F: drivers/dma/altera-msgdma.c
ALTERA PIO DRIVER
-M: Joyce Ooi <joyce.ooi@intel.com>
+M: Mun Yew Tham <mun.yew.tham@intel.com>
L: linux-gpio@vger.kernel.org
S: Maintained
F: drivers/gpio/gpio-altera.c
F: include/linux/async_tx.h
AT24 EEPROM DRIVER
-M: Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M: Bartosz Golaszewski <brgl@bgdev.pl>
L: linux-i2c@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
F: Documentation/userspace-api/ebpf/
F: arch/*/net/*
F: include/linux/bpf*
+F: include/linux/btf*
F: include/linux/filter.h
F: include/trace/events/xdp.h
F: include/uapi/linux/bpf*
+F: include/uapi/linux/btf*
F: include/uapi/linux/filter.h
F: kernel/bpf/
F: kernel/trace/bpf_trace.c
BROADCOM NETXTREME-E ROCE DRIVER
M: Selvin Xavier <selvin.xavier@broadcom.com>
-M: Naresh Kumar PBS <nareshkumar.pbs@broadcom.com>
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.broadcom.com
GPIO SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
-M: Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M: Bartosz Golaszewski <brgl@bgdev.pl>
L: linux-gpio@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
F: drivers/iio/proximity/mb1232.c
MAXIM MAX77650 PMIC MFD DRIVER
-M: Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M: Bartosz Golaszewski <brgl@bgdev.pl>
L: linux-kernel@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/*/*max77650.yaml
M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Maintained
-F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml
+F: Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
+F: Documentation/devicetree/bindings/sound/st,stm32-*.yaml
F: sound/soc/stm/
STM32 TIMER/LPTIMER DRIVERS
TI DAVINCI MACHINE SUPPORT
M: Sekhar Nori <nsekhar@ti.com>
-R: Bartosz Golaszewski <bgolaszewski@baylibre.com>
+R: Bartosz Golaszewski <brgl@bgdev.pl>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci.git
# runtime. Because the hypervisor is part of the kernel binary, relocations
# produce a kernel VA. We enumerate relocations targeting hyp at build time
# and convert the kernel VAs at those positions to hyp VAs.
-$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel
+$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE
$(call if_changed,hyprel)
# 5) Compile hyp-reloc.S and link it into the existing partially linked object.
int kvm_perf_init(void)
{
- if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled())
- static_branch_enable(&kvm_arm_pmu_available);
-
return perf_register_guest_info_callbacks(&kvm_guest_cbs);
}
kvm_pmu_create_perf_event(vcpu, select_idx);
}
-int kvm_pmu_probe_pmuver(void)
+void kvm_host_pmu_init(struct arm_pmu *pmu)
+{
+ if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF &&
+ !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled())
+ static_branch_enable(&kvm_arm_pmu_available);
+}
+
+static int kvm_pmu_probe_pmuver(void)
{
struct perf_event_attr attr = { };
struct perf_event *event;
#include <asm/unistd.h>
#include <asm/errno.h>
#include <asm/setup.h>
-#include <asm/segment.h>
#include <asm/traps.h>
#include <asm/asm-offsets.h>
#include <asm/entry.h>
.globl system_call
.globl resume
.globl ret_from_exception
-.globl ret_from_signal
.globl sys_call_table
.globl bad_interrupt
.globl inthandler1
subql #4,%sp /* dummy return address */
SAVE_SWITCH_STACK
jbsr syscall_trace_leave
-
-ret_from_signal:
RESTORE_SWITCH_STACK
addql #4,%sp
jra ret_from_exception
select NO_DMA if !MMU && !COLDFIRE
select OLD_SIGACTION
select OLD_SIGSUSPEND3
- select SET_FS
select UACCESS_MEMCPY if !MMU
select VIRT_TO_BUS
select ZONE_DMA
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/setup.h>
-#include <asm/segment.h>
#include <asm/asm-offsets.h>
#include <asm/entry.h>
.globl system_call
.globl resume
.globl ret_from_exception
-.globl ret_from_signal
.globl sys_call_table
.globl inthandler
subql #4,%sp /* dummy return address */
SAVE_SWITCH_STACK
jbsr syscall_trace_leave
-
-ret_from_signal:
RESTORE_SWITCH_STACK
addql #4,%sp
#define __ASM_M68K_PROCESSOR_H
#include <linux/thread_info.h>
-#include <asm/segment.h>
#include <asm/fpu.h>
#include <asm/ptrace.h>
#define TASK_UNMAPPED_BASE 0
#endif
+/* Address spaces (or Function Codes in Motorola lingo) */
+#define USER_DATA 1
+#define USER_PROGRAM 2
+#define SUPER_DATA 5
+#define SUPER_PROGRAM 6
+#define CPU_SPACE 7
+
+#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES
+/*
+ * Set the SFC/DFC registers for special MM operations. For most normal
+ * operation these remain set to USER_DATA for the uaccess routines.
+ */
+static inline void set_fc(unsigned long val)
+{
+ WARN_ON_ONCE(in_interrupt());
+
+ __asm__ __volatile__ ("movec %0,%/sfc\n\t"
+ "movec %0,%/dfc\n\t"
+ : /* no outputs */ : "r" (val) : "memory");
+}
+#else
+static inline void set_fc(unsigned long val)
+{
+}
+#endif /* CONFIG_CPU_HAS_ADDRESS_SPACES */
+
struct thread_struct {
unsigned long ksp; /* kernel stack pointer */
unsigned long usp; /* user stack pointer */
unsigned short sr; /* saved status register */
- unsigned short fs; /* saved fs (sfc, dfc) */
+ unsigned short fc; /* saved fc (sfc, dfc) */
unsigned long crp[2]; /* cpu root pointer */
unsigned long esp0; /* points to SR of stack frame */
unsigned long faddr; /* info about last fault */
#define INIT_THREAD { \
.ksp = sizeof(init_stack) + (unsigned long) init_stack, \
.sr = PS_S, \
- .fs = __KERNEL_DS, \
+ .fc = USER_DATA, \
}
/*
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_SEGMENT_H
-#define _M68K_SEGMENT_H
-
-/* define constants */
-/* Address spaces (FC0-FC2) */
-#define USER_DATA (1)
-#ifndef __USER_DS
-#define __USER_DS (USER_DATA)
-#endif
-#define USER_PROGRAM (2)
-#define SUPER_DATA (5)
-#ifndef __KERNEL_DS
-#define __KERNEL_DS (SUPER_DATA)
-#endif
-#define SUPER_PROGRAM (6)
-#define CPU_SPACE (7)
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
- unsigned long seg;
-} mm_segment_t;
-
-#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) })
-
-#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES
-/*
- * Get/set the SFC/DFC registers for MOVES instructions
- */
-#define USER_DS MAKE_MM_SEG(__USER_DS)
-#define KERNEL_DS MAKE_MM_SEG(__KERNEL_DS)
-
-static inline mm_segment_t get_fs(void)
-{
- mm_segment_t _v;
- __asm__ ("movec %/dfc,%0":"=r" (_v.seg):);
- return _v;
-}
-
-static inline void set_fs(mm_segment_t val)
-{
- __asm__ __volatile__ ("movec %0,%/sfc\n\t"
- "movec %0,%/dfc\n\t"
- : /* no outputs */ : "r" (val.seg) : "memory");
-}
-
-#else
-#define USER_DS MAKE_MM_SEG(TASK_SIZE)
-#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF)
-#define get_fs() (current_thread_info()->addr_limit)
-#define set_fs(x) (current_thread_info()->addr_limit = (x))
-#endif
-
-#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _M68K_SEGMENT_H */
#include <asm/types.h>
#include <asm/page.h>
-#include <asm/segment.h>
/*
* On machines with 4k pages we default to an 8k thread size, though we
struct thread_info {
struct task_struct *task; /* main task structure */
unsigned long flags;
- mm_segment_t addr_limit; /* thread address space */
int preempt_count; /* 0 => preemptable, <0 => BUG */
__u32 cpu; /* should always be 0 on m68k */
unsigned long tp_value; /* thread pointer */
#define INIT_THREAD_INFO(tsk) \
{ \
.task = &tsk, \
- .addr_limit = KERNEL_DS, \
.preempt_count = INIT_PREEMPT_COUNT, \
}
if (CPU_IS_COLDFIRE) {
mmu_write(MMUOR, MMUOR_CNL);
} else if (CPU_IS_040_OR_060) {
- mm_segment_t old_fs = get_fs();
- set_fs(KERNEL_DS);
+ set_fc(SUPER_DATA);
__asm__ __volatile__(".chip 68040\n\t"
"pflush (%0)\n\t"
".chip 68k"
: : "a" (addr));
- set_fs(old_fs);
+ set_fc(USER_DATA);
} else if (CPU_IS_020_OR_030)
__asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr));
}
static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
{
- if (vma->vm_mm == current->active_mm) {
- mm_segment_t old_fs = force_uaccess_begin();
-
+ if (vma->vm_mm == current->active_mm)
__flush_tlb_one(addr);
- force_uaccess_end(old_fs);
- }
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
} un;
};
+#ifdef CONFIG_M68040
+asmlinkage void berr_040cleanup(struct frame *fp);
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _M68K_TRAPS_H */
*/
#include <linux/compiler.h>
#include <linux/types.h>
-#include <asm/segment.h>
#include <asm/extable.h>
/* We let the MMU do all checking */
static inline int access_ok(const void __user *addr,
unsigned long size)
{
+ /*
+ * XXX: for !CONFIG_CPU_HAS_ADDRESS_SPACES this really needs to check
+ * for TASK_SIZE!
