copy of the skb to post to the next qp
*/
skb_copy = (mce->qp_list.next != &mcg->qp_list) ?
- skb_clone(skb, GFP_KERNEL) : NULL;
+ skb_clone(skb, GFP_ATOMIC) : NULL;
pkt->qp = qp;
rxe_add_ref(qp);
}
static void update_wqe_state(struct rxe_qp *qp,
- struct rxe_send_wqe *wqe,
- struct rxe_pkt_info *pkt,
- enum wqe_state *prev_state)
+ struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt)
{
- enum wqe_state prev_state_ = wqe->state;
-
if (pkt->mask & RXE_END_MASK) {
if (qp_type(qp) == IB_QPT_RC)
wqe->state = wqe_state_pending;
} else {
wqe->state = wqe_state_processing;
}
-
- *prev_state = prev_state_;
}
-static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
- struct rxe_pkt_info *pkt, int payload)
+static void update_wqe_psn(struct rxe_qp *qp,
+ struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt,
+ int payload)
{
/* number of packets left to send including current one */
int num_pkt = (wqe->dma.resid + payload + qp->mtu - 1) / qp->mtu;
qp->req.psn = (wqe->first_psn + num_pkt) & BTH_PSN_MASK;
else
qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
+}
- qp->req.opcode = pkt->opcode;
+static void save_state(struct rxe_send_wqe *wqe,
+ struct rxe_qp *qp,
+ struct rxe_send_wqe *rollback_wqe,
+ struct rxe_qp *rollback_qp)
+{
+ rollback_wqe->state = wqe->state;
+ rollback_wqe->first_psn = wqe->first_psn;
+ rollback_wqe->last_psn = wqe->last_psn;
+ rollback_qp->req.psn = qp->req.psn;
+}
+static void rollback_state(struct rxe_send_wqe *wqe,
+ struct rxe_qp *qp,
+ struct rxe_send_wqe *rollback_wqe,
+ struct rxe_qp *rollback_qp)
+{
+ wqe->state = rollback_wqe->state;
+ wqe->first_psn = rollback_wqe->first_psn;
+ wqe->last_psn = rollback_wqe->last_psn;
+ qp->req.psn = rollback_qp->req.psn;
+}
+
+static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt, int payload)
+{
+ qp->req.opcode = pkt->opcode;
if (pkt->mask & RXE_END_MASK)
qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index);
int mtu;
int opcode;
int ret;
- enum wqe_state prev_state;
+ struct rxe_qp rollback_qp;
+ struct rxe_send_wqe rollback_wqe;
next_wqe:
if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
goto err;
}
- update_wqe_state(qp, wqe, &pkt, &prev_state);
+ /*
+ * To prevent a race on wqe access between requester and completer,
+ * wqe members state and psn need to be set before calling
+ * rxe_xmit_packet().
+ * Otherwise, completer might initiate an unjustified retry flow.
+ */
+ save_state(wqe, qp, &rollback_wqe, &rollback_qp);
+ update_wqe_state(qp, wqe, &pkt);
+ update_wqe_psn(qp, wqe, &pkt, payload);
ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
if (ret) {
qp->need_req_skb = 1;
kfree_skb(skb);
- wqe->state = prev_state;
+ rollback_state(wqe, qp, &rollback_wqe, &rollback_qp);
if (ret == -EAGAIN) {
rxe_run_task(&qp->req.task, 1);
free_rd_atomic_resource(qp, res);
rxe_advance_resp_resource(qp);
+ memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb));
+
res->type = RXE_ATOMIC_MASK;
res->atomic.skb = skb;
- res->first_psn = qp->resp.psn;
- res->last_psn = qp->resp.psn;
- res->cur_psn = qp->resp.psn;
+ res->first_psn = ack_pkt.psn;
+ res->last_psn = ack_pkt.psn;
+ res->cur_psn = ack_pkt.psn;
rc = rxe_xmit_packet(rxe, qp, &ack_pkt, skb_copy);
if (rc) {
rc = RESPST_CLEANUP;
goto out;
}
- bth_set_psn(SKB_TO_PKT(skb_copy),
- qp->resp.psn - 1);
+
/* Resend the result. */
rc = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp,
pkt, skb_copy);
}
if (level == IPOIB_FLUSH_LIGHT) {
+ int oper_up;
ipoib_mark_paths_invalid(dev);
+ /* Set IPoIB operation as down to prevent races between:
+ * the flush flow which leaves MCG and on the fly joins
+ * which can happen during that time. mcast restart task
+ * should deal with join requests we missed.
+ */
+ oper_up = test_and_clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
ipoib_mcast_dev_flush(dev);
+ if (oper_up)
+ set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
ipoib_flush_ah(dev);
}
{
struct irq_domain_chip_generic *dgc = d->gc;
struct irq_chip_generic *gc;
+ unsigned long flags;
unsigned smr;
int idx;
int ret;
gc = dgc->gc[idx];
- irq_gc_lock(gc);
+ irq_gc_lock_irqsave(gc, flags);
smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
aic_common_set_priority(intspec[2], &smr);
irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
- irq_gc_unlock(gc);
+ irq_gc_unlock_irqrestore(gc, flags);
return ret;
}
unsigned int *out_type)
{
struct irq_chip_generic *bgc = irq_get_domain_generic_chip(d, 0);
+ unsigned long flags;
unsigned smr;
int ret;
if (ret)
return ret;
- irq_gc_lock(bgc);
+ irq_gc_lock_irqsave(bgc, flags);
irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
aic_common_set_priority(intspec[2], &smr);
irq_reg_writel(bgc, smr, AT91_AIC5_SMR);
- irq_gc_unlock(bgc);
+ irq_gc_unlock_irqrestore(bgc, flags);
return ret;
}
int md_setup_cluster(struct mddev *mddev, int nodes)
{
- int err;
-
- err = request_module("md-cluster");
- if (err) {
- pr_err("md-cluster module not found.\n");
- return -ENOENT;
- }
-
+ if (!md_cluster_ops)
+ request_module("md-cluster");
spin_lock(&pers_lock);
+ /* ensure module won't be unloaded */
if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
+ pr_err("can't find md-cluster module or get it's reference.\n");
spin_unlock(&pers_lock);
return -ENOENT;
}
spinlock_t no_space_stripes_lock;
bool need_cache_flush;
- bool in_teardown;
};
/*
mddev = log->rdev->mddev;
/*
- * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
- * wait for this thread to finish. This thread waits for
- * MD_CHANGE_PENDING clear, which is supposed to be done in
- * md_check_recovery(). md_check_recovery() tries to get
- * reconfig_mutex. Since r5l_quiesce already holds the mutex,
- * md_check_recovery() fails, so the PENDING never get cleared. The
- * in_teardown check workaround this issue.
+ * Discard could zero data, so before discard we must make sure
+ * superblock is updated to new log tail. Updating superblock (either
+ * directly call md_update_sb() or depend on md thread) must hold
+ * reconfig mutex. On the other hand, raid5_quiesce is called with
+ * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
+ * for all IO finish, hence waitting for reclaim thread, while reclaim
+ * thread is calling this function and waitting for reconfig mutex. So
+ * there is a deadlock. We workaround this issue with a trylock.
+ * FIXME: we could miss discard if we can't take reconfig mutex
*/
- if (!log->in_teardown) {
- set_mask_bits(&mddev->flags, 0,
- BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
- md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
- log->in_teardown);
- /*
- * r5l_quiesce could run after in_teardown check and hold
- * mutex first. Superblock might get updated twice.
