select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32
+ select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_TRACEHOOK
+ select HAVE_ARM_SMCCC if CPU_V7
select HAVE_BPF_JIT
select HAVE_CC_STACKPROTECTOR
select HAVE_CONTEXT_TRACKING
Select if you want MMU-based virtualised addressing space
support by paged memory management. If unsure, say 'Y'.
+config ARCH_MMAP_RND_BITS_MIN
+ default 8
+
+config ARCH_MMAP_RND_BITS_MAX
+ default 14 if PAGE_OFFSET=0x40000000
+ default 15 if PAGE_OFFSET=0x80000000
+ default 16
+
#
# The "ARM system type" choice list is ordered alphabetically by option
# text. Please add new entries in the option alphabetic order.
config BL_SWITCHER
bool "big.LITTLE switcher support"
- depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
- select ARM_CPU_SUSPEND
+ depends on BIG_LITTLE && MCPM && HOTPLUG_CPU && ARM_GIC
select CPU_PM
help
The big.LITTLE "switcher" provides the core functionality to
config ARM_PSCI
bool "Support for the ARM Power State Coordination Interface (PSCI)"
- depends on CPU_V7
+ depends on HAVE_ARM_SMCCC
select ARM_PSCI_FW
help
Say Y here if you want Linux to communicate with system firmware
help
Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
+config ARM_FLUSH_CONSOLE_ON_RESTART
+ bool "Force flush the console on restart"
+ help
+ If the console is locked while the system is rebooted, the messages
+ in the temporary logbuffer would not have propogated to all the
+ console drivers. This option forces the console lock to be
+ released if it failed to be acquired, which will cause all the
+ pending messages to be flushed.
+
endmenu
menu "Boot options"
This was deprecated in 2001 and announced to live on for 5 years.
Some old boot loaders still use this way.
+config BUILD_ARM_APPENDED_DTB_IMAGE
+ bool "Build a concatenated zImage/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated zImage and list of
+ DTBs to be built by default (instead of a standalone zImage.)
+ The image will built in arch/arm/boot/zImage-dtb
+
+config BUILD_ARM_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated zImage-dtb.
+
# Compressed boot loader in ROM. Yes, we really want to ask about
# TEXT and BSS so we preserve their values in the config files.
config ZBOOT_ROM_TEXT
def_bool y
config ARM_CPU_SUSPEND
- def_bool PM_SLEEP
+ def_bool PM_SLEEP || BL_SWITCHER || ARM_PSCI_FW
+ depends on ARCH_SUSPEND_POSSIBLE
config ARCH_HIBERNATION_POSSIBLE
bool
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
select HAVE_ARCH_KGDB
+ select HAVE_ARCH_MMAP_RND_BITS
+ select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_BPF_JIT
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select HAVE_CONTEXT_TRACKING
+ select HAVE_ARM_SMCCC
help
ARM 64-bit (AArch64) Linux support.
config MMU
def_bool y
+config ARCH_MMAP_RND_BITS_MIN
+ default 14 if ARM64_64K_PAGES
+ default 16 if ARM64_16K_PAGES
+ default 18
+
+# max bits determined by the following formula:
+# VA_BITS - PAGE_SHIFT - 3
+config ARCH_MMAP_RND_BITS_MAX
+ default 19 if ARM64_VA_BITS=36
+ default 24 if ARM64_VA_BITS=39
+ default 27 if ARM64_VA_BITS=42
+ default 30 if ARM64_VA_BITS=47
+ default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES
+ default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES
+ default 33 if ARM64_VA_BITS=48
+ default 14 if ARM64_64K_PAGES
+ default 16 if ARM64_16K_PAGES
+ default 18
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+ default 7 if ARM64_64K_PAGES
+ default 9 if ARM64_16K_PAGES
+ default 11
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+ default 16
+
config NO_IOPORT_MAP
def_bool y if !PCI
+config ILLEGAL_POINTER_VALUE
+ hex
+ default 0xdead000000000000
+
config STACKTRACE_SUPPORT
def_bool y
If unsure, say Y
endif
+config ARM64_SW_TTBR0_PAN
+ bool "Emulate Priviledged Access Never using TTBR0_EL1 switching"
+ help
+ Enabling this option prevents the kernel from accessing
+ user-space memory directly by pointing TTBR0_EL1 to a reserved
+ zeroed area and reserved ASID. The user access routines
+ restore the valid TTBR0_EL1 temporarily.
+
menu "ARMv8.1 architectural features"
config ARM64_HW_AFDBM
config RANDOMIZE_BASE
bool "Randomize the address of the kernel image"
- select ARM64_MODULE_PLTS
+ select ARM64_MODULE_PLTS if MODULES
select RELOCATABLE
help
Randomizes the virtual address at which the kernel image is
config RANDOMIZE_MODULE_REGION_FULL
bool "Randomize the module region independently from the core kernel"
- depends on RANDOMIZE_BASE
+ depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
default y
help
Randomizes the location of the module region without considering the
entering them here. As a minimum, you should specify the the
root device (e.g. root=/dev/nfs).
+choice
+ prompt "Kernel command line type" if CMDLINE != ""
+ default CMDLINE_FROM_BOOTLOADER
+
+config CMDLINE_FROM_BOOTLOADER
+ bool "Use bootloader kernel arguments if available"
+ help
+ Uses the command-line options passed by the boot loader. If
+ the boot loader doesn't provide any, the default kernel command
+ string provided in CMDLINE will be used.
+
+config CMDLINE_EXTEND
+ bool "Extend bootloader kernel arguments"
+ help
+ The command-line arguments provided by the boot loader will be
+ appended to the default kernel command string.
+
config CMDLINE_FORCE
bool "Always use the default kernel command string"
help
loader passes other arguments to the kernel.
This is useful if you cannot or don't want to change the
command-line options your boot loader passes to the kernel.
+endchoice
config EFI_STUB
bool
However, even with this option, the resultant kernel should
continue to boot on existing non-UEFI platforms.
+config BUILD_ARM64_APPENDED_DTB_IMAGE
+ bool "Build a concatenated Image.gz/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated Image.gz and list of
+ DTBs to be built by default (instead of a standalone Image.gz.)
+ The image will built in arch/arm64/boot/Image.gz-dtb
+
+config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated Image.gz-dtb.