+ */
return 1;
}
#define MOVES "move"
#endif
-extern int __put_user_bad(void);
-extern int __get_user_bad(void);
-
-#define __put_user_asm(res, x, ptr, bwl, reg, err) \
+#define __put_user_asm(inst, res, x, ptr, bwl, reg, err) \
asm volatile ("\n" \
- "1: "MOVES"."#bwl" %2,%1\n" \
+ "1: "inst"."#bwl" %2,%1\n" \
"2:\n" \
" .section .fixup,\"ax\"\n" \
" .even\n" \
: "+d" (res), "=m" (*(ptr)) \
: #reg (x), "i" (err))
+#define __put_user_asm8(inst, res, x, ptr) \
+do { \
+ const void *__pu_ptr = (const void __force *)(ptr); \
+ \
+ asm volatile ("\n" \
+ "1: "inst".l %2,(%1)+\n" \
+ "2: "inst".l %R2,(%1)\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .even\n" \
+ "10: movel %3,%0\n" \
+ " jra 3b\n" \
+ " .previous\n" \
+ "\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,10b\n" \
+ " .long 2b,10b\n" \
+ " .long 3b,10b\n" \
+ " .previous" \
+ : "+d" (res), "+a" (__pu_ptr) \
+ : "r" (x), "i" (-EFAULT) \
+ : "memory"); \
+} while (0)
+
/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
__chk_user_ptr(ptr); \
switch (sizeof (*(ptr))) { \
case 1: \
- __put_user_asm(__pu_err, __pu_val, ptr, b, d, -EFAULT); \
+ __put_user_asm(MOVES, __pu_err, __pu_val, ptr, b, d, -EFAULT); \
break; \
case 2: \
- __put_user_asm(__pu_err, __pu_val, ptr, w, r, -EFAULT); \
+ __put_user_asm(MOVES, __pu_err, __pu_val, ptr, w, r, -EFAULT); \
break; \
case 4: \
- __put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT); \
+ __put_user_asm(MOVES, __pu_err, __pu_val, ptr, l, r, -EFAULT); \
break; \
case 8: \
- { \
- const void __user *__pu_ptr = (ptr); \
- asm volatile ("\n" \
- "1: "MOVES".l %2,(%1)+\n" \
- "2: "MOVES".l %R2,(%1)\n" \
- "3:\n" \
- " .section .fixup,\"ax\"\n" \
- " .even\n" \
- "10: movel %3,%0\n" \
- " jra 3b\n" \
- " .previous\n" \
- "\n" \
- " .section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 1b,10b\n" \
- " .long 2b,10b\n" \
- " .long 3b,10b\n" \
- " .previous" \
- : "+d" (__pu_err), "+a" (__pu_ptr) \
- : "r" (__pu_val), "i" (-EFAULT) \
- : "memory"); \
+ __put_user_asm8(MOVES, __pu_err, __pu_val, ptr); \
break; \
- } \
default: \
- __pu_err = __put_user_bad(); \
- break; \
+ BUILD_BUG(); \
} \
__pu_err; \
})
#define put_user(x, ptr) __put_user(x, ptr)
-#define __get_user_asm(res, x, ptr, type, bwl, reg, err) ({ \
+#define __get_user_asm(inst, res, x, ptr, type, bwl, reg, err) ({ \
type __gu_val; \
asm volatile ("\n" \
- "1: "MOVES"."#bwl" %2,%1\n" \
+ "1: "inst"."#bwl" %2,%1\n" \
"2:\n" \
" .section .fixup,\"ax\"\n" \
" .even\n" \
(x) = (__force typeof(*(ptr)))(__force unsigned long)__gu_val; \
})
+#define __get_user_asm8(inst, res, x, ptr) \
+do { \
+ const void *__gu_ptr = (const void __force *)(ptr); \
+ union { \
+ u64 l; \
+ __typeof__(*(ptr)) t; \
+ } __gu_val; \
+ \
+ asm volatile ("\n" \
+ "1: "inst".l (%2)+,%1\n" \
+ "2: "inst".l (%2),%R1\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .even\n" \
+ "10: move.l %3,%0\n" \
+ " sub.l %1,%1\n" \
+ " sub.l %R1,%R1\n" \
+ " jra 3b\n" \
+ " .previous\n" \
+ "\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,10b\n" \
+ " .long 2b,10b\n" \
+ " .previous" \
+ : "+d" (res), "=&r" (__gu_val.l), \
+ "+a" (__gu_ptr) \
+ : "i" (-EFAULT) \
+ : "memory"); \
+ (x) = __gu_val.t; \
+} while (0)
+
#define __get_user(x, ptr) \
({ \
int __gu_err = 0; \
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: \
- __get_user_asm(__gu_err, x, ptr, u8, b, d, -EFAULT); \
+ __get_user_asm(MOVES, __gu_err, x, ptr, u8, b, d, -EFAULT); \
break; \
case 2: \
- __get_user_asm(__gu_err, x, ptr, u16, w, r, -EFAULT); \
+ __get_user_asm(MOVES, __gu_err, x, ptr, u16, w, r, -EFAULT); \
break; \
case 4: \
- __get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \
+ __get_user_asm(MOVES, __gu_err, x, ptr, u32, l, r, -EFAULT); \
break; \
- case 8: { \
- const void __user *__gu_ptr = (ptr); \
- union { \
- u64 l; \
- __typeof__(*(ptr)) t; \
- } __gu_val; \
- asm volatile ("\n" \
- "1: "MOVES".l (%2)+,%1\n" \
- "2: "MOVES".l (%2),%R1\n" \
- "3:\n" \
- " .section .fixup,\"ax\"\n" \
- " .even\n" \
- "10: move.l %3,%0\n" \
- " sub.l %1,%1\n" \
- " sub.l %R1,%R1\n" \
- " jra 3b\n" \
- " .previous\n" \
- "\n" \
- " .section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 1b,10b\n" \
- " .long 2b,10b\n" \
- " .previous" \
- : "+d" (__gu_err), "=&r" (__gu_val.l), \
- "+a" (__gu_ptr) \
- : "i" (-EFAULT) \
- : "memory"); \
- (x) = __gu_val.t; \
+ case 8: \
+ __get_user_asm8(MOVES, __gu_err, x, ptr); \
break; \
- } \
default: \
- __gu_err = __get_user_bad(); \
- break; \
+ BUILD_BUG(); \
} \
__gu_err; \
})
switch (n) {
case 1:
- __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1);
+ __put_user_asm(MOVES, res, *(u8 *)from, (u8 __user *)to,
+ b, d, 1);
break;
case 2:
- __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, r, 2);
+ __put_user_asm(MOVES, res, *(u16 *)from, (u16 __user *)to,
+ w, r, 2);
break;
case 3:
__constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,);
break;
case 4:
- __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4);
+ __put_user_asm(MOVES, res, *(u32 *)from, (u32 __user *)to,
+ l, r, 4);
break;
case 5:
__constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,);
#define INLINE_COPY_FROM_USER
#define INLINE_COPY_TO_USER
-#define user_addr_max() \
- (uaccess_kernel() ? ~0UL : TASK_SIZE)
+#define HAVE_GET_KERNEL_NOFAULT
+
+#define __get_kernel_nofault(dst, src, type, err_label) \
+do { \
+ type *__gk_dst = (type *)(dst); \
+ type *__gk_src = (type *)(src); \
+ int __gk_err = 0; \
+ \
+ switch (sizeof(type)) { \
+ case 1: \
+ __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \
+ u8, b, d, -EFAULT); \
+ break; \
+ case 2: \
+ __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \
+ u16, w, r, -EFAULT); \
+ break; \
+ case 4: \
+ __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \
+ u32, l, r, -EFAULT); \
+ break; \
+ case 8: \
+ __get_user_asm8("move", __gk_err, *__gk_dst, __gk_src); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ if (unlikely(__gk_err)) \
+ goto err_label; \
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label) \
+do { \
+ type __pk_src = *(type *)(src); \
+ type *__pk_dst = (type *)(dst); \
+ int __pk_err = 0; \
+ \
+ switch (sizeof(type)) { \
+ case 1: \
+ __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \
+ b, d, -EFAULT); \
+ break; \
+ case 2: \
+ __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \
+ w, r, -EFAULT); \
+ break; \
+ case 4: \
+ __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \
+ l, r, -EFAULT); \
+ break; \
+ case 8: \
+ __put_user_asm8("move", __pk_err, __pk_src, __pk_dst); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ if (unlikely(__pk_err)) \
+ goto err_label; \
+} while (0)
extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strnlen_user(const char __user *str, long n);
DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
DEFINE(THREAD_SR, offsetof(struct thread_struct, sr));
- DEFINE(THREAD_FS, offsetof(struct thread_struct, fs));
+ DEFINE(THREAD_FC, offsetof(struct thread_struct, fc));
DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp));
DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0));
DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp));
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/setup.h>
-#include <asm/segment.h>
#include <asm/traps.h>
#include <asm/unistd.h>
#include <asm/asm-offsets.h>
ENTRY(sys_sigreturn)
SAVE_SWITCH_STACK
- movel %sp,%sp@- | switch_stack pointer
- pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
+ movel %sp,%a1 | switch_stack pointer
+ lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer
+ lea %sp@(-84),%sp | leave a gap
+ movel %a1,%sp@-
+ movel %a0,%sp@-
jbsr do_sigreturn
- addql #8,%sp
- RESTORE_SWITCH_STACK
- rts
+ jra 1f | shared with rt_sigreturn()
ENTRY(sys_rt_sigreturn)
SAVE_SWITCH_STACK
- movel %sp,%sp@- | switch_stack pointer
- pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
+ movel %sp,%a1 | switch_stack pointer
+ lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer
+ lea %sp@(-84),%sp | leave a gap
+ movel %a1,%sp@-
+ movel %a0,%sp@-
+ | stack contents:
+ | [original pt_regs address] [original switch_stack address]
+ | [gap] [switch_stack] [pt_regs] [exception frame]
jbsr do_rt_sigreturn
- addql #8,%sp
+
+1:
+ | stack contents now:
+ | [original pt_regs address] [original switch_stack address]
+ | [unused part of the gap] [moved switch_stack] [moved pt_regs]
+ | [replacement exception frame]
+ | return value of do_{rt_,}sigreturn() points to moved switch_stack.
+
+ movel %d0,%sp | discard the leftover junk
RESTORE_SWITCH_STACK
+ | stack contents now is just [syscall return address] [pt_regs] [frame]
+ | return pt_regs.d0
+ movel %sp@(PT_OFF_D0+4),%d0
rts
ENTRY(buserr)
addql #4,%sp
jra .Lret_from_exception
-ENTRY(ret_from_signal)
- movel %curptr@(TASK_STACK),%a1
- tstb %a1@(TINFO_FLAGS+2)
- jge 1f
- jbsr syscall_trace
-1: RESTORE_SWITCH_STACK
- addql #4,%sp
-/* on 68040 complete pending writebacks if any */
-#ifdef CONFIG_M68040
- bfextu %sp@(PT_OFF_FORMATVEC){#0,#4},%d0
- subql #7,%d0 | bus error frame ?
- jbne 1f
- movel %sp,%sp@-
- jbsr berr_040cleanup
- addql #4,%sp
-1:
-#endif
- jra .Lret_from_exception
-
ENTRY(system_call)
SAVE_ALL_SYS
/* save fs (sfc,%dfc) (may be pointing to kernel memory) */
movec %sfc,%d0
- movew %d0,%a0@(TASK_THREAD+THREAD_FS)
+ movew %d0,%a0@(TASK_THREAD+THREAD_FC)
/* save usp */
/* it is better to use a movel here instead of a movew 8*) */
movel %a0,%usp
/* restore fs (sfc,%dfc) */
- movew %a1@(TASK_THREAD+THREAD_FS),%a0
+ movew %a1@(TASK_THREAD+THREAD_FC),%a0
movec %a0,%sfc
movec %a0,%dfc
void flush_thread(void)
{
- current->thread.fs = __USER_DS;
+ current->thread.fc = USER_DATA;
#ifdef CONFIG_FPU
if (!FPU_IS_EMU) {
unsigned long zero = 0;
* Must save the current SFC/DFC value, NOT the value when
* the parent was last descheduled - RGH 10-08-96
*/
- p->thread.fs = get_fs().seg;
+ p->thread.fc = USER_DATA;
if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
/* kernel thread */
if (CPU_IS_060 ? sc->sc_fpstate[2] : sc->sc_fpstate[0]) {
fpu_version = sc->sc_fpstate[0];
- if (CPU_IS_020_OR_030 &&
+ if (CPU_IS_020_OR_030 && !regs->stkadj &&
regs->vector >= (VEC_FPBRUC * 4) &&
regs->vector <= (VEC_FPNAN * 4)) {
/* Clear pending exception in 68882 idle frame */
if (!(CPU_IS_060 || CPU_IS_COLDFIRE))
context_size = fpstate[1];
fpu_version = fpstate[0];
- if (CPU_IS_020_OR_030 &&
+ if (CPU_IS_020_OR_030 && !regs->stkadj &&
regs->vector >= (VEC_FPBRUC * 4) &&
regs->vector <= (VEC_FPNAN * 4)) {
/* Clear pending exception in 68882 idle frame */
static int mangle_kernel_stack(struct pt_regs *regs, int formatvec,
void __user *fp)
{
- int fsize = frame_extra_sizes(formatvec >> 12);
- if (fsize < 0) {
+ int extra = frame_extra_sizes(formatvec >> 12);
+ char buf[sizeof_field(struct frame, un)];
+
+ if (extra < 0) {
/*
* user process trying to return with weird frame format
*/
pr_debug("user process returning with weird frame format\n");
- return 1;
+ return -1;
}
- if (!fsize) {
- regs->format = formatvec >> 12;
- regs->vector = formatvec & 0xfff;
- } else {
- struct switch_stack *sw = (struct switch_stack *)regs - 1;
- /* yes, twice as much as max(sizeof(frame.un.fmt<x>)) */
- unsigned long buf[sizeof_field(struct frame, un) / 2];
-
- /* that'll make sure that expansion won't crap over data */
- if (copy_from_user(buf + fsize / 4, fp, fsize))
- return 1;
-
- /* point of no return */
- regs->format = formatvec >> 12;
- regs->vector = formatvec & 0xfff;
-#define frame_offset (sizeof(struct pt_regs)+sizeof(struct switch_stack))
- __asm__ __volatile__ (
-#ifdef CONFIG_COLDFIRE
- " movel %0,%/sp\n\t"
- " bra ret_from_signal\n"
-#else
- " movel %0,%/a0\n\t"
- " subl %1,%/a0\n\t" /* make room on stack */
- " movel %/a0,%/sp\n\t" /* set stack pointer */
- /* move switch_stack and pt_regs */
- "1: movel %0@+,%/a0@+\n\t"
- " dbra %2,1b\n\t"
- " lea %/sp@(%c3),%/a0\n\t" /* add offset of fmt */
- " lsrl #2,%1\n\t"
- " subql #1,%1\n\t"
- /* copy to the gap we'd made */
- "2: movel %4@+,%/a0@+\n\t"
- " dbra %1,2b\n\t"
- " bral ret_from_signal\n"
+ if (extra && copy_from_user(buf, fp, extra))
+ return -1;
+ regs->format = formatvec >> 12;
+ regs->vector = formatvec & 0xfff;
+ if (extra) {
+ void *p = (struct switch_stack *)regs - 1;
+ struct frame *new = (void *)regs - extra;
+ int size = sizeof(struct pt_regs)+sizeof(struct switch_stack);
+
+ memmove(p - extra, p, size);
+ memcpy(p - extra + size, buf, extra);
+ current->thread.esp0 = (unsigned long)&new->ptregs;
+#ifdef CONFIG_M68040
+ /* on 68040 complete pending writebacks if any */
+ if (new->ptregs.format == 7) // bus error frame
+ berr_040cleanup(new);
#endif
- : /* no outputs, it doesn't ever return */
- : "a" (sw), "d" (fsize), "d" (frame_offset/4-1),
- "n" (frame_offset), "a" (buf + fsize/4)
- : "a0");
-#undef frame_offset
}
- return 0;
+ return extra;
}
static inline int
{
int formatvec;
struct sigcontext context;