- */
- if (log->in_teardown)
- md_update_sb(mddev, 1);
- } else {
- WARN_ON(!mddev_is_locked(mddev));
- md_update_sb(mddev, 1);
- }
+ set_mask_bits(&mddev->flags, 0,
+ BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+ if (!mddev_trylock(mddev))
+ return;
+ md_update_sb(mddev, 1);
+ mddev_unlock(mddev);
/* discard IO error really doesn't matter, ignore it */
if (log->last_checkpoint < end) {
if (!log || state == 2)
return;
if (state == 0) {
- log->in_teardown = 0;
/*
* This is a special case for hotadd. In suspend, the array has
* no journal. In resume, journal is initialized as well as the
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
} else if (state == 1) {
- /*
- * at this point all stripes are finished, so io_unit is at
- * least in STRIPE_END state
- */
- log->in_teardown = 1;
/* make sure r5l_write_super_and_discard_space exits */
mddev = log->rdev->mddev;
wake_up(&mddev->sb_wait);
}
}
rdev_dec_pending(rdev, conf->mddev);
+ bio_reset(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
- bio_reset(bi);
}
static void raid5_end_write_request(struct bio *bi)
if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
+ bio_reset(bi);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
if (sh->batch_head && sh != sh->batch_head)
raid5_release_stripe(sh->batch_head);
- bio_reset(bi);
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
}
conf->min_nr_stripes = NR_STRIPES;
+ if (mddev->reshape_position != MaxSector) {
+ int stripes = max_t(int,
+ ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ conf->min_nr_stripes = max(NR_STRIPES, stripes);
+ if (conf->min_nr_stripes != NR_STRIPES)
+ printk(KERN_INFO
+ "md/raid:%s: force stripe size %d for reshape\n",
+ mdname(mddev), conf->min_nr_stripes);
+ }
memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
/* Only reconfigure if we have a different burst size */
if (*bp != burst) {
- struct dma_slave_config cfg;
-
- cfg.src_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
- cfg.dst_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
- cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
- cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
- cfg.src_maxburst = burst;
- cfg.dst_maxburst = burst;
+ struct dma_slave_config cfg = {
+ .src_addr = host->phys_base +
+ OMAP_MMC_REG(host, DATA),
+ .dst_addr = host->phys_base +
+ OMAP_MMC_REG(host, DATA),
+ .src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES,
+ .dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES,
+ .src_maxburst = burst,
+ .dst_maxburst = burst,
+ };
if (dmaengine_slave_config(c, &cfg))
goto use_pio;
static int omap_hsmmc_setup_dma_transfer(struct omap_hsmmc_host *host,
struct mmc_request *req)
{
- struct dma_slave_config cfg;
struct dma_async_tx_descriptor *tx;
int ret = 0, i;
struct mmc_data *data = req->data;
struct dma_chan *chan;
+ struct dma_slave_config cfg = {
+ .src_addr = host->mapbase + OMAP_HSMMC_DATA,
+ .dst_addr = host->mapbase + OMAP_HSMMC_DATA,
+ .src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+ .dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+ .src_maxburst = data->blksz / 4,
+ .dst_maxburst = data->blksz / 4,
+ };
/* Sanity check: all the SG entries must be aligned by block size. */
for (i = 0; i < data->sg_len; i++) {
chan = omap_hsmmc_get_dma_chan(host, data);
- cfg.src_addr = host->mapbase + OMAP_HSMMC_DATA;
- cfg.dst_addr = host->mapbase + OMAP_HSMMC_DATA;
- cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- cfg.src_maxburst = data->blksz / 4;
- cfg.dst_maxburst = data->blksz / 4;
-
ret = dmaengine_slave_config(chan, &cfg);
if (ret)
return ret;
struct st_mmc_platform_data {
struct reset_control *rstc;
+ struct clk *icnclk;
void __iomem *top_ioaddr;
};
struct sdhci_host *host;
struct st_mmc_platform_data *pdata;
struct sdhci_pltfm_host *pltfm_host;
- struct clk *clk;
+ struct clk *clk, *icnclk;
int ret = 0;
u16 host_version;
struct resource *res;
return PTR_ERR(clk);
}
+ /* ICN clock isn't compulsory, but use it if it's provided. */
+ icnclk = devm_clk_get(&pdev->dev, "icn");
+ if (IS_ERR(icnclk))
+ icnclk = NULL;
+
rstc = devm_reset_control_get(&pdev->dev, NULL);
if (IS_ERR(rstc))
rstc = NULL;
}
clk_prepare_enable(clk);
+ clk_prepare_enable(icnclk);
/* Configure the FlashSS Top registers for setting eMMC TX/RX delay */
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
}
pltfm_host->clk = clk;
+ pdata->icnclk = icnclk;
/* Configure the Arasan HC inside the flashSS */
st_mmcss_cconfig(np, host);
return 0;
err_out:
+ clk_disable_unprepare(icnclk);
clk_disable_unprepare(clk);
err_of:
sdhci_pltfm_free(pdev);
ret = sdhci_pltfm_unregister(pdev);
+ clk_disable_unprepare(pdata->icnclk);
+
if (rstc)
reset_control_assert(rstc);
if (pdata->rstc)
reset_control_assert(pdata->rstc);
+ clk_disable_unprepare(pdata->icnclk);
clk_disable_unprepare(pltfm_host->clk);
out:
return ret;
struct device_node *np = dev->of_node;
clk_prepare_enable(pltfm_host->clk);
+ clk_prepare_enable(pdata->icnclk);
if (pdata->rstc)
reset_control_deassert(pdata->rstc);
nvme_suspend_queue(dev->queues[i]);
if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- nvme_suspend_queue(dev->queues[0]);
+ /* A device might become IO incapable very soon during
+ * probe, before the admin queue is configured. Thus,
+ * queue_count can be 0 here.
+ */
+ if (dev->queue_count)
+ nvme_suspend_queue(dev->queues[0]);
} else {
nvme_disable_io_queues(dev);
nvme_disable_admin_queue(dev, shutdown);
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+ { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ 0, }
enum nvme_rdma_queue_flags {
NVME_RDMA_Q_CONNECTED = (1 << 0),
+ NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1),
+ NVME_RDMA_Q_DELETING = (1 << 2),
};
struct nvme_rdma_queue {
if (IS_ERR(req->mr)) {
ret = PTR_ERR(req->mr);
req->mr = NULL;
+ goto out;
}
req->mr->need_inval = false;
static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
{
- struct nvme_rdma_device *dev = queue->device;
- struct ib_device *ibdev = dev->dev;
+ struct nvme_rdma_device *dev;
+ struct ib_device *ibdev;
+
+ if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags))
+ return;
+ dev = queue->device;
+ ibdev = dev->dev;
rdma_destroy_qp(queue->cm_id);
ib_free_cq(queue->ib_cq);
ret = -ENOMEM;
goto out_destroy_qp;
}
+ set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags);
return 0;
queue = &ctrl->queues[idx];
queue->ctrl = ctrl;
+ queue->flags = 0;
init_completion(&queue->cm_done);
if (idx > 0)
return 0;
out_destroy_cm_id:
+ nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
return ret;
}
static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
{
- if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+ if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
return;
nvme_rdma_stop_queue(queue);
nvme_rdma_free_queue(queue);
return 0;
out_free_queues:
- for (; i >= 1; i--)
+ for (i--; i >= 1; i--)
nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
return ret;
{
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, err_work);
+ int i;
nvme_stop_keep_alive(&ctrl->ctrl);
+
+ for (i = 0; i < ctrl->queue_count; i++)
+ clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags);
+
if (ctrl->queue_count > 1)
nvme_stop_queues(&ctrl->ctrl);
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
return ret;
}
-/**
- * nvme_rdma_device_unplug() - Handle RDMA device unplug
- * @queue: Queue that owns the cm_id that caught the event
- *
- * DEVICE_REMOVAL event notifies us that the RDMA device is about
- * to unplug so we should take care of destroying our RDMA resources.
- * This event will be generated for each allocated cm_id.
- *
- * In our case, the RDMA resources are managed per controller and not
- * only per queue. So the way we handle this is we trigger an implicit
- * controller deletion upon the first DEVICE_REMOVAL event we see, and
- * hold the event inflight until the controller deletion is completed.
- *
- * One exception that we need to handle is the destruction of the cm_id
- * that caught the event. Since we hold the callout until the controller
- * deletion is completed, we'll deadlock if the controller deletion will
- * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
- * of destroying this queue before-hand, destroy the queue resources,
- * then queue the controller deletion which won't destroy this queue and
- * we destroy the cm_id implicitely by returning a non-zero rc to the callout.
- */
-static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
-{
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- int ret = 0;
-
- /* Own the controller deletion */
- if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
- return 0;
-
- dev_warn(ctrl->ctrl.device,
- "Got rdma device removal event, deleting ctrl\n");
-
- /* Get rid of reconnect work if its running */
- cancel_delayed_work_sync(&ctrl->reconnect_work);
-
- /* Disable the queue so ctrl delete won't free it */
- if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) {
- /* Free this queue ourselves */
- nvme_rdma_stop_queue(queue);
- nvme_rdma_destroy_queue_ib(queue);
-
- /* Return non-zero so the cm_id will destroy implicitly */
- ret = 1;
- }
-
- /* Queue controller deletion */
- queue_work(nvme_rdma_wq, &ctrl->delete_work);
- flush_work(&ctrl->delete_work);
- return ret;
-}
-
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *ev)
{
nvme_rdma_error_recovery(queue->ctrl);
break;
case RDMA_CM_EVENT_DEVICE_REMOVAL:
- /* return 1 means impliciy CM ID destroy */
- return nvme_rdma_device_unplug(queue);
+ /* device removal is handled via the ib_client API */
+ break;
default:
dev_err(queue->ctrl->ctrl.device,
"Unexpected RDMA CM event (%d)\n", ev->event);
static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
- int ret;
+ int ret = 0;
+ /*
+ * Keep a reference until all work is flushed since
+ * __nvme_rdma_del_ctrl can free the ctrl mem