+
endmenu
menu "Userspace binary formats"
source "kernel/power/Kconfig"
+ config ARCH_HIBERNATION_POSSIBLE
+ def_bool y
+ depends on CPU_PM
+
+ config ARCH_HIBERNATION_HEADER
+ def_bool y
+ depends on HIBERNATION
+
config ARCH_SUSPEND_POSSIBLE
def_bool y
#define ARM64_HAS_UAO 9
#define ARM64_ALT_PAN_NOT_UAO 10
- #define ARM64_NCAPS 11
- #define ARM64_WORKAROUND_CAVIUM_27456 12
-
+ #define ARM64_WORKAROUND_CAVIUM_27456 11
+ #define ARM64_HAS_VIRT_HOST_EXTN 12
+ #define ARM64_NCAPS 13
#ifndef __ASSEMBLY__
return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
}
+static inline bool system_uses_ttbr0_pan(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
+ !cpus_have_cap(ARM64_HAS_PAN);
+}
+
#endif /* __ASSEMBLY__ */
#endif
#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4))
+ #define KERNEL_START _text
+ #define KERNEL_END _end
+
/*
* The size of the KASAN shadow region. This should be 1/8th of the
* size of the entire kernel virtual address space.
#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET)
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+#define _virt_addr_is_linear(kaddr) (((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(kaddr) (_virt_addr_is_linear(kaddr) && \
+ _virt_addr_valid(kaddr))
#endif
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
+ #include <linux/suspend.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
#include <asm/suspend.h>
#include <asm/vdso_datapage.h>
#include <linux/kbuild.h>
+ #include <linux/arm-smccc.h>
int main(void)
{
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit));
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ DEFINE(TI_TTBR0, offsetof(struct thread_info, ttbr0));
+#endif
DEFINE(TI_TASK, offsetof(struct thread_info, task));
DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
BLANK();
DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs));
DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs));
DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs));
- DEFINE(CPU_SP_EL1, offsetof(struct kvm_regs, sp_el1));
- DEFINE(CPU_ELR_EL1, offsetof(struct kvm_regs, elr_el1));
- DEFINE(CPU_SPSR, offsetof(struct kvm_regs, spsr));
- DEFINE(CPU_SYSREGS, offsetof(struct kvm_cpu_context, sys_regs));
+ DEFINE(VCPU_FPEXC32_EL2, offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2));
DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2));
DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
- DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags));
- DEFINE(VCPU_DEBUG_PTR, offsetof(struct kvm_vcpu, arch.debug_ptr));
- DEFINE(DEBUG_BCR, offsetof(struct kvm_guest_debug_arch, dbg_bcr));
- DEFINE(DEBUG_BVR, offsetof(struct kvm_guest_debug_arch, dbg_bvr));
- DEFINE(DEBUG_WCR, offsetof(struct kvm_guest_debug_arch, dbg_wcr));
- DEFINE(DEBUG_WVR, offsetof(struct kvm_guest_debug_arch, dbg_wvr));
- DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2));
- DEFINE(VCPU_MDCR_EL2, offsetof(struct kvm_vcpu, arch.mdcr_el2));
- DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines));
DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context));
- DEFINE(VCPU_HOST_DEBUG_STATE, offsetof(struct kvm_vcpu, arch.host_debug_state));
- DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
- DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
- DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff));
- DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled));
- DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
- DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu));
- DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
- DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
- DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
- DEFINE(VGIC_V2_CPU_EISR, offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
- DEFINE(VGIC_V2_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
- DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
- DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
- DEFINE(VGIC_V3_CPU_SRE, offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
- DEFINE(VGIC_V3_CPU_HCR, offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
- DEFINE(VGIC_V3_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
- DEFINE(VGIC_V3_CPU_MISR, offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
- DEFINE(VGIC_V3_CPU_EISR, offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
- DEFINE(VGIC_V3_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
- DEFINE(VGIC_V3_CPU_AP0R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
- DEFINE(VGIC_V3_CPU_AP1R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
- DEFINE(VGIC_V3_CPU_LR, offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
- DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr));
- DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr));
- DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base));
#endif
#ifdef CONFIG_CPU_PM
DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx));
DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
DEFINE(MPIDR_HASH_MASK, offsetof(struct mpidr_hash, mask));
DEFINE(MPIDR_HASH_SHIFTS, offsetof(struct mpidr_hash, shift_aff));
- DEFINE(SLEEP_SAVE_SP_SZ, sizeof(struct sleep_save_sp));
- DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys));
- DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash));
+ DEFINE(SLEEP_STACK_DATA_SYSTEM_REGS, offsetof(struct sleep_stack_data, system_regs));
+ DEFINE(SLEEP_STACK_DATA_CALLEE_REGS, offsetof(struct sleep_stack_data, callee_saved_regs));
#endif
+ DEFINE(ARM_SMCCC_RES_X0_OFFS, offsetof(struct arm_smccc_res, a0));
+ DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2));
+ BLANK();
+ DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address));
+ DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address));
+ DEFINE(HIBERN_PBE_NEXT, offsetof(struct pbe, next));
return 0;
}
#include <asm/cpu_ops.h>
#include <asm/processor.h>
#include <asm/sysreg.h>
+ #include <asm/virt.h>
unsigned long elf_hwcap __read_mostly;
EXPORT_SYMBOL_GPL(elf_hwcap);
#endif
DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcaps);
#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
{ \
return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, rv_min, rv_max);
}
+ static bool runs_at_el2(const struct arm64_cpu_capabilities *entry)
+ {
+ return is_kernel_in_hyp_mode();
+ }
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
.matches = cpufeature_pan_not_uao,
},
#endif /* CONFIG_ARM64_PAN */
+ {
+ .desc = "Virtualization Host Extensions",
+ .capability = ARM64_HAS_VIRT_HOST_EXTN,
+ .matches = runs_at_el2,
+ },
{},
};
#error TEXT_OFFSET must be less than 2MB
#endif
- #define KERNEL_START _text
- #define KERNEL_END _end
-
/*
* Kernel startup entry point.
* ---------------------------
* dirty cache lines being evicted.
*/
mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ add x1, x26, #SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
*/
mov x0, x25
- add x6, x26, #SWAPPER_DIR_SIZE
+ add x6, x26, #SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
* tables again to remove any speculatively loaded cache lines.
*/
mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ add x1, x26, #SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
dmb sy
bl __inval_cache_range
* If it isn't, park the CPU
*/
.section ".idmap.text", "ax"
- __enable_mmu:
+ ENTRY(__enable_mmu)
mrs x18, sctlr_el1 // preserve old SCTLR_EL1 value
mrs x1, ID_AA64MMFR0_EL1
ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
isb
bl __create_page_tables // recreate kernel mapping
+ tlbi vmalle1 // Remove any stale TLB entries
+ dsb nsh
+
msr sctlr_el1, x19 // re-enable the MMU
isb
ic iallu // flush instructions fetched
*/
if (mpidr_hash_size() > 4 * num_possible_cpus())
pr_warn("Large number of MPIDR hash buckets detected\n");
- __flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
}
static void __init setup_machine_fdt(phys_addr_t dt_phys)
struct resource *res;
kernel_code.start = virt_to_phys(_text);
- kernel_code.end = virt_to_phys(_etext - 1);
+ kernel_code.end = virt_to_phys(__init_begin - 1);
kernel_data.start = virt_to_phys(_sdata);
kernel_data.end = virt_to_phys(_end - 1);
smp_init_cpus();
smp_build_mpidr_hash();
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ /*
+ * Make sure init_thread_info.ttbr0 always generates translation
+ * faults in case uaccess_enable() is inadvertently called by the init
+ * thread.