- int err = 0;
siginfo_build_tests();
/* get previous context */
if (copy_from_user(&context, usc, sizeof(context)))
- goto badframe;
+ return -1;
/* restore passed registers */
regs->d0 = context.sc_d0;
wrusp(context.sc_usp);
formatvec = context.sc_formatvec;
- err = restore_fpu_state(&context);
+ if (restore_fpu_state(&context))
+ return -1;
- if (err || mangle_kernel_stack(regs, formatvec, fp))
- goto badframe;
-
- return 0;
-
-badframe:
- return 1;
+ return mangle_kernel_stack(regs, formatvec, fp);
}
static inline int
err = __get_user(temp, &uc->uc_mcontext.version);
if (temp != MCONTEXT_VERSION)
- goto badframe;
+ return -1;
/* restore passed registers */
err |= __get_user(regs->d0, &gregs[0]);
err |= __get_user(regs->d1, &gregs[1]);
err |= restore_altstack(&uc->uc_stack);
if (err)
- goto badframe;
+ return -1;
- if (mangle_kernel_stack(regs, temp, &uc->uc_extra))
- goto badframe;
-
- return 0;
-
-badframe:
- return 1;
+ return mangle_kernel_stack(regs, temp, &uc->uc_extra);
}
-asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
+asmlinkage void *do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
{
unsigned long usp = rdusp();
struct sigframe __user *frame = (struct sigframe __user *)(usp - 4);
sigset_t set;
+ int size;
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->sc, frame + 1))
+ size = restore_sigcontext(regs, &frame->sc, frame + 1);
+ if (size < 0)
goto badframe;
- return regs->d0;
+ return (void *)sw - size;
badframe:
force_sig(SIGSEGV);
- return 0;
+ return sw;
}
-asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
+asmlinkage void *do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
{
unsigned long usp = rdusp();
struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4);
sigset_t set;
+ int size;
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
set_current_blocked(&set);
- if (rt_restore_ucontext(regs, sw, &frame->uc))
+ size = rt_restore_ucontext(regs, sw, &frame->uc);
+ if (size < 0)
goto badframe;
- return regs->d0;
+ return (void *)sw - size;
badframe:
force_sig(SIGSEGV);
- return 0;
+ return sw;
+}
+
+static inline struct pt_regs *rte_regs(struct pt_regs *regs)
+{
+ return (void *)regs + regs->stkadj;
}
static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs,
unsigned long mask)
{
+ struct pt_regs *tregs = rte_regs(regs);
sc->sc_mask = mask;
sc->sc_usp = rdusp();
sc->sc_d0 = regs->d0;
sc->sc_d1 = regs->d1;
sc->sc_a0 = regs->a0;
sc->sc_a1 = regs->a1;
- sc->sc_sr = regs->sr;
- sc->sc_pc = regs->pc;
- sc->sc_formatvec = regs->format << 12 | regs->vector;
+ sc->sc_sr = tregs->sr;
+ sc->sc_pc = tregs->pc;
+ sc->sc_formatvec = tregs->format << 12 | tregs->vector;
save_a5_state(sc, regs);
save_fpu_state(sc, regs);
}
static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *regs)
{
struct switch_stack *sw = (struct switch_stack *)regs - 1;
+ struct pt_regs *tregs = rte_regs(regs);
greg_t __user *gregs = uc->uc_mcontext.gregs;
int err = 0;
err |= __put_user(sw->a5, &gregs[13]);
err |= __put_user(sw->a6, &gregs[14]);
err |= __put_user(rdusp(), &gregs[15]);
- err |= __put_user(regs->pc, &gregs[16]);
- err |= __put_user(regs->sr, &gregs[17]);
- err |= __put_user((regs->format << 12) | regs->vector, &uc->uc_formatvec);
+ err |= __put_user(tregs->pc, &gregs[16]);
+ err |= __put_user(tregs->sr, &gregs[17]);
+ err |= __put_user((tregs->format << 12) | tregs->vector, &uc->uc_formatvec);
err |= rt_save_fpu_state(uc, regs);
return err;
}
struct pt_regs *regs)
{
struct sigframe __user *frame;
- int fsize = frame_extra_sizes(regs->format);
+ struct pt_regs *tregs = rte_regs(regs);
+ int fsize = frame_extra_sizes(tregs->format);
struct sigcontext context;
int err = 0, sig = ksig->sig;
if (fsize < 0) {
pr_debug("setup_frame: Unknown frame format %#x\n",
- regs->format);
+ tregs->format);
return -EFAULT;
}
err |= __put_user(sig, &frame->sig);
- err |= __put_user(regs->vector, &frame->code);
+ err |= __put_user(tregs->vector, &frame->code);
err |= __put_user(&frame->sc, &frame->psc);
if (_NSIG_WORDS > 1)
push_cache ((unsigned long) &frame->retcode);
/*
- * Set up registers for signal handler. All the state we are about
- * to destroy is successfully copied to sigframe.
- */
- wrusp ((unsigned long) frame);
- regs->pc = (unsigned long) ksig->ka.sa.sa_handler;
- adjustformat(regs);
-
- /*
* This is subtle; if we build more than one sigframe, all but the
* first one will see frame format 0 and have fsize == 0, so we won't
* screw stkadj.
*/
- if (fsize)
+ if (fsize) {
regs->stkadj = fsize;
-
- /* Prepare to skip over the extra stuff in the exception frame. */
- if (regs->stkadj) {
- struct pt_regs *tregs =
- (struct pt_regs *)((ulong)regs + regs->stkadj);
+ tregs = rte_regs(regs);
pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
- /* This must be copied with decreasing addresses to
- handle overlaps. */
tregs->vector = 0;
tregs->format = 0;
- tregs->pc = regs->pc;
tregs->sr = regs->sr;
}
+
+ /*
+ * Set up registers for signal handler. All the state we are about
+ * to destroy is successfully copied to sigframe.
+ */
+ wrusp ((unsigned long) frame);
+ tregs->pc = (unsigned long) ksig->ka.sa.sa_handler;
+ adjustformat(regs);
+
return 0;
}
struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
- int fsize = frame_extra_sizes(regs->format);
+ struct pt_regs *tregs = rte_regs(regs);
+ int fsize = frame_extra_sizes(tregs->format);
int err = 0, sig = ksig->sig;
if (fsize < 0) {
push_cache ((unsigned long) &frame->retcode);
/*
- * Set up registers for signal handler. All the state we are about
- * to destroy is successfully copied to sigframe.
- */
- wrusp ((unsigned long) frame);
- regs->pc = (unsigned long) ksig->ka.sa.sa_handler;
- adjustformat(regs);
-
- /*
* This is subtle; if we build more than one sigframe, all but the
* first one will see frame format 0 and have fsize == 0, so we won't
* screw stkadj.
*/
- if (fsize)
+ if (fsize) {
regs->stkadj = fsize;
-
- /* Prepare to skip over the extra stuff in the exception frame. */
- if (regs->stkadj) {
- struct pt_regs *tregs =
- (struct pt_regs *)((ulong)regs + regs->stkadj);
+ tregs = rte_regs(regs);
pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
- /* This must be copied with decreasing addresses to
- handle overlaps. */
tregs->vector = 0;
tregs->format = 0;
- tregs->pc = regs->pc;
tregs->sr = regs->sr;
}
+
+ /*
+ * Set up registers for signal handler. All the state we are about
+ * to destroy is successfully copied to sigframe.