+ */
+ if (!kref_get_unless_zero(&ctrl->ctrl.kref))
+ return -EBUSY;
ret = __nvme_rdma_del_ctrl(ctrl);
- if (ret)
- return ret;
-
- flush_work(&ctrl->delete_work);
-
- return 0;
+ if (!ret)
+ flush_work(&ctrl->delete_work);
+ nvme_put_ctrl(&ctrl->ctrl);
+ return ret;
}
static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
.create_ctrl = nvme_rdma_create_ctrl,
};
+static void nvme_rdma_add_one(struct ib_device *ib_device)
+{
+}
+
+static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
+{
+ struct nvme_rdma_ctrl *ctrl;
+
+ /* Delete all controllers using this device */
+ mutex_lock(&nvme_rdma_ctrl_mutex);
+ list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) {
+ if (ctrl->device->dev != ib_device)
+ continue;
+ dev_info(ctrl->ctrl.device,
+ "Removing ctrl: NQN \"%s\", addr %pISp\n",
+ ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ __nvme_rdma_del_ctrl(ctrl);
+ }
+ mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+ flush_workqueue(nvme_rdma_wq);
+}
+
+static struct ib_client nvme_rdma_ib_client = {
+ .name = "nvme_rdma",
+ .add = nvme_rdma_add_one,
+ .remove = nvme_rdma_remove_one
+};
+
static int __init nvme_rdma_init_module(void)
{
+ int ret;
+
nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
if (!nvme_rdma_wq)
return -ENOMEM;
+ ret = ib_register_client(&nvme_rdma_ib_client);
+ if (ret) {
+ destroy_workqueue(nvme_rdma_wq);
+ return ret;
+ }
+
nvmf_register_transport(&nvme_rdma_transport);
return 0;
}
static void __exit nvme_rdma_cleanup_module(void)
{
- struct nvme_rdma_ctrl *ctrl;
-
nvmf_unregister_transport(&nvme_rdma_transport);
-
- mutex_lock(&nvme_rdma_ctrl_mutex);
- list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
- __nvme_rdma_del_ctrl(ctrl);
- mutex_unlock(&nvme_rdma_ctrl_mutex);
-
+ ib_unregister_client(&nvme_rdma_ib_client);
destroy_workqueue(nvme_rdma_wq);
}
list_del(&dev->bus_list);
up_write(&pci_bus_sem);
+ pci_bridge_d3_device_removed(dev);
pci_free_resources(dev);
put_device(&dev->dev);
}
dev->subordinate = NULL;
}
- pci_bridge_d3_device_removed(dev);
-
pci_destroy_dev(dev);
}
/************************ runtime PM support ***************************/
-static int pcmcia_dev_suspend(struct device *dev, pm_message_t state);
+static int pcmcia_dev_suspend(struct device *dev);
static int pcmcia_dev_resume(struct device *dev);
static int runtime_suspend(struct device *dev)
int rc;
device_lock(dev);
- rc = pcmcia_dev_suspend(dev, PMSG_SUSPEND);
+ rc = pcmcia_dev_suspend(dev);
device_unlock(dev);
return rc;
}
/* PM support, also needed for reset */
-static int pcmcia_dev_suspend(struct device *dev, pm_message_t state)
+static int pcmcia_dev_suspend(struct device *dev)
{
struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
struct pcmcia_driver *p_drv = NULL;
.remove_dev = &pcmcia_bus_remove_socket,
};
+static const struct dev_pm_ops pcmcia_bus_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(pcmcia_dev_suspend, pcmcia_dev_resume)
+};
struct bus_type pcmcia_bus_type = {
.name = "pcmcia",
.dev_groups = pcmcia_dev_groups,
.probe = pcmcia_device_probe,
.remove = pcmcia_device_remove,
- .suspend = pcmcia_dev_suspend,
- .resume = pcmcia_dev_resume,
+ .pm = &pcmcia_bus_pm_ops,
};
}
#endif
-void pxa2xx_configure_sockets(struct device *dev)
+void pxa2xx_configure_sockets(struct device *dev, struct pcmcia_low_level *ops)
{
- struct pcmcia_low_level *ops = dev->platform_data;
/*
* We have at least one socket, so set MECR:CIT
* (Card Is There)
goto err1;
}
- pxa2xx_configure_sockets(&dev->dev);
+ pxa2xx_configure_sockets(&dev->dev, ops);
dev_set_drvdata(&dev->dev, sinfo);
return 0;
static int pxa2xx_drv_pcmcia_resume(struct device *dev)
{
- pxa2xx_configure_sockets(dev);
+ struct pcmcia_low_level *ops = (struct pcmcia_low_level *)dev->platform_data;
+
+ pxa2xx_configure_sockets(dev, ops);
return 0;
}
int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt);
void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops);
-void pxa2xx_configure_sockets(struct device *dev);
+void pxa2xx_configure_sockets(struct device *dev, struct pcmcia_low_level *ops);
int pcmcia_badge4_init(struct sa1111_dev *dev)
{
- int ret = -ENODEV;
-
- if (machine_is_badge4()) {
- printk(KERN_INFO
- "%s: badge4_pcmvcc=%d, badge4_pcmvpp=%d, badge4_cfvcc=%d\n",
- __func__,
- badge4_pcmvcc, badge4_pcmvpp, badge4_cfvcc);
-
- sa11xx_drv_pcmcia_ops(&badge4_pcmcia_ops);
- ret = sa1111_pcmcia_add(dev, &badge4_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ printk(KERN_INFO
+ "%s: badge4_pcmvcc=%d, badge4_pcmvpp=%d, badge4_cfvcc=%d\n",
+ __func__,
+ badge4_pcmvcc, badge4_pcmvpp, badge4_cfvcc);
+
+ sa11xx_drv_pcmcia_ops(&badge4_pcmcia_ops);
+ return sa1111_pcmcia_add(dev, &badge4_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
static int __init pcmv_setup(char *s)
#include <mach/hardware.h>
#include <asm/hardware/sa1111.h>
+#include <asm/mach-types.h>
#include <asm/irq.h>
#include "sa1111_generic.h"
sa1111_writel(PCSSR_S0_SLEEP | PCSSR_S1_SLEEP, base + PCSSR);
sa1111_writel(PCCR_S0_FLT | PCCR_S1_FLT, base + PCCR);
+ ret = -ENODEV;
#ifdef CONFIG_SA1100_BADGE4
- pcmcia_badge4_init(dev);
+ if (machine_is_badge4())
+ ret = pcmcia_badge4_init(dev);
#endif
#ifdef CONFIG_SA1100_JORNADA720
- pcmcia_jornada720_init(dev);
+ if (machine_is_jornada720())
+ ret = pcmcia_jornada720_init(dev);
#endif
#ifdef CONFIG_ARCH_LUBBOCK
- pcmcia_lubbock_init(dev);
+ if (machine_is_lubbock())
+ ret = pcmcia_lubbock_init(dev);
#endif
#ifdef CONFIG_ASSABET_NEPONSET
- pcmcia_neponset_init(dev);
+ if (machine_is_assabet())
+ ret = pcmcia_neponset_init(dev);
#endif
- return 0;
+
+ if (ret) {
+ release_mem_region(dev->res.start, 512);
+ sa1111_disable_device(dev);
+ }
+
+ return ret;
}
static int pcmcia_remove(struct sa1111_dev *dev)
int pcmcia_jornada720_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
+ unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3;
- if (machine_is_jornada720()) {
- unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3;
+ /* Fixme: why messing around with SA11x0's GPIO1? */
+ GRER |= 0x00000002;
- GRER |= 0x00000002;
+ /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */
+ sa1111_set_io_dir(sadev, pin, 0, 0);
+ sa1111_set_io(sadev, pin, 0);
+ sa1111_set_sleep_io(sadev, pin, 0);
- /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */
- sa1111_set_io_dir(sadev, pin, 0, 0);
- sa1111_set_io(sadev, pin, 0);
- sa1111_set_sleep_io(sadev, pin, 0);
-
- sa11xx_drv_pcmcia_ops(&jornada720_pcmcia_ops);
- ret = sa1111_pcmcia_add(sadev, &jornada720_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ sa11xx_drv_pcmcia_ops(&jornada720_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &jornada720_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
int pcmcia_lubbock_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
-
- if (machine_is_lubbock()) {
- /*
- * Set GPIO_A<3:0> to be outputs for the MAX1600,
- * and switch to standby mode.
- */
- sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
- sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
-
- /* Set CF Socket 1 power to standby mode. */
- lubbock_set_misc_wr((1 << 15) | (1 << 14), 0);
+ /*
+ * Set GPIO_A<3:0> to be outputs for the MAX1600,
+ * and switch to standby mode.
+ */
+ sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
+ sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops);
- pxa2xx_configure_sockets(&sadev->dev);
- ret = sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops,
- pxa2xx_drv_pcmcia_add_one);
- }
+ /* Set CF Socket 1 power to standby mode. */
+ lubbock_set_misc_wr((1 << 15) | (1 << 14), 0);
- return ret;
+ pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops);
+ pxa2xx_configure_sockets(&sadev->dev, &lubbock_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops,
+ pxa2xx_drv_pcmcia_add_one);
}
MODULE_LICENSE("GPL");
int pcmcia_neponset_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
-
- if (machine_is_assabet()) {
- /*
- * Set GPIO_A<3:0> to be outputs for the MAX1600,
- * and switch to standby mode.
- */
- sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
- sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa11xx_drv_pcmcia_ops(&neponset_pcmcia_ops);
- ret = sa1111_pcmcia_add(sadev, &neponset_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ /*
+ * Set GPIO_A<3:0> to be outputs for the MAX1600,
+ * and switch to standby mode.
+ */
+ sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
+ sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa11xx_drv_pcmcia_ops(&neponset_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &neponset_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
sa1100_pcmcia_show_timing(struct soc_pcmcia_socket *skt, char *buf)
{
struct soc_pcmcia_timing timing;
- unsigned int clock = clk_get_rate(skt->clk);
+ unsigned int clock = clk_get_rate(skt->clk) / 1000;
unsigned long mecr = MECR;
char *p = buf;
soc_common_pcmcia_get_timing(skt, &timing);
- p+=sprintf(p, "I/O : %u (%u)\n", timing.io,
+ p+=sprintf(p, "I/O : %uns (%uns)\n", timing.io,
sa1100_pcmcia_cmd_time(clock, MECR_BSIO_GET(mecr, skt->nr)));
- p+=sprintf(p, "attribute: %u (%u)\n", timing.attr,
+ p+=sprintf(p, "attribute: %uns (%uns)\n", timing.attr,
sa1100_pcmcia_cmd_time(clock, MECR_BSA_GET(mecr, skt->nr)));
- p+=sprintf(p, "common : %u (%u)\n", timing.mem,
+ p+=sprintf(p, "common : %uns (%uns)\n", timing.mem,
sa1100_pcmcia_cmd_time(clock, MECR_BSM_GET(mecr, skt->nr)));
return p - buf;
stat |= skt->cs_state.Vcc ? SS_POWERON : 0;
if (skt->cs_state.flags & SS_IOCARD)
- stat |= state.bvd1 ? SS_STSCHG : 0;
+ stat |= state.bvd1 ? 0 : SS_STSCHG;
else {
if (state.bvd1 == 0)
stat |= SS_BATDEAD;
{
struct rio_channel *ch;
unsigned int i;
+ LIST_HEAD(list);
riocm_debug(EXIT, ".");
+ /*
+ * If there are any channels left in connected state send
+ * close notification to the connection partner.