+ */
+ init_thread_info.ttbr0 = virt_to_phys(empty_zero_page);
+#endif
+
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
*(.idmap.text) \
VMLINUX_SYMBOL(__idmap_text_end) = .;
+ #ifdef CONFIG_HIBERNATION
+ #define HIBERNATE_TEXT \
+ . = ALIGN(SZ_4K); \
+ VMLINUX_SYMBOL(__hibernate_exit_text_start) = .;\
+ *(.hibernate_exit.text) \
+ VMLINUX_SYMBOL(__hibernate_exit_text_end) = .;
+ #else
+ #define HIBERNATE_TEXT
+ #endif
+
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from stext to _edata, must be a round multiple of the PE/COFF
KPROBES_TEXT
HYPERVISOR_TEXT
IDMAP_TEXT
+ HIBERNATE_TEXT
*(.fixup)
*(.gnu.warning)
. = ALIGN(16);
}
. = ALIGN(SEGMENT_ALIGN);
- RO_DATA(PAGE_SIZE) /* everything from this point to */
- EXCEPTION_TABLE(8) /* _etext will be marked RO NX */
+ _etext = .; /* End of text section */
+
+ RO_DATA(PAGE_SIZE) /* everything from this point to */
+ EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */
NOTES
. = ALIGN(SEGMENT_ALIGN);
- _etext = .; /* End of text and rodata section */
__init_begin = .;
INIT_TEXT_SECTION(8)
swapper_pg_dir = .;
. += SWAPPER_DIR_SIZE;
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ reserved_ttbr0 = .;
+ . += RESERVED_TTBR0_SIZE;
+#endif
+
_end = .;
STABS_DEBUG
"HYP init code too big or misaligned")
ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
"ID map text too big or misaligned")
+ #ifdef CONFIG_HIBERNATION
+ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
+ <= SZ_4K, "Hibernate exit text too big or misaligned")
+ #endif
/*
* If padding is applied before .head.text, virt<->phys conversions will fail.
#include <asm/asm-offsets.h>
#include <asm/hwcap.h>
#include <asm/pgtable.h>
+ #include <asm/pgtable-hwdef.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
mrs x2, tpidr_el0
mrs x3, tpidrro_el0
mrs x4, contextidr_el1
- mrs x5, mair_el1
- mrs x6, cpacr_el1
- mrs x7, ttbr1_el1
- mrs x8, tcr_el1
- mrs x9, vbar_el1
- mrs x10, mdscr_el1
- mrs x11, oslsr_el1
- mrs x12, sctlr_el1
+ mrs x5, cpacr_el1
+ mrs x6, tcr_el1
+ mrs x7, vbar_el1
+ mrs x8, mdscr_el1
+ mrs x9, oslsr_el1
+ mrs x10, sctlr_el1
stp x2, x3, [x0]
- stp x4, x5, [x0, #16]
- stp x6, x7, [x0, #32]
- stp x8, x9, [x0, #48]
- stp x10, x11, [x0, #64]
- str x12, [x0, #80]
+ stp x4, xzr, [x0, #16]
+ stp x5, x6, [x0, #32]
+ stp x7, x8, [x0, #48]
+ stp x9, x10, [x0, #64]
ret
ENDPROC(cpu_do_suspend)
/**
* cpu_do_resume - restore CPU register context
*
- * x0: Physical address of context pointer
- * x1: ttbr0_el1 to be restored
- *
- * Returns:
- * sctlr_el1 value in x0
+ * x0: Address of context pointer
*/
ENTRY(cpu_do_resume)
- /*
- * Invalidate local tlb entries before turning on MMU
- */
- tlbi vmalle1
ldp x2, x3, [x0]
ldp x4, x5, [x0, #16]
- ldp x6, x7, [x0, #32]
- ldp x8, x9, [x0, #48]
- ldp x10, x11, [x0, #64]
- ldr x12, [x0, #80]
+ ldp x6, x8, [x0, #32]
+ ldp x9, x10, [x0, #48]
+ ldp x11, x12, [x0, #64]
msr tpidr_el0, x2
msr tpidrro_el0, x3
msr contextidr_el1, x4
- msr mair_el1, x5
msr cpacr_el1, x6
- msr ttbr0_el1, x1
- msr ttbr1_el1, x7
- tcr_set_idmap_t0sz x8, x7
+
+ /* Don't change t0sz here, mask those bits when restoring */
+ mrs x5, tcr_el1
+ bfi x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+
msr tcr_el1, x8
msr vbar_el1, x9
msr mdscr_el1, x10
+ msr sctlr_el1, x12
/*
* Restore oslsr_el1 by writing oslar_el1
*/
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
- mov x0, x12
- dsb nsh // Make sure local tlb invalidation completed
isb
ret
ENDPROC(cpu_do_resume)
bfi x0, x1, #48, #16 // set the ASID
msr ttbr0_el1, x0 // set TTBR0
isb
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
+ post_ttbr0_update_workaround
ret
- nop
- nop
- nop
-alternative_else
- ic iallu
- dsb nsh
- isb
- ret
-alternative_endif
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
#define __get_user_asm_u64(x, ptr, retval, errret) \
__get_user_asm(x, ptr, retval, "q", "", "=r", errret)
#define __get_user_asm_ex_u64(x, ptr) \
- __get_user_asm_ex(x, ptr, "q", "", "=r")
+ __get_user_asm_ex(x, ptr, "q", "", "=&r")
#endif
#define __get_user_size(x, ptr, size, retval, errret) \
__chk_user_ptr(ptr); \
switch (size) { \
case 1: \
- __get_user_asm_ex(x, ptr, "b", "b", "=q"); \
+ __get_user_asm_ex(x, ptr, "b", "b", "=&q"); \
break; \
case 2: \
- __get_user_asm_ex(x, ptr, "w", "w", "=r"); \
+ __get_user_asm_ex(x, ptr, "w", "w", "=&r"); \
break; \
case 4: \
- __get_user_asm_ex(x, ptr, "l", "k", "=r"); \
+ __get_user_asm_ex(x, ptr, "l", "k", "=&r"); \
break; \
case 8: \
__get_user_asm_ex_u64(x, ptr); \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
_ASM_EXTABLE_EX(1b, 2b) \
- : ltype(x) : "m" (__m(addr)))
+ : ltype(x) : "m" (__m(addr)), "0" (0))
#define __put_user_nocheck(x, ptr, size) \
({ \
#endif
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
int sz = __compiletime_object_size(to);
return n;
}
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
int sz = __compiletime_object_size(from);