+ */
+ wrusp ((unsigned long) frame);
+ tregs->pc = (unsigned long) ksig->ka.sa.sa_handler;
+ adjustformat(regs);
return 0;
}
static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs)
{
unsigned long mmusr;
- mm_segment_t old_fs = get_fs();
- set_fs(MAKE_MM_SEG(wbs));
+ set_fc(wbs);
if (iswrite)
asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr));
asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr));
- set_fs(old_fs);
+ set_fc(USER_DATA);
return mmusr;
}
unsigned long wbd)
{
int res = 0;
- mm_segment_t old_fs = get_fs();
- /* set_fs can not be moved, otherwise put_user() may oops */
- set_fs(MAKE_MM_SEG(wbs));
+ set_fc(wbs);
switch (wbs & WBSIZ_040) {
case BA_SIZE_BYTE:
break;
}
- /* set_fs can not be moved, otherwise put_user() may oops */
- set_fs(old_fs);
-
+ set_fc(USER_DATA);
pr_debug("do_040writeback1, res=%d\n", res);
#include <linux/uaccess.h>
#include <asm/io.h>
-#include <asm/segment.h>
#include <asm/setup.h>
#include <asm/macintosh.h>
#include <asm/mac_via.h>
if (mmusr & MMU_R_040)
return (mmusr & PAGE_MASK) | (vaddr & ~PAGE_MASK);
} else {
- unsigned short mmusr;
- unsigned long *descaddr;
-
- asm volatile ("ptestr %3,%2@,#7,%0\n\t"
- "pmove %%psr,%1"
- : "=a&" (descaddr), "=m" (mmusr)
- : "a" (vaddr), "d" (get_fs().seg));
- if (mmusr & (MMU_I|MMU_B|MMU_L))
- return 0;
- descaddr = phys_to_virt((unsigned long)descaddr);
- switch (mmusr & MMU_NUM) {
- case 1:
- return (*descaddr & 0xfe000000) | (vaddr & 0x01ffffff);
- case 2:
- return (*descaddr & 0xfffc0000) | (vaddr & 0x0003ffff);
- case 3:
- return (*descaddr & PAGE_MASK) | (vaddr & ~PAGE_MASK);
- }
+ WARN_ON_ONCE(!CPU_IS_040_OR_060);
}
return 0;
}
void flush_icache_range(unsigned long address, unsigned long endaddr)
{
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
+ set_fc(SUPER_DATA);
flush_icache_user_range(address, endaddr);
- set_fs(old_fs);
+ set_fc(USER_DATA);
}
EXPORT_SYMBOL(flush_icache_range);
if (!empty_zero_page)
panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
__func__, PAGE_SIZE, PAGE_SIZE);
-
- /*
- * Set up SFC/DFC registers (user data space).
- */
- set_fs (USER_DS);
-
max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT;
free_area_init(max_zone_pfn);
}
#include <linux/vmalloc.h>
#include <asm/setup.h>
-#include <asm/segment.h>
#include <asm/page.h>
#include <asm/io.h>
#include <asm/tlbflush.h>
#include <linux/gfp.h>
#include <asm/setup.h>
-#include <asm/segment.h>
#include <asm/page.h>
#include <asm/traps.h>
#include <asm/machdep.h>
/*
* Set up SFC/DFC registers
*/
- set_fs(KERNEL_DS);
+ set_fc(USER_DATA);
#ifdef DEBUG
printk ("before free_area_init\n");
#include <asm/intersil.h>
#include <asm/irq.h>
#include <asm/sections.h>
-#include <asm/segment.h>
#include <asm/sun3ints.h>
char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
sun3_reserved_pmeg[249] = 1;
sun3_reserved_pmeg[252] = 1;
sun3_reserved_pmeg[253] = 1;
- set_fs(KERNEL_DS);
+ set_fc(USER_DATA);
}
/* Without this, Bad Things happen when something calls arch_reset. */
#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/sun3mmu.h>
-#include <asm/segment.h>
#include <asm/oplib.h>
#include <asm/mmu_context.h>
#include <asm/dvma.h>
for(seg = 0; seg < PAGE_OFFSET; seg += SUN3_PMEG_SIZE)
sun3_put_segmap(seg, SUN3_INVALID_PMEG);
- set_fs(MAKE_MM_SEG(3));
+ set_fc(3);
for(seg = 0; seg < 0x10000000; seg += SUN3_PMEG_SIZE) {
i = sun3_get_segmap(seg);
for(j = 1; j < CONTEXTS_NUM; j++)
(*(romvec->pv_setctxt))(j, (void *)seg, i);
}
- set_fs(KERNEL_DS);
-
+ set_fc(USER_DATA);
}
/* erase the mappings for a dead context. Uses the pg_dir for hints
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
-#include <asm/segment.h>
#include <asm/intersil.h>
#include <asm/oplib.h>
#include <asm/sun3ints.h>
#include <asm/traps.h>
#include <asm/sun3xprom.h>
#include <asm/idprom.h>
-#include <asm/segment.h>
#include <asm/sun3ints.h>
#include <asm/openprom.h>
#include <asm/machines.h>
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \
func##_positive)
+static bool is_bad_offset(int b_off)
+{
+ return b_off > 0x1ffff || b_off < -0x20000;
+}
+
static int build_body(struct jit_ctx *ctx)
{
const struct bpf_prog *prog = ctx->skf;
/* Load return register on DS for failures */
emit_reg_move(r_ret, r_zero, ctx);
/* Return with error */
- emit_b(b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_b(b_off, ctx);
emit_nop(ctx);
break;
case BPF_LD | BPF_W | BPF_IND:
emit_jalr(MIPS_R_RA, r_s0, ctx);
emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */
/* Check the error value */
- emit_bcond(MIPS_COND_NE, r_ret, 0,
- b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_bcond(MIPS_COND_NE, r_ret, 0, b_off, ctx);
emit_reg_move(r_ret, r_zero, ctx);
/* We are good */
/* X <- P[1:K] & 0xf */
/* A /= X */
ctx->flags |= SEEN_X | SEEN_A;
/* Check if r_X is zero */
- emit_bcond(MIPS_COND_EQ, r_X, r_zero,
- b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx);
emit_load_imm(r_ret, 0, ctx); /* delay slot */
emit_div(r_A, r_X, ctx);
break;
/* A %= X */
ctx->flags |= SEEN_X | SEEN_A;
/* Check if r_X is zero */
- emit_bcond(MIPS_COND_EQ, r_X, r_zero,
- b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx);
emit_load_imm(r_ret, 0, ctx); /* delay slot */
emit_mod(r_A, r_X, ctx);
break;
break;
case BPF_JMP | BPF_JA:
/* pc += K */
- emit_b(b_imm(i + k + 1, ctx), ctx);
+ b_off = b_imm(i + k + 1, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_b(b_off, ctx);
emit_nop(ctx);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
break;
case BPF_RET | BPF_A:
ctx->flags |= SEEN_A;
- if (i != prog->len - 1)
+ if (i != prog->len - 1) {
/*
* If this is not the last instruction
* then jump to the epilogue
*/
- emit_b(b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_b(b_off, ctx);
+ }
emit_reg_move(r_ret, r_A, ctx); /* delay slot */
break;
case BPF_RET | BPF_K:
* If this is not the last instruction
* then jump to the epilogue
*/
- emit_b(b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_b(b_off, ctx);
emit_nop(ctx);
}
break;
/* Load *dev pointer */
emit_load_ptr(r_s0, r_skb, off, ctx);
/* error (0) in the delay slot */
- emit_bcond(MIPS_COND_EQ, r_s0, r_zero,
- b_imm(prog->len, ctx), ctx);
+ b_off = b_imm(prog->len, ctx);
+ if (is_bad_offset(b_off))
+ return -E2BIG;
+ emit_bcond(MIPS_COND_EQ, r_s0, r_zero, b_off, ctx);
emit_reg_move(r_ret, r_zero, ctx);
if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4);
/* Generate the actual JIT code */
build_prologue(&ctx);
- build_body(&ctx);
+ if (build_body(&ctx)) {
+ module_memfree(ctx.target);
+ goto out;
+ }
build_epilogue(&ctx);
/* Update the icache */
config EARLY_PRINTK
bool "Activate early kernel debugging"
default y
+ depends on TTY
select SERIAL_CORE_CONSOLE
help
- Enable early printk on console
+ Enable early printk on console.
This is useful for kernel debugging when your machine crashes very
early before the console code is initialized.