+ * First build a list of channels that require a closing
+ * notification because function riocm_send_close() should
+ * be called outside of spinlock protected code.
+ */
spin_lock_bh(&idr_lock);
idr_for_each_entry(&ch_idr, ch, i) {
- riocm_debug(EXIT, "close ch %d", ch->id);
- if (ch->state == RIO_CM_CONNECTED)
- riocm_send_close(ch);
+ if (ch->state == RIO_CM_CONNECTED) {
+ riocm_debug(EXIT, "close ch %d", ch->id);
+ idr_remove(&ch_idr, ch->id);
+ list_add(&ch->ch_node, &list);
+ }
}
spin_unlock_bh(&idr_lock);
+ list_for_each_entry(ch, &list, ch_node)
+ riocm_send_close(ch);
+
return NOTIFY_DONE;
}
memcpy(&endpoint->desc, d, n);
INIT_LIST_HEAD(&endpoint->urb_list);
- /* Fix up bInterval values outside the legal range. Use 32 ms if no
- * proper value can be guessed. */
+ /*
+ * Fix up bInterval values outside the legal range.
+ * Use 10 or 8 ms if no proper value can be guessed.
+ */
i = 0; /* i = min, j = max, n = default */
j = 255;
if (usb_endpoint_xfer_int(d)) {
case USB_SPEED_SUPER_PLUS:
case USB_SPEED_SUPER:
case USB_SPEED_HIGH:
- /* Many device manufacturers are using full-speed
+ /*
+ * Many device manufacturers are using full-speed
* bInterval values in high-speed interrupt endpoint
- * descriptors. Try to fix those and fall back to a
- * 32 ms default value otherwise. */
+ * descriptors. Try to fix those and fall back to an
+ * 8-ms default value otherwise.
+ */
n = fls(d->bInterval*8);
if (n == 0)
- n = 9; /* 32 ms = 2^(9-1) uframes */
+ n = 7; /* 8 ms = 2^(7-1) uframes */
j = 16;
/*
}
break;
default: /* USB_SPEED_FULL or _LOW */
- /* For low-speed, 10 ms is the official minimum.
+ /*
+ * For low-speed, 10 ms is the official minimum.
* But some "overclocked" devices might want faster
- * polling so we'll allow it. */
- n = 32;
+ * polling so we'll allow it.
+ */
+ n = 10;
break;
}
} else if (usb_endpoint_xfer_isoc(d)) {
j = 16;
switch (to_usb_device(ddev)->speed) {
case USB_SPEED_HIGH:
- n = 9; /* 32 ms = 2^(9-1) uframes */
+ n = 7; /* 8 ms = 2^(7-1) uframes */
break;
default: /* USB_SPEED_FULL */
- n = 6; /* 32 ms = 2^(6-1) frames */
+ n = 4; /* 8 ms = 2^(4-1) frames */
break;
}
}
config USB_MUSB_TUSB6010
tristate "TUSB6010"
depends on HAS_IOMEM
- depends on ARCH_OMAP2PLUS || COMPILE_TEST
+ depends on (ARCH_OMAP2PLUS || COMPILE_TEST) && !BLACKFIN
depends on NOP_USB_XCEIV = USB_MUSB_HDRC # both built-in or both modules
config USB_MUSB_OMAP2PLUS
/* Infineon Flashloader driver */
#define FLASHLOADER_IDS() \
{ USB_DEVICE_INTERFACE_CLASS(0x058b, 0x0041, USB_CLASS_CDC_DATA) }, \
- { USB_DEVICE(0x8087, 0x0716) }
+ { USB_DEVICE(0x8087, 0x0716) }, \
+ { USB_DEVICE(0x8087, 0x0801) }
DEVICE(flashloader, FLASHLOADER_IDS);
/* Google Serial USB SubClass */
static const struct dentry_operations ops = {
.d_dname = simple_dname,
};
- return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+ struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+ AIO_RING_MAGIC);
+
+ if (!IS_ERR(root))
+ root->d_sb->s_iflags |= SB_I_NOEXEC;
+ return root;
}
/* aio_setup
}
return NULL;
}
+
/*
* Find an eligible tree to time-out
* A tree is eligible if :-
struct dentry *root = sb->s_root;
struct dentry *dentry;
struct dentry *expired;
+ struct dentry *found;
struct autofs_info *ino;
if (!root)
dentry = NULL;
while ((dentry = get_next_positive_subdir(dentry, root))) {
+ int flags = how;
+
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
- if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
- expired = NULL;
- else
- expired = should_expire(dentry, mnt, timeout, how);
- if (!expired) {
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
spin_unlock(&sbi->fs_lock);
continue;
}
+ spin_unlock(&sbi->fs_lock);
+
+ expired = should_expire(dentry, mnt, timeout, flags);
+ if (!expired)
+ continue;
+
+ spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(expired);
ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
- spin_lock(&sbi->fs_lock);
- if (should_expire(expired, mnt, timeout, how)) {
- if (expired != dentry)
- dput(dentry);
- goto found;
- }
+ /* Make sure a reference is not taken on found if
+ * things have changed.
+ */
+ flags &= ~AUTOFS_EXP_LEAVES;
+ found = should_expire(expired, mnt, timeout, how);
+ if (!found || found != expired)
+ /* Something has changed, continue */
+ goto next;
+
+ if (expired != dentry)
+ dput(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ goto found;
+next:
+ spin_lock(&sbi->fs_lock);
ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
+ spin_unlock(&sbi->fs_lock);
if (expired != dentry)
dput(expired);
- spin_unlock(&sbi->fs_lock);
}
return NULL;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
+ int state;
/* Block on any pending expire */
if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
if (rcu_walk)
return -ECHILD;
+retry:
spin_lock(&sbi->fs_lock);
- if (ino->flags & AUTOFS_INF_EXPIRING) {
+ state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+ if (state == AUTOFS_INF_WANT_EXPIRE) {
+ spin_unlock(&sbi->fs_lock);
+ /*
+ * Possibly being selected for expire, wait until
+ * it's selected or not.
+ */
+ schedule_timeout_uninterruptible(HZ/10);
+ goto retry;
+ }
+ if (state & AUTOFS_INF_EXPIRING) {
spin_unlock(&sbi->fs_lock);
pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
char *s, *p;
char sep;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+ return dget(sb->s_root);
+
full_path = cifs_build_path_to_root(vol, cifs_sb,
cifs_sb_master_tcon(cifs_sb));
if (full_path == NULL)
cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
if (cifs_sb->mountdata == NULL) {
root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
+ goto out_free;
}
- if (volume_info->prepath) {
- cifs_sb->prepath = kstrdup(volume_info->prepath, GFP_KERNEL);
- if (cifs_sb->prepath == NULL) {
- root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
- }
+ rc = cifs_setup_cifs_sb(volume_info, cifs_sb);
+ if (rc) {
+ root = ERR_PTR(rc);
+ goto out_free;
}
- cifs_setup_cifs_sb(volume_info, cifs_sb);
-
rc = cifs_mount(cifs_sb, volume_info);
if (rc) {
if (!(flags & MS_SILENT))
cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
rc);
root = ERR_PTR(rc);
- goto out_mountdata;
+ goto out_free;
}
mnt_data.vol = volume_info;
sb->s_flags |= MS_ACTIVE;
}
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
- root = dget(sb->s_root);
- else
- root = cifs_get_root(volume_info, sb);
-
+ root = cifs_get_root(volume_info, sb);
if (IS_ERR(root))
goto out_super;
cifs_cleanup_volume_info(volume_info);
return root;
-out_mountdata:
+out_free:
+ kfree(cifs_sb->prepath);
kfree(cifs_sb->mountdata);
-out_cifs_sb:
kfree(cifs_sb);
out_nls:
unload_nls(volume_info->local_nls);
unsigned int to_read);
extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
struct page *page, unsigned int to_read);
-extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb);
extern int cifs_match_super(struct super_block *, void *);
extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info);
return 1;
}
+static int
+match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
+{
+ struct cifs_sb_info *old = CIFS_SB(sb);
+ struct cifs_sb_info *new = mnt_data->cifs_sb;
+
+ if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
+ if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
+ return 0;
+ /* The prepath should be null terminated strings */
+ if (strcmp(new->prepath, old->prepath))
+ return 0;
+
+ return 1;
+ }
+ return 0;
+}
+
int
cifs_match_super(struct super_block *sb, void *data)
{
if (!match_server(tcp_srv, volume_info) ||
!match_session(ses, volume_info) ||
- !match_tcon(tcon, volume_info->UNC)) {
+ !match_tcon(tcon, volume_info->UNC) ||
+ !match_prepath(sb, mnt_data)) {
rc = 0;
goto out;
}
}
}
-void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb)
{
INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
cifs_dbg(VFS, "mount option dynperm ignored if cifsacl mount option supported\n");
+
+ if (pvolume_info->prepath) {
+ cifs_sb->prepath = kstrdup(pvolume_info->prepath, GFP_KERNEL);
+ if (cifs_sb->prepath == NULL)
+ return -ENOMEM;
+ }
+
+ return 0;
}
static void
return thaw_super(sb);
}
-static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
{
struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
}
size = offsetof(struct file_dedupe_range __user, info[count]);
+ if (size > PAGE_SIZE) {
+ ret = -ENOMEM;
+ goto out;
+ }
same = memdup_user(argp, size);
if (IS_ERR(same)) {
if (result <= 0)
goto out;
- written = generic_write_sync(iocb, result);
+ result = generic_write_sync(iocb, result);
+ if (result < 0)
+ goto out;
+ written = result;
iocb->ki_pos += written;
/* Return error values */
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
trace_nfs4_create_session(clp, status);
+ switch (status) {
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_DELAY:
+ case -ETIMEDOUT:
+ case -EACCES:
+ case -EAGAIN:
+ goto out;
+ };
+
+ clp->cl_seqid++;
if (!status) {
/* Verify the session's negotiated channel_attrs values */
status = nfs4_verify_channel_attrs(&args, &res);
/* Increment the clientid slot sequence id */
- if (clp->cl_seqid == res.seqid)
- clp->cl_seqid++;
if (status)
goto out;
nfs4_update_session(session, &res);
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
- be32_to_cpu(lrp->args.stateid.seqid));
- if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
+ if (lrp->res.lrs_present) {
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme,
+ &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+ } else
+ pnfs_mark_layout_stateid_invalid(lo, &freeme);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&lo->plh_inode->i_lock);
nfs4_sequence_free_slot(&lrp->res.seq_res);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs)) {
- set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ if (atomic_read(&lo->plh_outstanding) == 0)
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
pnfs_destroy_layouts_byclid(clp, false);
}
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+ lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
+ clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier = 0;
- bool invalid = !pnfs_layout_is_valid(lo);
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
- if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
+
+ if (!pnfs_layout_is_valid(lo)) {
+ nfs4_stateid_copy(&lo->plh_stateid, new);
+ lo->plh_barrier = newseq;
+ pnfs_clear_layoutreturn_info(lo);
+ clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ return;
+ }
+ if (pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
/*
* Because of wraparound, we want to keep the barrier
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+ if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
-static void
-pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
-{
- lo->plh_return_iomode = 0;
- lo->plh_return_seq = 0;
- clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-}
-
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
nfs4_stateid *stateid,
enum pnfs_iomode *iomode)
{
+ /* Serialise LAYOUTGET/LAYOUTRETURN */
+ if (atomic_read(&lo->plh_outstanding) != 0)
+ return false;
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
pnfs_get_layout_hdr(lo);
*/
pnfs_mark_layout_stateid_invalid(lo, &free_me);
- nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
- lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+ pnfs_set_layout_stateid(lo, &res->stateid, true);
}
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg, &free_me);
- if (!pnfs_layout_is_valid(lo)) {
- pnfs_clear_layoutreturn_info(lo);
- clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- }
if (res->return_on_close)
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- wait_event(group->fanotify_data.access_waitq, event->response ||
- atomic_read(&group->fanotify_data.bypass_perm));
-
- if (!event->response) { /* bypass_perm set */
- /*
- * Event was canceled because group is being destroyed. Remove
- * it from group's event list because we are responsible for
- * freeing the permission event.