static struct binder_ref *binder_get_ref(struct binder_proc *proc,
- uint32_t desc, bool need_strong_ref)
+ u32 desc, bool need_strong_ref)
{
struct rb_node *n = proc->refs_by_desc.rb_node;
struct binder_ref *ref;
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref = binder_get_ref(proc, fp->handle,
- fp->type == BINDER_TYPE_HANDLE);
+ struct binder_ref *ref;
+
+ ref = binder_get_ref(proc, fp->handle,
+ fp->type == BINDER_TYPE_HANDLE);
if (ref == NULL) {
pr_err("transaction release %d bad handle %d\n",
struct binder_transaction *t;
struct binder_work *tcomplete;
binder_size_t *offp, *off_end;
+ binder_size_t off_min;
struct binder_proc *target_proc;
struct binder_thread *target_thread = NULL;
struct binder_node *target_node = NULL;
goto err_bad_offset;
}
off_end = (void *)offp + tr->offsets_size;
+ off_min = 0;
for (; offp < off_end; offp++) {
struct flat_binder_object *fp;
if (*offp > t->buffer->data_size - sizeof(*fp) ||
+ *offp < off_min ||
t->buffer->data_size < sizeof(*fp) ||
!IS_ALIGNED(*offp, sizeof(u32))) {
- binder_user_error("%d:%d got transaction with invalid offset, %lld\n",
- proc->pid, thread->pid, (u64)*offp);
+ binder_user_error("%d:%d got transaction with invalid offset, %lld (min %lld, max %lld)\n",
+ proc->pid, thread->pid, (u64)*offp,
+ (u64)off_min,
+ (u64)(t->buffer->data_size -
+ sizeof(*fp)));
return_error = BR_FAILED_REPLY;
goto err_bad_offset;
}
fp = (struct flat_binder_object *)(t->buffer->data + *offp);
+ off_min = *offp + sizeof(struct flat_binder_object);
switch (fp->type) {
case BINDER_TYPE_BINDER:
case BINDER_TYPE_WEAK_BINDER: {
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref = binder_get_ref(proc, fp->handle,
- fp->type == BINDER_TYPE_HANDLE);
+ struct binder_ref *ref;
+
+ ref = binder_get_ref(proc, fp->handle,
+ fp->type == BINDER_TYPE_HANDLE);
if (ref == NULL) {
binder_user_error("%d:%d got transaction with invalid handle, %d\n",
static int binder_proc_show(struct seq_file *m, void *unused)
{
+ struct binder_proc *itr;
struct binder_proc *proc = m->private;
int do_lock = !binder_debug_no_lock;
+ bool valid_proc = false;
if (do_lock)
binder_lock(__func__);
- seq_puts(m, "binder proc state:\n");
- print_binder_proc(m, proc, 1);
+
+ hlist_for_each_entry(itr, &binder_procs, proc_node) {
+ if (itr == proc) {
+ valid_proc = true;
+ break;
+ }
+ }
+ if (valid_proc) {
+ seq_puts(m, "binder proc state:\n");
+ print_binder_proc(m, proc, 1);
+ }
if (do_lock)
binder_unlock(__func__);
return 0;
* blocks and still have efficient handling. */
#define GETHER_MAX_ETH_FRAME_LEN 15412
+static struct workqueue_struct *uether_wq;
+
struct eth_dev {
/* lock is held while accessing port_usb
*/
spinlock_t req_lock; /* guard {rx,tx}_reqs */
struct list_head tx_reqs, rx_reqs;
- atomic_t tx_qlen;
+ unsigned tx_qlen;
+/* Minimum number of TX USB request queued to UDC */
+#define TX_REQ_THRESHOLD 5
+ int no_tx_req_used;
+ int tx_skb_hold_count;
+ u32 tx_req_bufsize;
struct sk_buff_head rx_frames;
unsigned qmult;
unsigned header_len;
+ unsigned ul_max_pkts_per_xfer;
+ unsigned dl_max_pkts_per_xfer;
struct sk_buff *(*wrap)(struct gether *, struct sk_buff *skb);
int (*unwrap)(struct gether *,
struct sk_buff *skb,
struct sk_buff_head *list);
struct work_struct work;
+ struct work_struct rx_work;
unsigned long todo;
#define WORK_RX_MEMORY 0
size += out->maxpacket - 1;
size -= size % out->maxpacket;
+ if (dev->ul_max_pkts_per_xfer)
+ size *= dev->ul_max_pkts_per_xfer;
+
if (dev->port_usb->is_fixed)
size = max_t(size_t, size, dev->port_usb->fixed_out_len);
+ DBG(dev, "%s: size: %zd\n", __func__, size);
skb = alloc_skb(size + NET_IP_ALIGN, gfp_flags);
if (skb == NULL) {
DBG(dev, "no rx skb\n");
DBG(dev, "rx submit --> %d\n", retval);
if (skb)
dev_kfree_skb_any(skb);
- spin_lock_irqsave(&dev->req_lock, flags);
- list_add(&req->list, &dev->rx_reqs);
- spin_unlock_irqrestore(&dev->req_lock, flags);
}
return retval;
}
static void rx_complete(struct usb_ep *ep, struct usb_request *req)
{
- struct sk_buff *skb = req->context, *skb2;
+ struct sk_buff *skb = req->context;
struct eth_dev *dev = ep->driver_data;
int status = req->status;
+ bool queue = 0;
switch (status) {
status = dev->unwrap(dev->port_usb,
skb,
&dev->rx_frames);
+ if (status == -EINVAL)
+ dev->net->stats.rx_errors++;
+ else if (status == -EOVERFLOW)
+ dev->net->stats.rx_over_errors++;
} else {
dev_kfree_skb_any(skb);
status = -ENOTCONN;
} else {
skb_queue_tail(&dev->rx_frames, skb);
}
- skb = NULL;
-
- skb2 = skb_dequeue(&dev->rx_frames);
- while (skb2) {
- if (status < 0
- || ETH_HLEN > skb2->len
- || skb2->len > GETHER_MAX_ETH_FRAME_LEN) {
- dev->net->stats.rx_errors++;
- dev->net->stats.rx_length_errors++;
- DBG(dev, "rx length %d\n", skb2->len);
- dev_kfree_skb_any(skb2);
- goto next_frame;
- }
- skb2->protocol = eth_type_trans(skb2, dev->net);
- dev->net->stats.rx_packets++;
- dev->net->stats.rx_bytes += skb2->len;
-
- /* no buffer copies needed, unless hardware can't
- * use skb buffers.