You should normally say N here, unless you want to debug such a crash.
void __init setup_arch(char **cmdline_p)
{
- int dram_start;
-
console_verbose();
memory_start = memblock_start_of_DRAM();
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
- set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+ set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
- clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+ clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
kvm_s390_patch_guest_per_regs(vcpu);
}
- clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask);
+ clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
vcpu->arch.sie_block->icptcode = 0;
cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
{
- return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+ return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
* %rdx: src (1..8 blocks)
* %rcx: num blocks (1..8)
*/
- FRAME_BEGIN
-
cmpq $5, %rcx;
jb sm4_aesni_avx_crypt4;
+
+ FRAME_BEGIN
+
vmovdqu (0 * 16)(%rdx), RA0;
vmovdqu (1 * 16)(%rdx), RA1;
vmovdqu (2 * 16)(%rdx), RA2;
struct kvm_page_track_notifier_node *node);
};
-void kvm_page_track_init(struct kvm *kvm);
+int kvm_page_track_init(struct kvm *kvm);
void kvm_page_track_cleanup(struct kvm *kvm);
void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt))
- return emulate_ud(ctxt);
+ return emulate_gp(ctxt, 0);
return X86EMUL_CONTINUE;
}
for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
stimer_init(&hv_vcpu->stimer[i], i);
- hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+ hv_vcpu->vp_index = vcpu->vcpu_idx;
return 0;
}
switch (msr) {
case HV_X64_MSR_VP_INDEX: {
struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
- int vcpu_idx = kvm_vcpu_get_idx(vcpu);
u32 new_vp_index = (u32)data;
if (!host || new_vp_index >= KVM_MAX_VCPUS)
* VP index is changing, adjust num_mismatched_vp_indexes if
* it now matches or no longer matches vcpu_idx.
*/
- if (hv_vcpu->vp_index == vcpu_idx)
+ if (hv_vcpu->vp_index == vcpu->vcpu_idx)
atomic_inc(&hv->num_mismatched_vp_indexes);
- else if (new_vp_index == vcpu_idx)
+ else if (new_vp_index == vcpu->vcpu_idx)
atomic_dec(&hv->num_mismatched_vp_indexes);
hv_vcpu->vp_index = new_vp_index;
{
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
- return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu);
+ return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx;
}
int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
unsigned index;
bool mask_before, mask_after;
union kvm_ioapic_redirect_entry *e;
- unsigned long vcpu_bitmap;
int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
switch (ioapic->ioregsel) {
case IOAPIC_REG_VERSION:
irq.shorthand = APIC_DEST_NOSHORT;
irq.dest_id = e->fields.dest_id;
irq.msi_redir_hint = false;
- bitmap_zero(&vcpu_bitmap, 16);
+ bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
- &vcpu_bitmap);
+ vcpu_bitmap);
if (old_dest_mode != e->fields.dest_mode ||
old_dest_id != e->fields.dest_id) {
/*
kvm_lapic_irq_dest_mode(
!!e->fields.dest_mode);
kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
- &vcpu_bitmap);
+ vcpu_bitmap);
}
kvm_make_scan_ioapic_request_mask(ioapic->kvm,
- &vcpu_bitmap);
+ vcpu_bitmap);
} else {
kvm_make_scan_ioapic_request(ioapic->kvm);
}
} while (!sp->unsync_children);
}
-static void mmu_sync_children(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *parent)
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *parent, bool can_yield)
{
int i;
struct kvm_mmu_page *sp;
}
if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+ if (!can_yield) {
+ kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+ return -EINTR;
+ }
+
cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
flush = false;
}
}
kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+ return 0;
}
static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}
- if (sp->unsync_children)
- kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-
__clear_sp_write_flooding_count(sp);
trace_get_page:
write_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
- mmu_sync_children(vcpu, sp);
+ mmu_sync_children(vcpu, sp, true);
kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
write_unlock(&vcpu->kvm->mmu_lock);
if (IS_VALID_PAE_ROOT(root)) {
root &= PT64_BASE_ADDR_MASK;
sp = to_shadow_page(root);
- mmu_sync_children(vcpu, sp);
+ mmu_sync_children(vcpu, sp, true);
}
}
cleanup_srcu_struct(&head->track_srcu);
}
-void kvm_page_track_init(struct kvm *kvm)
+int kvm_page_track_init(struct kvm *kvm)
{
struct kvm_page_track_notifier_head *head;
head = &kvm->arch.track_notifier_head;
- init_srcu_struct(&head->track_srcu);
INIT_HLIST_HEAD(&head->track_notifier_list);
+ return init_srcu_struct(&head->track_srcu);
}
/*
if (!is_shadow_present_pte(*it.sptep)) {
table_gfn = gw->table_gfn[it.level - 2];
access = gw->pt_access[it.level - 2];
- sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
- false, access);
+ sp = kvm_mmu_get_page(vcpu, table_gfn, addr,
+ it.level-1, false, access);
+ /*
+ * We must synchronize the pagetable before linking it
+ * because the guest doesn't need to flush tlb when
+ * the gpte is changed from non-present to present.
+ * Otherwise, the guest may use the wrong mapping.
+ *
+ * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+ * synchronized it transiently via kvm_sync_page().
+ *
+ * For higher level pagetable, we synchronize it via
+ * the slower mmu_sync_children(). If it needs to
+ * break, some progress has been made; return
+ * RET_PF_RETRY and retry on the next #PF.
+ * KVM_REQ_MMU_SYNC is not necessary but it
+ * expedites the process.
+ */
+ if (sp->unsync_children &&
+ mmu_sync_children(vcpu, sp, false))
+ return RET_PF_RETRY;
}
/*
* Using the cached information from sp->gfns is safe because:
* - The spte has a reference to the struct page, so the pfn for a given gfn
* can't change unless all sptes pointing to it are nuked first.
- *
- * Note:
- * We should flush all tlbs if spte is dropped even though guest is
- * responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
- * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
- * used by guest then tlbs are not flushed, so guest is allowed to access the
- * freed pages.
- * And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
*/
static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
return 0;
if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
- /*
- * Update spte before increasing tlbs_dirty to make
- * sure no tlb flush is lost after spte is zapped; see
- * the comments in kvm_flush_remote_tlbs().
- */
- smp_wmb();
- vcpu->kvm->tlbs_dirty++;
+ set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
continue;
}
if (gfn != sp->gfns[i]) {
drop_spte(vcpu->kvm, &sp->spt[i]);
- /*
- * The same as above where we are doing
- * prefetch_invalid_gpte().
- */
- smp_wmb();
- vcpu->kvm->tlbs_dirty++;
+ set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
continue;
}
(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
(svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
- svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext;
svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
svm->vmcb->control.int_state = svm->nested.ctl.int_state;
svm->vmcb->control.event_inj = svm->nested.ctl.event_inj;
}
int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
- struct vmcb *vmcb12)
+ struct vmcb *vmcb12, bool from_vmrun)
{
struct vcpu_svm *svm = to_svm(vcpu);
int ret;
nested_vmcb02_prepare_save(svm, vmcb12);
ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
- nested_npt_enabled(svm), true);
+ nested_npt_enabled(svm), from_vmrun);
if (ret)
return ret;
if (!npt_enabled)
vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
+ if (!from_vmrun)
+ kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
svm_set_gif(svm, true);
return 0;
svm->nested.nested_run_pending = 1;
- if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12))
+ if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
goto out_exit_err;
if (nested_svm_vmrun_msrpm(svm))
return 0;
}
-static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
+ int *error)
{
- struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_data_launch_update_vmsa vmsa;
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int ret;
+
+ /* Perform some pre-encryption checks against the VMSA */
+ ret = sev_es_sync_vmsa(svm);
+ if (ret)
+ return ret;
+
+ /*
+ * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of
+ * the VMSA memory content (i.e it will write the same memory region
+ * with the guest's key), so invalidate it first.
+ */
+ clflush_cache_range(svm->vmsa, PAGE_SIZE);
+
+ vmsa.reserved = 0;
+ vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
+ vmsa.address = __sme_pa(svm->vmsa);
+ vmsa.len = PAGE_SIZE;
+ return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+}
+
+static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
struct kvm_vcpu *vcpu;
int i, ret;
if (!sev_es_guest(kvm))
return -ENOTTY;
- vmsa.reserved = 0;
-
kvm_for_each_vcpu(i, vcpu, kvm) {
- struct vcpu_svm *svm = to_svm(vcpu);
-
- /* Perform some pre-encryption checks against the VMSA */
- ret = sev_es_sync_vmsa(svm);
+ ret = mutex_lock_killable(&vcpu->mutex);
if (ret)
return ret;
- /*
- * The LAUNCH_UPDATE_VMSA command will perform in-place
- * encryption of the VMSA memory content (i.e it will write
- * the same memory region with the guest's key), so invalidate
- * it first.