- */
- fsnotify_remove_event(group, &event->fae.fse);
- return 0;
- }
+ wait_event(group->fanotify_data.access_waitq, event->response);
/* userspace responded, convert to something usable */
switch (event->response) {
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_perm_event_info *event, *next;
+ struct fsnotify_event *fsn_event;
/*
- * There may be still new events arriving in the notification queue
- * but since userspace cannot use fanotify fd anymore, no event can
- * enter or leave access_list by now.
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
*/
- spin_lock(&group->fanotify_data.access_lock);
-
- atomic_inc(&group->fanotify_data.bypass_perm);
+ fsnotify_group_stop_queueing(group);
+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->fanotify_data.access_lock);
list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
fae.fse.list) {
pr_debug("%s: found group=%p event=%p\n", __func__, group,
spin_unlock(&group->fanotify_data.access_lock);
/*
- * Since bypass_perm is set, newly queued events will not wait for
- * access response. Wake up the already sleeping ones now.
- * synchronize_srcu() in fsnotify_destroy_group() will wait for all
- * processes sleeping in fanotify_handle_event() waiting for access
- * response and thus also for all permission events to be freed.
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
*/
+ mutex_lock(&group->notification_mutex);
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ fsn_event = fsnotify_remove_first_event(group);
+ if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+ fsnotify_destroy_event(group, fsn_event);
+ else
+ FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ }
+ mutex_unlock(&group->notification_mutex);
+
+ /* Response for all permission events it set, wakeup waiters */
wake_up(&group->fanotify_data.access_waitq);
#endif
spin_lock_init(&group->fanotify_data.access_lock);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
- atomic_set(&group->fanotify_data.bypass_perm, 0);
#endif
switch (flags & FAN_ALL_CLASS_BITS) {
case FAN_CLASS_NOTIF:
kfree(group);
}
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+ mutex_lock(&group->notification_mutex);
+ group->shutdown = true;
+ mutex_unlock(&group->notification_mutex);
+}
+
/*
* Trying to get rid of a group. Remove all marks, flush all events and release
* the group reference.
*/
void fsnotify_destroy_group(struct fsnotify_group *group)
{
+ /*
+ * Stop queueing new events. The code below is careful enough to not
+ * require this but fanotify needs to stop queuing events even before
+ * fsnotify_destroy_group() is called and this makes the other callers
+ * of fsnotify_destroy_group() to see the same behavior.
+ */
+ fsnotify_group_stop_queueing(group);
+
/* clear all inode marks for this group, attach them to destroy_list */
fsnotify_detach_group_marks(group);
* Add an event to the group notification queue. The group can later pull this
* event off the queue to deal with. The function returns 0 if the event was
* added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
*/
int fsnotify_add_event(struct fsnotify_group *group,
struct fsnotify_event *event,
mutex_lock(&group->notification_mutex);
+ if (group->shutdown) {
+ mutex_unlock(&group->notification_mutex);
+ return 2;
+ }
+
if (group->q_len >= group->max_events) {
ret = 2;
/* Queue overflow event only if it isn't already queued */
return ret;
}
-/*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
- struct fsnotify_event *event)
-{
- mutex_lock(&group->notification_mutex);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- group->q_len--;
- }
- mutex_unlock(&group->notification_mutex);
-}
-
/*
* Remove and return the first event from the notification list. It is the
* responsibility of the caller to destroy the obtained event
}
static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
- handle_t *handle,
struct inode *data_alloc_inode,
struct buffer_head *data_alloc_bh)
{
struct ocfs2_truncate_log *tl;
struct inode *tl_inode = osb->osb_tl_inode;
struct buffer_head *tl_bh = osb->osb_tl_bh;
+ handle_t *handle;
di = (struct ocfs2_dinode *) tl_bh->b_data;
tl = &di->id2.i_dealloc;
i = le16_to_cpu(tl->tl_used) - 1;
while (i >= 0) {
+ handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail;
+ }
+
/* Caller has given us at least enough credits to
* update the truncate log dinode */
status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
}
}
- status = ocfs2_extend_trans(handle,
- OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
+ ocfs2_commit_trans(osb, handle);
i--;
}
{
int status;
unsigned int num_to_flush;
- handle_t *handle;
struct inode *tl_inode = osb->osb_tl_inode;
struct inode *data_alloc_inode = NULL;
struct buffer_head *tl_bh = osb->osb_tl_bh;
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (IS_ERR(handle)) {
- status = PTR_ERR(handle);
- mlog_errno(status);
- goto out_unlock;
- }
-
- status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
+ status = ocfs2_replay_truncate_records(osb, data_alloc_inode,
data_alloc_bh);
if (status < 0)
mlog_errno(status);
- ocfs2_commit_trans(osb, handle);
-
-out_unlock:
brelse(data_alloc_bh);
ocfs2_inode_unlock(data_alloc_inode, 1);
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto out_unlock;
- }
-
while (head) {
if (head->free_bg)
bg_blkno = head->free_bg;
else
bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
head->free_bit);
+ handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto out_unlock;
+ }
+
trace_ocfs2_free_cached_blocks(
(unsigned long long)head->free_blk, head->free_bit);
ret = ocfs2_free_suballoc_bits(handle, inode, di_bh,
head->free_bit, bg_blkno, 1);
- if (ret) {
+ if (ret)
mlog_errno(ret);
- goto out_journal;
- }
- ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE);
- if (ret) {
- mlog_errno(ret);
- goto out_journal;
- }
+ ocfs2_commit_trans(osb, handle);
tmp = head;
head = head->free_next;
kfree(tmp);
}
-out_journal:
- ocfs2_commit_trans(osb, handle);
-
out_unlock:
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
* version here in tcp_internal.h should not need to be bumped for
* filesystem locking changes.
*
- * New in version 12
- * - Negotiate hb timeout when storage is down.
- *
* New in version 11
* - Negotiation of filesystem locking in the dlm join.
*
* - full 64 bit i_size in the metadata lock lvbs
* - introduction of "rw" lock and pushing meta/data locking down
*/
-#define O2NET_PROTOCOL_VERSION 12ULL
+#define O2NET_PROTOCOL_VERSION 11ULL
struct o2net_handshake {
__be64 protocol_version;
__be64 connector_id;
struct dlm_lock *lock, int flags, int type)
{
enum dlm_status status;
- u8 old_owner = res->owner;
mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
spin_lock(&res->spinlock);
res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
- lock->convert_pending = 0;
/* if it failed, move it back to granted queue.
* if master returns DLM_NORMAL and then down before sending ast,
* it may have already been moved to granted queue, reset to
if (status != DLM_NOTQUEUED)
dlm_error(status);
dlm_revert_pending_convert(res, lock);
- } else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
- (old_owner != res->owner)) {
- mlog(0, "res %.*s is in recovering or has been recovered.\n",
- res->lockname.len, res->lockname.name);
+ } else if (!lock->convert_pending) {
+ mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+ "to granted list, retry convert.\n",
+ dlm->name, res->lockname.len, res->lockname.name);
status = DLM_RECOVERING;
}
+
+ lock->convert_pending = 0;
bail:
spin_unlock(&res->spinlock);
u64 start, u64 len)
{
int ret = 0;
- u64 tmpend, end = start + len;
+ u64 tmpend = 0;
+ u64 end = start + len;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
}
/*
- * We want to get the byte offset of the end of the 1st cluster.