- */
- status = netif_rx(skb2);
-next_frame:
- skb2 = skb_dequeue(&dev->rx_frames);
- }
+ if (!status)
+ queue = 1;
break;
/* software-driven interface shutdown */
/* FALLTHROUGH */
default:
+ queue = 1;
+ dev_kfree_skb_any(skb);
dev->net->stats.rx_errors++;
DBG(dev, "rx status %d\n", status);
break;
}
- if (skb)
- dev_kfree_skb_any(skb);
- if (!netif_running(dev->net)) {
clean:
- spin_lock(&dev->req_lock);
- list_add(&req->list, &dev->rx_reqs);
- spin_unlock(&dev->req_lock);
- req = NULL;
- }
- if (req)
- rx_submit(dev, req, GFP_ATOMIC);
+ spin_lock(&dev->req_lock);
+ list_add(&req->list, &dev->rx_reqs);
+ spin_unlock(&dev->req_lock);
+
+ if (queue)
+ queue_work(uether_wq, &dev->rx_work);
}
static int prealloc(struct list_head *list, struct usb_ep *ep, unsigned n)
{
struct usb_request *req;
unsigned long flags;
+ int req_cnt = 0;
/* fill unused rxq slots with some skb */
spin_lock_irqsave(&dev->req_lock, flags);
while (!list_empty(&dev->rx_reqs)) {
+ /* break the nexus of continuous completion and re-submission*/
+ if (++req_cnt > qlen(dev->gadget, dev->qmult))
+ break;
+
req = container_of(dev->rx_reqs.next,
struct usb_request, list);
list_del_init(&req->list);
spin_unlock_irqrestore(&dev->req_lock, flags);
if (rx_submit(dev, req, gfp_flags) < 0) {
+ spin_lock_irqsave(&dev->req_lock, flags);
+ list_add(&req->list, &dev->rx_reqs);
+ spin_unlock_irqrestore(&dev->req_lock, flags);
defer_kevent(dev, WORK_RX_MEMORY);
return;
}
spin_unlock_irqrestore(&dev->req_lock, flags);
}
+static void process_rx_w(struct work_struct *work)
+{
+ struct eth_dev *dev = container_of(work, struct eth_dev, rx_work);
+ struct sk_buff *skb;
+ int status = 0;
+
+ if (!dev->port_usb)
+ return;
+
+ while ((skb = skb_dequeue(&dev->rx_frames))) {
+ if (status < 0
+ || ETH_HLEN > skb->len
+ || skb->len > ETH_FRAME_LEN) {
+ dev->net->stats.rx_errors++;
+ dev->net->stats.rx_length_errors++;
+ DBG(dev, "rx length %d\n", skb->len);
+ dev_kfree_skb_any(skb);
+ continue;
+ }
+ skb->protocol = eth_type_trans(skb, dev->net);
+ dev->net->stats.rx_packets++;
+ dev->net->stats.rx_bytes += skb->len;
+
+ status = netif_rx_ni(skb);
+ }
+
+ if (netif_running(dev->net))
+ rx_fill(dev, GFP_KERNEL);
+}
+
static void eth_work(struct work_struct *work)
{
struct eth_dev *dev = container_of(work, struct eth_dev, work);
{
struct sk_buff *skb = req->context;
struct eth_dev *dev = ep->driver_data;
+ struct net_device *net = dev->net;
+ struct usb_request *new_req;
+ struct usb_ep *in;
+ int length;
+ int retval;
switch (req->status) {
default:
case -ESHUTDOWN: /* disconnect etc */
break;
case 0:
- dev->net->stats.tx_bytes += skb->len;
+ if (!req->zero)
+ dev->net->stats.tx_bytes += req->length-1;
+ else
+ dev->net->stats.tx_bytes += req->length;
}
dev->net->stats.tx_packets++;
spin_lock(&dev->req_lock);
- list_add(&req->list, &dev->tx_reqs);
- spin_unlock(&dev->req_lock);
- dev_kfree_skb_any(skb);
+ list_add_tail(&req->list, &dev->tx_reqs);
+
+ if (dev->port_usb->multi_pkt_xfer) {
+ dev->no_tx_req_used--;
+ req->length = 0;
+ in = dev->port_usb->in_ep;
+
+ if (!list_empty(&dev->tx_reqs)) {
+ new_req = container_of(dev->tx_reqs.next,
+ struct usb_request, list);
+ list_del(&new_req->list);
+ spin_unlock(&dev->req_lock);
+ if (new_req->length > 0) {
+ length = new_req->length;
+
+ /* NCM requires no zlp if transfer is
+ * dwNtbInMaxSize */
+ if (dev->port_usb->is_fixed &&
+ length == dev->port_usb->fixed_in_len &&
+ (length % in->maxpacket) == 0)
+ new_req->zero = 0;
+ else
+ new_req->zero = 1;
+
+ /* use zlp framing on tx for strict CDC-Ether
+ * conformance, though any robust network rx
+ * path ignores extra padding. and some hardware
+ * doesn't like to write zlps.