- */
- clflush_cache_range(svm->vmsa, PAGE_SIZE);
+ ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
- vmsa.handle = sev->handle;
- vmsa.address = __sme_pa(svm->vmsa);
- vmsa.len = PAGE_SIZE;
- ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa,
- &argp->error);
+ mutex_unlock(&vcpu->mutex);
if (ret)
return ret;
-
- svm->vcpu.arch.guest_state_protected = true;
}
return 0;
/* Bind ASID to this guest */
ret = sev_bind_asid(kvm, start.handle, error);
- if (ret)
+ if (ret) {
+ sev_decommission(start.handle);
goto e_free_session;
+ }
params.handle = start.handle;
if (copy_to_user((void __user *)(uintptr_t)argp->data,
/* Pin guest memory */
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
- PAGE_SIZE, &n, 0);
+ PAGE_SIZE, &n, 1);
if (IS_ERR(guest_page)) {
ret = PTR_ERR(guest_page);
goto e_free_trans;
return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
}
+static bool cmd_allowed_from_miror(u32 cmd_id)
+{
+ /*
+ * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
+ * active mirror VMs. Also allow the debugging and status commands.
+ */
+ if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA ||
+ cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT ||
+ cmd_id == KVM_SEV_DBG_ENCRYPT)
+ return true;
+
+ return false;
+}
+
int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
{
struct kvm_sev_cmd sev_cmd;
mutex_lock(&kvm->lock);
- /* enc_context_owner handles all memory enc operations */
- if (is_mirroring_enc_context(kvm)) {
+ /* Only the enc_context_owner handles some memory enc operations. */
+ if (is_mirroring_enc_context(kvm) &&
+ !cmd_allowed_from_miror(sev_cmd.id)) {
r = -EINVAL;
goto out;
}
{
struct file *source_kvm_file;
struct kvm *source_kvm;
- struct kvm_sev_info *mirror_sev;
- unsigned int asid;
+ struct kvm_sev_info source_sev, *mirror_sev;
int ret;
source_kvm_file = fget(source_fd);
goto e_source_unlock;
}
- asid = to_kvm_svm(source_kvm)->sev_info.asid;
+ memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
+ sizeof(source_sev));
/*
* The mirror kvm holds an enc_context_owner ref so its asid can't
/* Set enc_context_owner and copy its encryption context over */
mirror_sev = &to_kvm_svm(kvm)->sev_info;
mirror_sev->enc_context_owner = source_kvm;
- mirror_sev->asid = asid;
mirror_sev->active = true;
+ mirror_sev->asid = source_sev.asid;
+ mirror_sev->fd = source_sev.fd;
+ mirror_sev->es_active = source_sev.es_active;
+ mirror_sev->handle = source_sev.handle;
+ /*
+ * Do not copy ap_jump_table. Since the mirror does not share the same
+ * KVM contexts as the original, and they may have different
+ * memory-views.
+ */
mutex_unlock(&kvm->lock);
return 0;
svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
V_IRQ_INJECTION_BITS_MASK;
+
+ svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
}
vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
if (error_code)
goto reinject;
+ /* All SVM instructions expect page aligned RAX */
+ if (svm->vmcb->save.rax & ~PAGE_MASK)
+ goto reinject;
+
/* Decode the instruction for usage later */
if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
goto reinject;
struct kvm_host_map map_save;
int ret;
- if (is_guest_mode(vcpu)) {
- /* FED8h - SVM Guest */
- put_smstate(u64, smstate, 0x7ed8, 1);
- /* FEE0h - SVM Guest VMCB Physical Address */
- put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+ if (!is_guest_mode(vcpu))
+ return 0;
- svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
- svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
- svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+ /* FED8h - SVM Guest */
+ put_smstate(u64, smstate, 0x7ed8, 1);
+ /* FEE0h - SVM Guest VMCB Physical Address */
+ put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
- ret = nested_svm_vmexit(svm);
- if (ret)
- return ret;
+ svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
- /*
- * KVM uses VMCB01 to store L1 host state while L2 runs but
- * VMCB01 is going to be used during SMM and thus the state will
- * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
- * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
- * format of the area is identical to guest save area offsetted
- * by 0x400 (matches the offset of 'struct vmcb_save_area'
- * within 'struct vmcb'). Note: HSAVE area may also be used by
- * L1 hypervisor to save additional host context (e.g. KVM does
- * that, see svm_prepare_guest_switch()) which must be
- * preserved.
- */
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
- &map_save) == -EINVAL)
- return 1;
+ ret = nested_svm_vmexit(svm);
+ if (ret)
+ return ret;
- BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+ /*
+ * KVM uses VMCB01 to store L1 host state while L2 runs but
+ * VMCB01 is going to be used during SMM and thus the state will
+ * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+ * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+ * format of the area is identical to guest save area offsetted
+ * by 0x400 (matches the offset of 'struct vmcb_save_area'
+ * within 'struct vmcb'). Note: HSAVE area may also be used by
+ * L1 hypervisor to save additional host context (e.g. KVM does
+ * that, see svm_prepare_guest_switch()) which must be
+ * preserved.
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
- svm_copy_vmrun_state(map_save.hva + 0x400,
- &svm->vmcb01.ptr->save);
+ BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
- kvm_vcpu_unmap(vcpu, &map_save, true);
- }
+ svm_copy_vmrun_state(map_save.hva + 0x400,
+ &svm->vmcb01.ptr->save);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
return 0;
}
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
- int ret = 0;
+ u64 saved_efer, vmcb12_gpa;
+ struct vmcb *vmcb12;
+ int ret;
- if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
- u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
- u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
- u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
- struct vmcb *vmcb12;
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return 0;
- if (guest) {
- if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
- return 1;
+ /* Non-zero if SMI arrived while vCPU was in guest mode. */
+ if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+ return 0;
- if (!(saved_efer & EFER_SVME))
- return 1;
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+ return 1;
- if (kvm_vcpu_map(vcpu,
- gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
- return 1;
+ saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+ if (!(saved_efer & EFER_SVME))
+ return 1;
- if (svm_allocate_nested(svm))
- return 1;
+ vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+ return 1;
- vmcb12 = map.hva;
+ ret = 1;
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+ goto unmap_map;
- nested_load_control_from_vmcb12(svm, &vmcb12->control);
+ if (svm_allocate_nested(svm))
+ goto unmap_save;
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
- kvm_vcpu_unmap(vcpu, &map, true);
+ /*
+ * Restore L1 host state from L1 HSAVE area as VMCB01 was
+ * used during SMM (see svm_enter_smm())
+ */
- /*
- * Restore L1 host state from L1 HSAVE area as VMCB01 was
- * used during SMM (see svm_enter_smm())
- */
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
- &map_save) == -EINVAL)
- return 1;
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400);
- svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
- map_save.hva + 0x400);
+ /*
+ * Enter the nested guest now
+ */
- kvm_vcpu_unmap(vcpu, &map_save, true);
- }
- }
+ vmcb12 = map.hva;
+ nested_load_control_from_vmcb12(svm, &vmcb12->control);
+ ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+unmap_save:
+ kvm_vcpu_unmap(vcpu, &map_save, true);
+unmap_map:
+ kvm_vcpu_unmap(vcpu, &map, true);
return ret;
}
return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
}
-int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12);
+int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
+ u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
void svm_leave_nested(struct vcpu_svm *svm);
void svm_free_nested(struct vcpu_svm *svm);
int svm_allocate_nested(struct vcpu_svm *svm);
switch (msr_index) {
case MSR_IA32_VMX_EXIT_CTLS:
case MSR_IA32_VMX_TRUE_EXIT_CTLS:
- ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
break;
case MSR_IA32_VMX_ENTRY_CTLS:
case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
- ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
break;
case MSR_IA32_VMX_PROCBASED_CTLS2:
- ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+ break;
+ case MSR_IA32_VMX_PINBASED_CTLS:
+ ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ break;
+ case MSR_IA32_VMX_VMFUNC:
+ ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
break;
}
* Guest state is invalid and unrestricted guest is disabled,
* which means L1 attempted VMEntry to L2 with invalid state.
* Fail the VMEntry.
+ *
+ * However when force loading the guest state (SMM exit or
+ * loading nested state after migration, it is possible to
+ * have invalid guest state now, which will be later fixed by
+ * restoring L2 register state
*/
- if (CC(!vmx_guest_state_valid(vcpu))) {
+ if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) {
*entry_failure_code = ENTRY_FAIL_DEFAULT;
return -EINVAL;
}
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+
+ to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
}
static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
return -ENOMEM;
}
-/*
- * Emulate the VMXON instruction.