+ * If start is on a cluster boundary and end is somewhere in another
+ * cluster, we have not COWed the cluster starting at start, unless
+ * end is also within the same cluster. So, in this case, we skip this
+ * first call to ocfs2_zero_range_for_truncate() truncate and move on
+ * to the next one.
*/
- tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
- if (tmpend > end)
- tmpend = end;
+ if ((start & (csize - 1)) != 0) {
+ /*
+ * We want to get the byte offset of the end of the 1st
+ * cluster.
+ */
+ tmpend = (u64)osb->s_clustersize +
+ (start & ~(osb->s_clustersize - 1));
+ if (tmpend > end)
+ tmpend = end;
- trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
- (unsigned long long)tmpend);
+ trace_ocfs2_zero_partial_clusters_range1(
+ (unsigned long long)start,
+ (unsigned long long)tmpend);
- ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
- if (ret)
- mlog_errno(ret);
+ ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+ tmpend);
+ if (ret)
+ mlog_errno(ret);
+ }
if (tmpend < end) {
/*
inode_unlock((*ac)->ac_inode);
ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
- if (ret == 1)
+ if (ret == 1) {
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
goto retry;
+ }
if (ret < 0)
mlog_errno(ret);
inode_lock((*ac)->ac_inode);
- ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ inode_unlock((*ac)->ac_inode);
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
+ goto bail;
+ }
}
if (status < 0) {
if (status != -ENOSPC)
static ssize_t
read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
{
+ char *buf = file->private_data;
ssize_t acc = 0;
size_t size, tsz;
size_t elf_buflen;
if (clear_user(buffer, tsz))
return -EFAULT;
} else if (is_vmalloc_or_module_addr((void *)start)) {
- char * elf_buf;
-
- elf_buf = kzalloc(tsz, GFP_KERNEL);
- if (!elf_buf)
- return -ENOMEM;
- vread(elf_buf, (char *)start, tsz);
+ vread(buf, (char *)start, tsz);
/* we have to zero-fill user buffer even if no read */
- if (copy_to_user(buffer, elf_buf, tsz)) {
- kfree(elf_buf);
+ if (copy_to_user(buffer, buf, tsz))
return -EFAULT;
- }
- kfree(elf_buf);
} else {
if (kern_addr_valid(start)) {
unsigned long n;
- n = copy_to_user(buffer, (char *)start, tsz);
+ /*
+ * Using bounce buffer to bypass the
+ * hardened user copy kernel text checks.
+ */
+ memcpy(buf, (char *) start, tsz);
+ n = copy_to_user(buffer, buf, tsz);
/*
* We cannot distinguish between fault on source
* and fault on destination. When this happens
{
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
+
+ filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
return 0;
}
+static int release_kcore(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
static const struct file_operations proc_kcore_operations = {
.read = read_kcore,
.open = open_kcore,
+ .release = release_kcore,
.llseek = default_llseek,
};
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/ramfs.h>
+#include <linux/sched.h>
#include "internal.h"
+static unsigned long ramfs_mmu_get_unmapped_area(struct file *file,
+ unsigned long addr, unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
const struct file_operations ramfs_file_operations = {
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = generic_file_llseek,
+ .get_unmapped_area = ramfs_mmu_get_unmapped_area,
};
const struct inode_operations ramfs_file_inode_operations = {
might_fault(); \
access_ok(VERIFY_READ, __p, sizeof(*ptr)) ? \
__get_user((x), (__typeof__(*(ptr)) *)__p) : \
- -EFAULT; \
+ ((x) = (__typeof__(*(ptr)))0,-EFAULT); \
})
#ifndef __get_user_fn
static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
{
- size = __copy_from_user(x, ptr, size);
- return size ? -EFAULT : size;
+ size_t n = __copy_from_user(x, ptr, size);
+ if (unlikely(n)) {
+ memset(x + (size - n), 0, n);
+ return -EFAULT;
+ }
+ return 0;
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
static inline long copy_from_user(void *to,
const void __user * from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- else
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to,
* object's lifetime is managed by something other than RCU. That
* "something other" might be reference counting or simple immortality.
*
- * The seemingly unused size_t variable is to validate @p is indeed a pointer
- * type by making sure it can be dereferenced.
+ * The seemingly unused variable ___typecheck_p validates that @p is
+ * indeed a pointer type by using a pointer to typeof(*p) as the type.
+ * Taking a pointer to typeof(*p) again is needed in case p is void *.
*/
#define lockless_dereference(p) \
({ \
typeof(p) _________p1 = READ_ONCE(p); \
- size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \
+ typeof(*(p)) *___typecheck_p __maybe_unused; \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
#ifndef __CPUHOTPLUG_H
#define __CPUHOTPLUG_H
+#include <linux/types.h>
+
enum cpuhp_state {
CPUHP_OFFLINE,
CPUHP_CREATE_THREADS,
u32 imagesize;
} efi_capsule_header_t;
+struct efi_boot_memmap {
+ efi_memory_desc_t **map;
+ unsigned long *map_size;
+ unsigned long *desc_size;
+ u32 *desc_ver;
+ unsigned long *key_ptr;
+ unsigned long *buff_size;
+};
+
/*
* EFI capsule flags
*/
/* Iterate through an efi_memory_map */
#define for_each_efi_memory_desc_in_map(m, md) \
for ((md) = (m)->map; \
- ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
+ (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
(md) = (void *)(md) + (m)->desc_size)
/**
efi_loaded_image_t *image, int *cmd_line_len);
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr);
+ struct efi_boot_memmap *map);
efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
unsigned long size, unsigned long align,
arch_efi_call_virt_teardown(); \
})
+typedef efi_status_t (*efi_exit_boot_map_processing)(
+ efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv);
+
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func);
#endif /* _LINUX_EFI_H */
#define FS_PRIO_1 1 /* fanotify content based access control */
#define FS_PRIO_2 2 /* fanotify pre-content access */
unsigned int priority;
+ bool shutdown; /* group is being shut down, don't queue more events */
/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
struct mutex mark_mutex; /* protect marks_list */
spinlock_t access_lock;
struct list_head access_list;
wait_queue_head_t access_waitq;
- atomic_t bypass_perm;
#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
int f_flags;
unsigned int max_marks;
extern void fsnotify_get_group(struct fsnotify_group *group);
/* drop reference on a group from fsnotify_alloc_group */
extern void fsnotify_put_group(struct fsnotify_group *group);
+/* group destruction begins, stop queuing new events */
+extern void fsnotify_group_stop_queueing(struct fsnotify_group *group);
/* destroy group */
extern void fsnotify_destroy_group(struct fsnotify_group *group);
/* fasync handler function */
struct fsnotify_event *event,
int (*merge)(struct list_head *,
struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
/* true if the group notification queue is empty */
extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
/* return, but do not dequeue the first event on the notification queue */
static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
#endif
+/*
+ * The irqsave variants are for usage in non interrupt code. Do not use
+ * them in irq_chip callbacks. Use irq_gc_lock() instead.
+ */
+#define irq_gc_lock_irqsave(gc, flags) \
+ raw_spin_lock_irqsave(&(gc)->lock, flags)
+
+#define irq_gc_unlock_irqrestore(gc, flags) \
+ raw_spin_unlock_irqrestore(&(gc)->lock, flags)
+
static inline void irq_reg_writel(struct irq_chip_generic *gc,
u32 val, int reg_offset)
{
*/
static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
{
- int ret = 0;
char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
- return ret;
+ return 0;
+ if (unlikely(uaddr > end))
+ return -EFAULT;
/*
* Writing zeroes into userspace here is OK, because we know that if
* the zero gets there, we'll be overwriting it.
*/
- while (uaddr <= end) {
- ret = __put_user(0, uaddr);
- if (ret != 0)
- return ret;
+ do {
+ if (unlikely(__put_user(0, uaddr) != 0))
+ return -EFAULT;
uaddr += PAGE_SIZE;
- }
+ } while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK))
- ret = __put_user(0, end);
+ return __put_user(0, end);
- return ret;
+ return 0;
}
static inline int fault_in_multipages_readable(const char __user *uaddr,
int size)
{
volatile char c;
- int ret = 0;
const char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
- return ret;
+ return 0;
- while (uaddr <= end) {
- ret = __get_user(c, uaddr);
- if (ret != 0)
- return ret;
+ if (unlikely(uaddr > end))
+ return -EFAULT;
+
+ do {
+ if (unlikely(__get_user(c, uaddr) != 0))
+ return -EFAULT;
uaddr += PAGE_SIZE;
- }
+ } while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK)) {
- ret = __get_user(c, end);
- (void)c;
+ return __get_user(c, end);
}
- return ret;
+ return 0;
}
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes);
+#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
if (cgroup_sk_alloc_disabled)
return;
+ /* Socket clone path */
+ if (skcd->val) {
+ cgroup_get(sock_cgroup_ptr(skcd));
+ return;
+ }
+
rcu_read_lock();
while (true) {
return 0;
}
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
{
struct stop_event_data sd = {
.event = event,
- .restart = 1,
+ .restart = restart,
};
int ret = 0;
.group = group,
.ret = 0,
};
- ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
- /* The event must have been read from an online CPU: */
- WARN_ON_ONCE(ret);
- ret = ret ? : data.ret;
+ /*
+ * Purposely ignore the smp_call_function_single() return
+ * value.