+ */
+ if (new_req->zero && !dev->zlp &&
+ (length % in->maxpacket) == 0) {
+ new_req->zero = 0;
+ length++;
+ }
+
+ new_req->length = length;
+ retval = usb_ep_queue(in, new_req, GFP_ATOMIC);
+ switch (retval) {
+ default:
+ DBG(dev, "tx queue err %d\n", retval);
+ break;
+ case 0:
+ spin_lock(&dev->req_lock);
+ dev->no_tx_req_used++;
+ spin_unlock(&dev->req_lock);
+ net->trans_start = jiffies;
+ }
+ } else {
+ spin_lock(&dev->req_lock);
+ list_add(&new_req->list, &dev->tx_reqs);
+ spin_unlock(&dev->req_lock);
+ }
+ } else {
+ spin_unlock(&dev->req_lock);
+ }
+ } else {
+ spin_unlock(&dev->req_lock);
+ dev_kfree_skb_any(skb);
+ }
- atomic_dec(&dev->tx_qlen);
if (netif_carrier_ok(dev->net))
netif_wake_queue(dev->net);
}
return cdc_filter & USB_CDC_PACKET_TYPE_PROMISCUOUS;
}
+static void alloc_tx_buffer(struct eth_dev *dev)
+{
+ struct list_head *act;
+ struct usb_request *req;
+
+ dev->tx_req_bufsize = (dev->dl_max_pkts_per_xfer *
+ (dev->net->mtu
+ + sizeof(struct ethhdr)
+ /* size of rndis_packet_msg_type */
+ + 44
+ + 22));
+
+ list_for_each(act, &dev->tx_reqs) {
+ req = container_of(act, struct usb_request, list);
+ if (!req->buf)
+ req->buf = kmalloc(dev->tx_req_bufsize,
+ GFP_ATOMIC);
+ }
+}
+
static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
struct net_device *net)
{
return NETDEV_TX_OK;
}
+ /* Allocate memory for tx_reqs to support multi packet transfer */
+ if (dev->port_usb->multi_pkt_xfer && !dev->tx_req_bufsize)
+ alloc_tx_buffer(dev);
+
/* apply outgoing CDC or RNDIS filters */
if (skb && !is_promisc(cdc_filter)) {
u8 *dest = skb->data;
}
}
- length = skb->len;
- req->buf = skb->data;
- req->context = skb;
+ spin_lock_irqsave(&dev->req_lock, flags);
+ dev->tx_skb_hold_count++;
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+
+ if (dev->port_usb->multi_pkt_xfer) {
+ memcpy(req->buf + req->length, skb->data, skb->len);
+ req->length = req->length + skb->len;
+ length = req->length;
+ dev_kfree_skb_any(skb);
+
+ spin_lock_irqsave(&dev->req_lock, flags);
+ if (dev->tx_skb_hold_count < dev->dl_max_pkts_per_xfer) {
+ if (dev->no_tx_req_used > TX_REQ_THRESHOLD) {
+ list_add(&req->list, &dev->tx_reqs);
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+ goto success;
+ }
+ }
+
+ dev->no_tx_req_used++;
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+
+ spin_lock_irqsave(&dev->lock, flags);
+ dev->tx_skb_hold_count = 0;
+ spin_unlock_irqrestore(&dev->lock, flags);
+ } else {
+ length = skb->len;
+ req->buf = skb->data;
+ req->context = skb;
+ }
+
req->complete = tx_complete;
/* NCM requires no zlp if transfer is dwNtbInMaxSize */
* though any robust network rx path ignores extra padding.
* and some hardware doesn't like to write zlps.
*/
- if (req->zero && !dev->zlp && (length % in->maxpacket) == 0)
+ if (req->zero && !dev->zlp && (length % in->maxpacket) == 0) {
+ req->zero = 0;
length++;
+ }
req->length = length;
- /* throttle high/super speed IRQ rate back slightly */
- if (gadget_is_dualspeed(dev->gadget))
- req->no_interrupt = (((dev->gadget->speed == USB_SPEED_HIGH ||
- dev->gadget->speed == USB_SPEED_SUPER)) &&
- !list_empty(&dev->tx_reqs))
- ? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
- : 0;
+ /* throttle highspeed IRQ rate back slightly */
+ if (gadget_is_dualspeed(dev->gadget) &&
- (dev->gadget->speed == USB_SPEED_HIGH)) {
++ (dev->gadget->speed == USB_SPEED_HIGH) &&
++ !list_empty(&dev->tx_reqs)) {
+ dev->tx_qlen++;
+ if (dev->tx_qlen == (dev->qmult/2)) {
+ req->no_interrupt = 0;
+ dev->tx_qlen = 0;
+ } else {
+ req->no_interrupt = 1;
+ }
+ } else {
+ req->no_interrupt = 0;
+ }
retval = usb_ep_queue(in, req, GFP_ATOMIC);
switch (retval) {
break;
case 0:
net->trans_start = jiffies;
- atomic_inc(&dev->tx_qlen);
}
if (retval) {
- dev_kfree_skb_any(skb);
+ if (!dev->port_usb->multi_pkt_xfer)
+ dev_kfree_skb_any(skb);
drop:
dev->net->stats.tx_dropped++;
multiframe:
list_add(&req->list, &dev->tx_reqs);
spin_unlock_irqrestore(&dev->req_lock, flags);
}
+success:
return NETDEV_TX_OK;
}
rx_fill(dev, gfp_flags);
/* and open the tx floodgates */
- atomic_set(&dev->tx_qlen, 0);
+ dev->tx_qlen = 0;
netif_wake_queue(dev->net);
}
spin_lock_init(&dev->lock);
spin_lock_init(&dev->req_lock);
INIT_WORK(&dev->work, eth_work);
+ INIT_WORK(&dev->rx_work, process_rx_w);
INIT_LIST_HEAD(&dev->tx_reqs);
INIT_LIST_HEAD(&dev->rx_reqs);
spin_lock_init(&dev->lock);
spin_lock_init(&dev->req_lock);
INIT_WORK(&dev->work, eth_work);
+ INIT_WORK(&dev->rx_work, process_rx_w);
INIT_LIST_HEAD(&dev->tx_reqs);
INIT_LIST_HEAD(&dev->rx_reqs);
dev->header_len = link->header_len;
dev->unwrap = link->unwrap;
dev->wrap = link->wrap;
+ dev->ul_max_pkts_per_xfer = link->ul_max_pkts_per_xfer;
+ dev->dl_max_pkts_per_xfer = link->dl_max_pkts_per_xfer;
spin_lock(&dev->lock);
+ dev->tx_skb_hold_count = 0;
+ dev->no_tx_req_used = 0;
+ dev->tx_req_bufsize = 0;
dev->port_usb = link;
if (netif_running(dev->net)) {
if (link->open)
{
struct eth_dev *dev = link->ioport;
struct usb_request *req;
+ struct sk_buff *skb;
WARN_ON(!dev);
if (!dev)
list_del(&req->list);
spin_unlock(&dev->req_lock);
+ if (link->multi_pkt_xfer)
+ kfree(req->buf);
usb_ep_free_request(link->in_ep, req);
spin_lock(&dev->req_lock);
}
spin_lock(&dev->req_lock);
}
spin_unlock(&dev->req_lock);
+
+ spin_lock(&dev->rx_frames.lock);
+ while ((skb = __skb_dequeue(&dev->rx_frames)))
+ dev_kfree_skb_any(skb);
+ spin_unlock(&dev->rx_frames.lock);
+
link->out_ep->desc = NULL;
/* finish forgetting about this USB link episode */
}
EXPORT_SYMBOL_GPL(gether_disconnect);
-MODULE_LICENSE("GPL");
+static int __init gether_init(void)
+{
+ uether_wq = create_singlethread_workqueue("uether");
+ if (!uether_wq) {
+ pr_err("%s: Unable to create workqueue: uether\n", __func__);
+ return -ENOMEM;
+ }
+ return 0;
+}
+module_init(gether_init);
+
+static void __exit gether_exit(void)
+{
+ destroy_workqueue(uether_wq);
+
+}
+module_exit(gether_exit);
MODULE_AUTHOR("David Brownell");
+MODULE_DESCRIPTION("ethernet over USB driver");
+MODULE_LICENSE("GPL v2");
/* -1 if not needed */
int bound_dev_if;
u8 tos;
+ kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
*/
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
- void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
int ip_cmsg_send(struct net *net, struct msghdr *msg,
struct ipcm_cookie *ipc, bool allow_ipv6);
int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
- ip_cmsg_recv_offset(msg, skb, 0);
+ ip_cmsg_recv_offset(msg, skb, 0, 0);
}
bool icmp_global_allow(void);
void (*destroy_cgroup)(struct mem_cgroup *memcg);
struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
+ int (*diag_destroy)(struct sock *sk, int err);
};
int proto_register(struct proto *prot, int alloc_slab);
if (!sk_has_account(sk))
return;
sk->sk_forward_alloc += size;
+
+ /* Avoid a possible overflow.
+ * TCP send queues can make this happen, if sk_mem_reclaim()
+ * is not called and more than 2 GBytes are released at once.
+ *
+ * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
+ * no need to hold that much forward allocation anyway.
+ */
+ if (unlikely(sk->sk_forward_alloc >= 1 << 21))
+ __sk_mem_reclaim(sk, 1 << 20);
}
static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
RTA_TABLE,
RTA_MARK,
RTA_MFC_STATS,
+ RTA_UID,
RTA_VIA,
RTA_NEWDST,
RTA_PREF,
#define RTNH_F_OFFLOAD 8 /* offloaded route */
#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */
- #define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN)
+ #define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
/* Macros to handle hexthops */
*/
static bool cgroup_ssid_enabled(int ssid)
{
+ if (CGROUP_SUBSYS_COUNT == 0)
+ return false;
+
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
}
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
+ !uid_eq(cred->euid, tcred->suid) &&
+ !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
ret = -EACCES;
if (!ret && cgroup_on_dfl(dst_cgrp)) {
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
+ /*
+ * The latency of the synchronize_sched() is too high for cgroups,
+ * avoid it at the cost of forcing all readers into the slow path.
+ */
+ rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
+
mutex_lock(&cgroup_mutex);
/* Add init_css_set to the hash table */
current->flags & PF_EXITING))
goto force;
+ /*
+ * Prevent unbounded recursion when reclaim operations need to
+ * allocate memory. This might exceed the limits temporarily,
+ * but we prefer facilitating memory reclaim and getting back
+ * under the limit over triggering OOM kills in these cases.
+ */
+ if (unlikely(current->flags & PF_MEMALLOC))
+ goto force;
+
if (unlikely(task_in_memcg_oom(current)))
goto nomem;
.css_reset = mem_cgroup_css_reset,
.can_attach = mem_cgroup_can_attach,
.cancel_attach = mem_cgroup_cancel_attach,
+ .attach = mem_cgroup_move_task,
.post_attach = mem_cgroup_move_task,
.bind = mem_cgroup_bind,
.dfl_cftypes = memory_files,
#endif
#include <net/l3mdev.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
if (protocol < 0 || protocol >= IPPROTO_MAX)
return -EINVAL;
+ if (!current_has_network())
+ return -EACCES;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
skb_gro_pull(skb, sizeof(*iph));
skb_set_transport_header(skb, skb_gro_offset(skb));
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(struct flowi4 *fl4, struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0,
+ sk ? sock_i_uid(sk) : GLOBAL_ROOT_UID);
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
- const struct sock *sk)
+ struct sock *sk)
{
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
}
-static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0,
+ sock_i_uid(sk));
rcu_read_unlock();
}
-static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
const struct sk_buff *skb)
{
if (skb)
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
int err = ipmr_get_route(net, skb,
fl4->saddr, fl4->daddr,
- r, nowait);
+ r, nowait, portid);
+
if (err <= 0) {
if (!nowait) {
if (err == 0)
int mark;
struct sk_buff *skb;
u32 table_id = RT_TABLE_MAIN;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (netif_index_is_l3_master(net, fl4.flowi4_oif))
fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF;
container_of(table->data, struct net, ipv4.ping_group_range.range);
unsigned int seq;
do {
- seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
}
/* Update system visible IP port range */
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
- write_seqlock(&net->ipv4.ip_local_ports.lock);
+ write_seqlock(&net->ipv4.ping_group_range.lock);
data[0] = low;
data[1] = high;
- write_sequnlock(&net->ipv4.ip_local_ports.lock);
+ write_sequnlock(&net->ipv4.ping_group_range.lock);
}
/* Validate changes from /proc interface. */
return ret;
}
+/* Validate changes from /proc interface. */
+static int proc_tcp_default_init_rwnd(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int old_value = *(int *)ctl->data;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
+
+ if (write && ret == 0 && (new_value < 3 || new_value > 100))
+ *(int *)ctl->data = old_value;
+
+ return ret;
+}
+
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
.proc_handler = proc_dointvec_ms_jiffies,
},
{
+ .procname = "tcp_default_init_rwnd",
+ .data = &sysctl_tcp_default_init_rwnd,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_default_init_rwnd
+ },
+ {
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
- struct ipv6_pinfo *np = inet6_sk(sk);
pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
msg,
- &np->daddr, ntohs(inet->inet_dport),
+ &sk->sk_v6_daddr, ntohs(inet->inet_dport),
tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
* (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
* limit when mss is larger than 1460.
*/
- u32 init_rwnd = TCP_INIT_CWND * 2;
+ u32 init_rwnd = sysctl_tcp_default_init_rwnd;
if (mss > 1460)
init_rwnd = max((1460 * init_rwnd) / mss, 2U);
len = 0;
tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
- if (nskb->ip_summed)
+ if (nskb->ip_summed) {
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
- else
- nskb->csum = skb_copy_and_csum_bits(skb, 0,
- skb_put(nskb, copy),
- copy, nskb->csum);
+ } else {
+ __wsum csum = skb_copy_and_csum_bits(skb, 0,
+ skb_put(nskb, copy),
+ copy, 0);
+ nskb->csum = csum_block_add(nskb->csum, csum, len);
+ }
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
* copying overhead: fragmentation, tunneling, mangling etc.