+ *
+ * If event->oncpu isn't a valid CPU it means the event got
+ * scheduled out and that will have updated the event count.
+ *
+ * Therefore, either way, we'll have an up-to-date event count
+ * after this.
+ */
+ (void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+ ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
spin_unlock_irqrestore(&rb->event_lock, flags);
}
+ /*
+ * Avoid racing with perf_mmap_close(AUX): stop the event
+ * before swizzling the event::rb pointer; if it's getting
+ * unmapped, its aux_mmap_count will be 0 and it won't
+ * restart. See the comment in __perf_pmu_output_stop().
+ *
+ * Data will inevitably be lost when set_output is done in
+ * mid-air, but then again, whoever does it like this is
+ * not in for the data anyway.
+ */
+ if (has_aux(event))
+ perf_event_stop(event, 0);
+
rcu_assign_pointer(event->rb, rb);
if (old_rb) {
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
void perf_event_exec(void)
/*
* In case of inheritance, it will be the parent that links to the
- * ring-buffer, but it will be the child that's actually using it:
+ * ring-buffer, but it will be the child that's actually using it.
+ *
+ * We are using event::rb to determine if the event should be stopped,
+ * however this may race with ring_buffer_attach() (through set_output),
+ * which will make us skip the event that actually needs to be stopped.
+ * So ring_buffer_attach() has to stop an aux event before re-assigning
+ * its rb pointer.
*/
if (rcu_dereference(parent->rb) == rb)
ro->err = __perf_event_stop(&sd);
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
mmput(mm);
restart:
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
if (!rb)
return NULL;
- if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+ if (!rb_has_aux(rb))
goto err;
/*
- * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
- * the aux buffer is in perf_mmap_close(), about to get freed.
+ * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+ * about to get freed, so we leave immediately.
+ *
+ * Checking rb::aux_mmap_count and rb::refcount has to be done in
+ * the same order, see perf_mmap_close. Otherwise we end up freeing
+ * aux pages in this path, which is a bug, because in_atomic().
*/
if (!atomic_read(&rb->aux_mmap_count))
- goto err_put;
+ goto err;
+
+ if (!atomic_inc_not_zero(&rb->aux_refcount))
+ goto err;
/*
* Nesting is not supported for AUX area, make sure nested
success = 1; /* we're going to change ->state */
cpu = task_cpu(p);
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * [S] p->on_rq = 1; [L] P->state
+ * UNLOCK rq->lock -----.
+ * \
+ * +--- RMB
+ * schedule() /
+ * LOCK rq->lock -----'
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ *
+ * Pairs with the UNLOCK+LOCK on rq->lock from the
+ * last wakeup of our task and the schedule that got our task
+ * current.
+ */
+ smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
goto stat;
return wanted - bytes;
}
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
- if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
- char __user *buf = i->iov->iov_base + i->iov_offset;
- bytes = min(bytes, i->iov->iov_len - i->iov_offset);
- return fault_in_pages_readable(buf, bytes);
- }
- return 0;
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
/*
* Fault in one or more iovecs of the given iov_iter, to a maximum length of
* bytes. For each iovec, fault in each page that constitutes the iovec.
* Return 0 on success, or non-zero if the memory could not be accessed (i.e.
* because it is an invalid address).
*/
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes)
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
{
size_t skip = i->iov_offset;
const struct iovec *iov;
}
return 0;
}
-EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable);
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
void iov_iter_init(struct iov_iter *i, int direction,
const struct iovec *iov, unsigned long nr_segs,
void __dump_page(struct page *page, const char *reason)
{
+ int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
- page, page_ref_count(page), page_mapcount(page),
- page->mapping, page->index);
+ page, page_ref_count(page), mapcount,
+ page->mapping, page_to_pgoff(page));
if (PageCompound(page))
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
pr_cont("\n");
* value (scan code).
*/
-static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address)
+static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
+ struct vm_area_struct **vmap)
{
struct vm_area_struct *vma;
unsigned long hstart, hend;
if (unlikely(khugepaged_test_exit(mm)))
return SCAN_ANY_PROCESS;
- vma = find_vma(mm, address);
+ *vmap = vma = find_vma(mm, address);
if (!vma)
return SCAN_VMA_NULL;
.pmd = pmd,
};
+ /* we only decide to swapin, if there is enough young ptes */
+ if (referenced < HPAGE_PMD_NR/2) {
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
+ return false;
+ }
fe.pte = pte_offset_map(pmd, address);
for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE;
fe.pte++, fe.address += PAGE_SIZE) {
if (!is_swap_pte(pteval))
continue;
swapped_in++;
- /* we only decide to swapin, if there is enough young ptes */
- if (referenced < HPAGE_PMD_NR/2) {
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return false;
- }
ret = do_swap_page(&fe, pteval);
/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
if (ret & VM_FAULT_RETRY) {
down_read(&mm->mmap_sem);
- if (hugepage_vma_revalidate(mm, address)) {
+ if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
/* vma is no longer available, don't continue to swapin */
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
return false;
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
- struct vm_area_struct *vma,
int node, int referenced)
{
pmd_t *pmd, _pmd;
spinlock_t *pmd_ptl, *pte_ptl;
int isolated = 0, result = 0;
struct mem_cgroup *memcg;
+ struct vm_area_struct *vma;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
gfp_t gfp;
}
down_read(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result) {
mem_cgroup_cancel_charge(new_page, memcg, true);
up_read(&mm->mmap_sem);
* handled by the anon_vma lock + PG_lock.
*/
down_write(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result)
goto out;
/* check if the pmd is still valid */
if (ret) {
node = khugepaged_find_target_node();
/* collapse_huge_page will return with the mmap_sem released */
- collapse_huge_page(mm, address, hpage, vma, node, referenced);
+ collapse_huge_page(mm, address, hpage, node, referenced);
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock;
+ unsigned long flags;
bool ret = false;
if (nr_pages > CHARGE_BATCH)
return ret;
- stock = &get_cpu_var(memcg_stock);
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
stock->nr_pages -= nr_pages;
ret = true;
}
- put_cpu_var(memcg_stock);
+
+ local_irq_restore(flags);
+
return ret;
}
stock->cached = NULL;
}
-/*
- * This must be called under preempt disabled or must be called by
- * a thread which is pinned to local cpu.
- */
static void drain_local_stock(struct work_struct *dummy)
{
- struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock);
+ struct memcg_stock_pcp *stock;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
+
+ local_irq_restore(flags);
}
/*
*/
static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+ struct memcg_stock_pcp *stock;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stock = this_cpu_ptr(&memcg_stock);
if (stock->cached != memcg) { /* reset if necessary */
drain_stock(stock);
stock->cached = memcg;
}
stock->nr_pages += nr_pages;
- put_cpu_var(memcg_stock);
+
+ local_irq_restore(flags);
}
/*
return alloc_huge_page_node(page_hstate(compound_head(page)),
next_node_in(nid, nmask));
- node_clear(nid, nmask);
+ if (nid != next_node_in(nid, nmask))
+ node_clear(nid, nmask);
+
if (PageHighMem(page)
|| (zone_idx(page_zone(page)) == ZONE_MOVABLE))
gfp_mask |= __GFP_HIGHMEM;
int ret;
struct swap_info_struct *sis = page_swap_info(page);
+ BUG_ON(!PageSwapCache(page));
if (sis->flags & SWP_FILE) {
struct kiocb kiocb;
struct file *swap_file = sis->swap_file;
int ret = 0;
struct swap_info_struct *sis = page_swap_info(page);
+ BUG_ON(!PageSwapCache(page));
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageUptodate(page), page);
if (frontswap_load(page) == 0) {
if (sis->flags & SWP_FILE) {
struct address_space *mapping = sis->swap_file->f_mapping;
+ BUG_ON(!PageSwapCache(page));
return mapping->a_ops->set_page_dirty(page);
} else {
return __set_page_dirty_no_writeback(page);
struct swap_info_struct *page_swap_info(struct page *page)
{
swp_entry_t swap = { .val = page_private(page) };
- BUG_ON(!PageSwapCache(page));
return swap_info[swp_type(swap)];
}
* Some architectures (arm64) return true for virt_addr_valid() on
* vmalloced addresses. Work around this by checking for vmalloc
* first.
+ *
+ * We also need to check for module addresses explicitly since we
+ * may copy static data from modules to userspace
*/
- if (is_vmalloc_addr(ptr))
+ if (is_vmalloc_or_module_addr(ptr))
return NULL;
if (!virt_addr_valid(ptr))
if (!try_module_get(prot->owner))
goto out_free_sec;
sk_tx_queue_clear(sk);
- cgroup_sk_alloc(&sk->sk_cgrp_data);
}
return sk;
sock_net_set(sk, net);
atomic_set(&sk->sk_wmem_alloc, 1);
+ cgroup_sk_alloc(&sk->sk_cgrp_data);
sock_update_classid(&sk->sk_cgrp_data);
sock_update_netprioidx(&sk->sk_cgrp_data);
}
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
+
+ cgroup_sk_alloc(&newsk->sk_cgrp_data);
+
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
struct rsc *found;
memset(&rsci, 0, sizeof(rsci));
- rsci.handle.data = handle->data;
- rsci.handle.len = handle->len;
+ if (dup_to_netobj(&rsci.handle, handle->data, handle->len))
+ return NULL;
found = rsc_lookup(cd, &rsci);
+ rsc_free(&rsci);
if (!found)
return NULL;
if (cache_check(cd, &found->h, NULL))
#include <linux/slab.h>
#include <linux/prefetch.h>
#include <linux/sunrpc/addr.h>
+#include <linux/sunrpc/svc_rdma.h>
#include <asm/bitops.h>
#include <linux/module.h> /* try_module_get()/module_put() */
}
INIT_LIST_HEAD(&buf->rb_recv_bufs);
- for (i = 0; i < buf->rb_max_requests; i++) {
+ for (i = 0; i < buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; i++) {
struct rpcrdma_rep *rep;
rep = rpcrdma_create_rep(r_xprt);
rep = rpcrdma_buffer_get_rep_locked(buf);
rpcrdma_destroy_rep(ia, rep);
}
+ buf->rb_send_count = 0;
spin_lock(&buf->rb_reqslock);
while (!list_empty(&buf->rb_allreqs)) {
spin_lock(&buf->rb_reqslock);
}
spin_unlock(&buf->rb_reqslock);
+ buf->rb_recv_count = 0;
rpcrdma_destroy_mrs(buf);
}
spin_unlock(&buf->rb_mwlock);
}
+static struct rpcrdma_rep *
+rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers)
+{
+ /* If an RPC previously completed without a reply (say, a
+ * credential problem or a soft timeout occurs) then hold off
+ * on supplying more Receive buffers until the number of new
+ * pending RPCs catches up to the number of posted Receives.