*/
if (atomic_read(&sk->sk_wmem_alloc) >
- min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+ min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+ sk->sk_sndbuf))
return -EAGAIN;
if (skb_still_in_host_queue(sk, skb))
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sock_i_uid(sk));
if (!saddr && ipc.oif) {
err = l3mdev_get_saddr(net, ipc.oif, fl4);
*addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
- ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
+ ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
err = copied;
if (flags & MSG_TRUNC)
}
EXPORT_SYMBOL(udp_poll);
+int udp_abort(struct sock *sk, int err)
+{
+ lock_sock(sk);
+
+ sk->sk_err = err;
+ sk->sk_error_report(sk);
+ udp_disconnect(sk, 0);
+
+ release_sock(sk);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(udp_abort);
+
struct proto udp_prot = {
.name = "UDP",
.owner = THIS_MODULE,
.compat_getsockopt = compat_udp_getsockopt,
#endif
.clear_sk = sk_prot_clear_portaddr_nulls,
+ .diag_destroy = udp_abort,
};
EXPORT_SYMBOL(udp_prot);
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
__ipv6_regen_rndid(idev);
}
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+ /* Determines into what table to put autoconf PIO/RIO/default routes
+ * learned on this device.
+ *
+ * - If 0, use the same table for every device. This puts routes into
+ * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+ * (but note that these three are currently all equal to
+ * RT6_TABLE_MAIN).
+ * - If > 0, use the specified table.
+ * - If < 0, put routes into table dev->ifindex + (-rt_table).
+ */
+ struct inet6_dev *idev = in6_dev_get(dev);
+ u32 table;
+ int sysctl = idev->cnf.accept_ra_rt_table;
+ if (sysctl == 0) {
+ table = default_table;
+ } else if (sysctl > 0) {
+ table = (u32) sysctl;
+ } else {
+ table = (unsigned) dev->ifindex + (-sysctl);
+ }
+ in6_dev_put(idev);
+ return table;
+}
+
/*
* Add prefix route.
*/
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
+ .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX),
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
+ u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX);
table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
* lo device down, release this obsolete dst and
* reallocate a new router for ifa.
*/
- if (sp_ifa->rt->dst.obsolete > 0) {
+ if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
ip6_rt_put(sp_ifa->rt);
sp_ifa->rt = NULL;
} else {
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
},
#endif
#endif
+ {
+ .procname = "accept_ra_rt_table",
+ .data = &ipv6_devconf.accept_ra_rt_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{
.procname = "proxy_ndp",
.data = &ipv6_devconf.proxy_ndp,
static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
- unsigned int pref);
-static struct rt6_info *rt6_get_route_info(struct net *net,
+ const struct in6_addr *gwaddr, unsigned int pref);
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex);
+ const struct in6_addr *gwaddr);
#endif
struct uncached_list {
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
{
- struct net *net = dev_net(dev);
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
if (rinfo->prefix_len == 0)
rt = rt6_get_dflt_router(gwaddr, dev);
else
- rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
- gwaddr, dev->ifindex);
+ rt = rt6_get_route_info(dev, prefix, rinfo->prefix_len, gwaddr);
if (rt && !lifetime) {
ip6_del_rt(rt);
}
if (!rt && lifetime)
- rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
- pref);
+ rt = rt6_add_route_info(dev, prefix, rinfo->prefix_len, gwaddr, pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sock_i_uid(sk));
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
}
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex)
+ const struct in6_addr *gwaddr)
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(net, RT6_TABLE_INFO);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_INFO));
if (!table)
return NULL;
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->dst.dev->ifindex != ifindex)
+ if (rt->dst.dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
return rt;
}
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
- unsigned int pref)
+ const struct in6_addr *gwaddr, unsigned int pref)
{
struct fib6_config cfg = {
.fc_metric = IP6_RT_PRIO_USER,
- .fc_ifindex = ifindex,
+ .fc_ifindex = dev->ifindex,
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
- .fc_nlinfo.nl_net = net,
+ .fc_nlinfo.nl_net = dev_net(dev),
};
- cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
+ cfg.fc_table = l3mdev_fib_table_by_index(dev_net(dev), dev->ifindex) ? : addrconf_rt_table(dev, RT6_TABLE_INFO);
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
ip6_route_add(&cfg);
- return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(dev, prefix, prefixlen, gwaddr);
}
#endif
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_MAIN));
if (!table)
return NULL;
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
+ .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_DFLT),
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
return rt6_get_dflt_router(gwaddr, dev);
}
-void rt6_purge_dflt_routers(struct net *net)
-{
- struct rt6_info *rt;
- struct fib6_table *table;
- /* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (!table)
- return;
+int rt6_addrconf_purge(struct rt6_info *rt, void *arg) {
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+ (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2))
+ return -1;
+ return 0;
+}
-restart:
- read_lock_bh(&table->tb6_lock);
- for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- ip6_del_rt(rt);
- goto restart;
- }
- }
- read_unlock_bh(&table->tb6_lock);
+void rt6_purge_dflt_routers(struct net *net)
+{
+ fib6_clean_all(net, rt6_addrconf_purge, NULL);
}
static void rtmsg_to_fib6_config(struct net *net,
[RTA_PREF] = { .type = NLA_U8 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
- int err = ip6mr_get_route(net, skb, rtm, nowait);
+ int err = ip6mr_get_route(net, skb, rtm, nowait,
+ portid);
+
if (err <= 0) {
if (!nowait) {
if (err == 0)
if (tb[RTA_MARK])
fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
if (iif) {
struct net_device *dev;
int flags = 0;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
return NULL;
}
+ static void tcp_v6_restore_cb(struct sk_buff *skb)
+ {
+ /* We need to move header back to the beginning if xfrm6_policy_check()
+ * and tcp_v6_fill_cb() are going to be called again.
+ * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+ */
+ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+ sizeof(struct inet6_skb_parm));
+ }
+
/* The socket must have it's spinlock held when we get
* here, unless it is a TCP_LISTEN socket.
*
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
skb_set_owner_r(opt_skb, sk);
+ tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
__kfree_skb(opt_skb);
TCP_SKB_CB(skb)->sacked = 0;
}
- static void tcp_v6_restore_cb(struct sk_buff *skb)
- {
- /* We need to move header back to the beginning if xfrm6_policy_check()
- * and tcp_v6_fill_cb() are going to be called again.
- */
- memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
- sizeof(struct inet6_skb_parm));
- }
-
static int tcp_v6_rcv(struct sk_buff *skb)
{
const struct tcphdr *th;
.proto_cgroup = tcp_proto_cgroup,
#endif
.clear_sk = tcp_v6_clear_sk,
+ .diag_destroy = tcp_abort,
};
static const struct inet6_protocol tcpv6_protocol = {
if (is_udp4) {
if (inet->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+ ip_cmsg_recv_offset(msg, skb,
+ sizeof(struct udphdr), off);
} else {
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (msg->msg_controllen) {
opt = &opt_space;
.compat_getsockopt = compat_udpv6_getsockopt,
#endif
.clear_sk = udp_v6_clear_sk,
+ .diag_destroy = udp_abort,
};
static struct inet_protosw udpv6_protosw = {
projects / firefly-linux-kernel-4.4.55.git / commitdiff