+ */
+ if (unlikely(buffers->rb_send_count < buffers->rb_recv_count))
+ return NULL;
+
+ if (unlikely(list_empty(&buffers->rb_recv_bufs)))
+ return NULL;
+ buffers->rb_recv_count++;
+ return rpcrdma_buffer_get_rep_locked(buffers);
+}
+
/*
* Get a set of request/reply buffers.
+ *
+ * Reply buffer (if available) is attached to send buffer upon return.
*/
struct rpcrdma_req *
rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
spin_lock(&buffers->rb_lock);
if (list_empty(&buffers->rb_send_bufs))
goto out_reqbuf;
+ buffers->rb_send_count++;
req = rpcrdma_buffer_get_req_locked(buffers);
- if (list_empty(&buffers->rb_recv_bufs))
- goto out_repbuf;
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
return req;
out_reqbuf:
spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
- return NULL;
-out_repbuf:
- list_add(&req->rl_free, &buffers->rb_send_bufs);
- spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
+ pr_warn("RPC: %s: out of request buffers\n", __func__);
return NULL;
}
req->rl_reply = NULL;
spin_lock(&buffers->rb_lock);
+ buffers->rb_send_count--;
list_add_tail(&req->rl_free, &buffers->rb_send_bufs);
- if (rep)
+ if (rep) {
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
+ }
spin_unlock(&buffers->rb_lock);
}
struct rpcrdma_buffer *buffers = req->rl_buffer;
spin_lock(&buffers->rb_lock);
- if (!list_empty(&buffers->rb_recv_bufs))
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
}
struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf;
spin_lock(&buffers->rb_lock);
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
spin_unlock(&buffers->rb_lock);
}
char *rb_pool;
spinlock_t rb_lock; /* protect buf lists */
+ int rb_send_count, rb_recv_count;
struct list_head rb_send_bufs;
struct list_head rb_recv_bufs;
u32 rb_max_requests;
skb = skb_recv_datagram(sk, 0, 1, &err);
if (skb != NULL) {
xs_udp_data_read_skb(&transport->xprt, sk, skb);
- skb_free_datagram(sk, skb);
+ skb_free_datagram_locked(sk, skb);
continue;
}
if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
--- /dev/null
+#!/bin/bash
+#
+# Translate stack dump function offsets.
+#
+# addr2line doesn't work with KASLR addresses. This works similarly to
+# addr2line, but instead takes the 'func+0x123' format as input:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux meminfo_proc_show+0x5/0x568
+# meminfo_proc_show+0x5/0x568:
+# meminfo_proc_show at fs/proc/meminfo.c:27
+#
+# If the address is part of an inlined function, the full inline call chain is
+# printed:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux native_write_msr+0x6/0x27
+# native_write_msr+0x6/0x27:
+# arch_static_branch at arch/x86/include/asm/msr.h:121
+# (inlined by) static_key_false at include/linux/jump_label.h:125
+# (inlined by) native_write_msr at arch/x86/include/asm/msr.h:125
+#
+# The function size after the '/' in the input is optional, but recommended.
+# It's used to help disambiguate any duplicate symbol names, which can occur
+# rarely. If the size is omitted for a duplicate symbol then it's possible for
+# multiple code sites to be printed:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux raw_ioctl+0x5
+# raw_ioctl+0x5/0x20:
+# raw_ioctl at drivers/char/raw.c:122
+#
+# raw_ioctl+0x5/0xb1:
+# raw_ioctl at net/ipv4/raw.c:876
+#
+# Multiple addresses can be specified on a single command line:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux type_show+0x10/45 free_reserved_area+0x90
+# type_show+0x10/0x2d:
+# type_show at drivers/video/backlight/backlight.c:213
+#
+# free_reserved_area+0x90/0x123:
+# free_reserved_area at mm/page_alloc.c:6429 (discriminator 2)
+
+
+set -o errexit
+set -o nounset
+
+command -v awk >/dev/null 2>&1 || die "awk isn't installed"
+command -v readelf >/dev/null 2>&1 || die "readelf isn't installed"
+command -v addr2line >/dev/null 2>&1 || die "addr2line isn't installed"
+
+usage() {
+ echo "usage: faddr2line <object file> <func+offset> <func+offset>..." >&2
+ exit 1
+}
+
+warn() {
+ echo "$1" >&2
+}
+
+die() {
+ echo "ERROR: $1" >&2
+ exit 1
+}
+
+# Try to figure out the source directory prefix so we can remove it from the
+# addr2line output. HACK ALERT: This assumes that start_kernel() is in
+# kernel/init.c! This only works for vmlinux. Otherwise it falls back to
+# printing the absolute path.
+find_dir_prefix() {
+ local objfile=$1
+
+ local start_kernel_addr=$(readelf -sW $objfile | awk '$8 == "start_kernel" {printf "0x%s", $2}')
+ [[ -z $start_kernel_addr ]] && return
+
+ local file_line=$(addr2line -e $objfile $start_kernel_addr)
+ [[ -z $file_line ]] && return
+
+ local prefix=${file_line%init/main.c:*}
+ if [[ -z $prefix ]] || [[ $prefix = $file_line ]]; then
+ return
+ fi
+
+ DIR_PREFIX=$prefix
+ return 0
+}
+
+__faddr2line() {
+ local objfile=$1
+ local func_addr=$2
+ local dir_prefix=$3
+ local print_warnings=$4
+
+ local func=${func_addr%+*}
+ local offset=${func_addr#*+}
+ offset=${offset%/*}
+ local size=
+ [[ $func_addr =~ "/" ]] && size=${func_addr#*/}
+
+ if [[ -z $func ]] || [[ -z $offset ]] || [[ $func = $func_addr ]]; then
+ warn "bad func+offset $func_addr"
+ DONE=1
+ return
+ fi
+
+ # Go through each of the object's symbols which match the func name.
+ # In rare cases there might be duplicates.
+ while read symbol; do
+ local fields=($symbol)
+ local sym_base=0x${fields[1]}
+ local sym_size=${fields[2]}
+ local sym_type=${fields[3]}
+
+ # calculate the address
+ local addr=$(($sym_base + $offset))
+ if [[ -z $addr ]] || [[ $addr = 0 ]]; then
+ warn "bad address: $sym_base + $offset"
+ DONE=1
+ return
+ fi
+ local hexaddr=0x$(printf %x $addr)
+
+ # weed out non-function symbols
+ if [[ $sym_type != "FUNC" ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to non-function symbol"
+ continue
+ fi
+
+ # if the user provided a size, make sure it matches the symbol's size
+ if [[ -n $size ]] && [[ $size -ne $sym_size ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to size mismatch ($size != $sym_size)"
+ continue;
+ fi
+
+ # make sure the provided offset is within the symbol's range
+ if [[ $offset -gt $sym_size ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to size mismatch ($offset > $sym_size)"
+ continue
+ fi
+
+ # separate multiple entries with a blank line
+ [[ $FIRST = 0 ]] && echo
+ FIRST=0
+
+ local hexsize=0x$(printf %x $sym_size)
+ echo "$func+$offset/$hexsize:"
+ addr2line -fpie $objfile $hexaddr | sed "s; $dir_prefix\(\./\)*; ;"
+ DONE=1
+
+ done < <(readelf -sW $objfile | awk -v f=$func '$8 == f {print}')
+}
+
+[[ $# -lt 2 ]] && usage
+
+objfile=$1
+[[ ! -f $objfile ]] && die "can't find objfile $objfile"
+shift
+
+DIR_PREFIX=supercalifragilisticexpialidocious
+find_dir_prefix $objfile
+
+FIRST=1
+while [[ $# -gt 0 ]]; do
+ func_addr=$1
+ shift
+
+ # print any matches found
+ DONE=0
+ __faddr2line $objfile $func_addr $DIR_PREFIX 0
+
+ # if no match was found, print warnings
+ if [[ $DONE = 0 ]]; then
+ __faddr2line $objfile $func_addr $DIR_PREFIX 1
+ warn "no match for $func_addr"
+ fi
+done
}
}
+ /* If we exit via err(), this kills all the threads, restores tty. */
+ atexit(cleanup_devices);
+
/* We always have a console device, and it's always device 1. */
setup_console();
/* Ensure that we terminate if a device-servicing child dies. */
signal(SIGCHLD, kill_launcher);
- /* If we exit via err(), this kills all the threads, restores tty. */
- atexit(cleanup_devices);
-
/* If requested, chroot to a directory */
if (chroot_path) {
if (chroot(chroot_path) != 0)
projects / cascardo / linux.git / commitdiff