- * Currently, we just remember that VMX is active, and do not save or even
- * inspect the argument to VMXON (the so-called "VMXON pointer") because we
- * do not currently need to store anything in that guest-allocated memory
- * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
- * argument is different from the VMXON pointer (which the spec says they do).
- */
+/* Emulate the VMXON instruction. */
static int handle_vmon(struct kvm_vcpu *vcpu)
{
int ret;
case EXIT_REASON_VMFUNC:
/* VM functions are emulated through L2->L0 vmexits. */
return true;
+ case EXIT_REASON_BUS_LOCK:
+ /*
+ * At present, bus lock VM exit is never exposed to L1.
+ * Handle L2's bus locks in L0 directly.
+ */
+ return true;
default:
break;
}
vmx_prepare_switch_to_host(to_vmx(vcpu));
}
-static bool emulation_required(struct kvm_vcpu *vcpu)
+bool vmx_emulation_required(struct kvm_vcpu *vcpu)
{
return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
}
vmcs_writel(GUEST_RFLAGS, rflags);
if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
- vmx->emulation_required = emulation_required(vcpu);
+ vmx->emulation_required = vmx_emulation_required(vcpu);
}
u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
&msr_info->data))
return 1;
/*
- * Enlightened VMCS v1 doesn't have certain fields, but buggy
- * Hyper-V versions are still trying to use corresponding
- * features when they are exposed. Filter out the essential
- * minimum.
+ * Enlightened VMCS v1 doesn't have certain VMCS fields but
+ * instead of just ignoring the features, different Hyper-V
+ * versions are either trying to use them and fail or do some
+ * sanity checking and refuse to boot. Filter all unsupported
+ * features out.
*/
if (!msr_info->host_initiated &&
vmx->nested.enlightened_vmcs_enabled)
}
/* depends on vcpu->arch.cr0 to be set to a new value */
- vmx->emulation_required = emulation_required(vcpu);
+ vmx->emulation_required = vmx_emulation_required(vcpu);
}
static int vmx_get_max_tdp_level(void)
{
__vmx_set_segment(vcpu, var, seg);
- to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+ to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
}
static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
vmx->loaded_vmcs->soft_vnmi_blocked))
vmx->loaded_vmcs->entry_time = ktime_get();
- /* Don't enter VMX if guest state is invalid, let the exit handler
- start emulation until we arrive back to a valid state */
- if (vmx->emulation_required)
+ /*
+ * Don't enter VMX if guest state is invalid, let the exit handler
+ * start emulation until we arrive back to a valid state. Synthesize a
+ * consistency check VM-Exit due to invalid guest state and bail.
+ */
+ if (unlikely(vmx->emulation_required)) {
+
+ /* We don't emulate invalid state of a nested guest */
+ vmx->fail = is_guest_mode(vcpu);
+
+ vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
+ vmx->exit_reason.failed_vmentry = 1;
+ kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
+ vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+ kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
+ vmx->exit_intr_info = 0;
return EXIT_FASTPATH_NONE;
+ }
trace_kvm_entry(vcpu);
* only loaded into hardware when necessary, e.g. SYSCALL #UDs outside
* of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to
* be loaded into hardware if those conditions aren't met.
- * nr_active_uret_msrs tracks the number of MSRs that need to be loaded
- * into hardware when running the guest. guest_uret_msrs[] is resorted
- * whenever the number of "active" uret MSRs is modified.
*/
struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
- int nr_active_uret_msrs;
bool guest_uret_msrs_loaded;
#ifdef CONFIG_X86_64
u64 msr_host_kernel_gs_base;
void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
unsigned long fs_base, unsigned long gs_base);
int vmx_get_cpl(struct kvm_vcpu *vcpu);
+bool vmx_emulation_required(struct kvm_vcpu *vcpu);
unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
+
+ MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
+ MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
+ MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
+ MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
+ MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
};
static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
offsetof(struct compat_vcpu_info, time));
if (vcpu->xen.vcpu_time_info_set)
kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
- if (v == kvm_get_vcpu(v->kvm, 0))
+ if (!v->vcpu_idx)
kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
return 0;
}
/* Process a latched INIT or SMI, if any. */
kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+ /*
+ * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+ * on SMM exit we still need to reload them from
+ * guest memory
+ */
+ vcpu->arch.pdptrs_from_userspace = false;
}
kvm_mmu_reset_context(vcpu);
int r;
vcpu->arch.last_vmentry_cpu = -1;
+ vcpu->arch.regs_avail = ~0;
+ vcpu->arch.regs_dirty = ~0;
if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
+ vcpu->arch.cr3 = 0;
+ kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
+
/*
* CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions
* of Intel's SDM list CD/NW as being set on INIT, but they contradict
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
+ int ret;
+
if (type)
return -EINVAL;
+ ret = kvm_page_track_init(kvm);
+ if (ret)
+ return ret;
+
INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
kvm_apicv_init(kvm);
kvm_hv_init_vm(kvm);
- kvm_page_track_init(kvm);
kvm_mmu_init_vm(kvm);
kvm_xen_init_vm(kvm);
if (insn->imm == (BPF_AND | BPF_FETCH) ||
insn->imm == (BPF_OR | BPF_FETCH) ||
insn->imm == (BPF_XOR | BPF_FETCH)) {
- u8 *branch_target;
bool is64 = BPF_SIZE(insn->code) == BPF_DW;
u32 real_src_reg = src_reg;
+ u32 real_dst_reg = dst_reg;
+ u8 *branch_target;
/*
* Can't be implemented with a single x86 insn.
emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
if (src_reg == BPF_REG_0)
real_src_reg = BPF_REG_AX;
+ if (dst_reg == BPF_REG_0)
+ real_dst_reg = BPF_REG_AX;
branch_target = prog;
/* Load old value */
emit_ldx(&prog, BPF_SIZE(insn->code),
- BPF_REG_0, dst_reg, insn->off);
+ BPF_REG_0, real_dst_reg, insn->off);
/*
* Perform the (commutative) operation locally,
* put the result in the AUX_REG.
add_2reg(0xC0, AUX_REG, real_src_reg));
/* Attempt to swap in new value */
err = emit_atomic(&prog, BPF_CMPXCHG,
- dst_reg, AUX_REG, insn->off,
+ real_dst_reg, AUX_REG,
+ insn->off,
BPF_SIZE(insn->code));
if (WARN_ON(err))
return err;
/* Restore R0 after clobbering RAX */
emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
break;
-
}
err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
- insn->off, BPF_SIZE(insn->code));
+ insn->off, BPF_SIZE(insn->code));
if (err)
return err;
break;
}
static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
- struct bpf_prog *p, int stack_size, bool mod_ret)
+ struct bpf_prog *p, int stack_size, bool save_ret)
{
u8 *prog = *pprog;
u8 *jmp_insn;
if (emit_call(&prog, p->bpf_func, prog))
return -EINVAL;
- /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
+ /*
+ * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
* of the previous call which is then passed on the stack to
* the next BPF program.
+ *
+ * BPF_TRAMP_FENTRY trampoline may need to return the return
+ * value of BPF_PROG_TYPE_STRUCT_OPS prog.
*/
- if (mod_ret)
+ if (save_ret)
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
/* replace 2 nops with JE insn, since jmp target is known */
}
static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
- struct bpf_tramp_progs *tp, int stack_size)
+ struct bpf_tramp_progs *tp, int stack_size,
+ bool save_ret)
{
int i;
u8 *prog = *pprog;
for (i = 0; i < tp->nr_progs; i++) {
- if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false))
+ if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size,
+ save_ret))
return -EINVAL;
}
*pprog = prog;
return 0;
}
+static bool is_valid_bpf_tramp_flags(unsigned int flags)
+{
+ if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+ (flags & BPF_TRAMP_F_SKIP_FRAME))
+ return false;
+
+ /*
+ * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
+ * and it must be used alone.
+ */
+ if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) &&
+ (flags & ~BPF_TRAMP_F_RET_FENTRY_RET))
+ return false;
+
+ return true;
+}
+
/* Example:
* __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
* its 'struct btf_func_model' will be nr_args=2
struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
u8 **branches = NULL;
u8 *prog;
+ bool save_ret;
/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
if (nr_args > 6)
return -ENOTSUPP;
- if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
- (flags & BPF_TRAMP_F_SKIP_FRAME))
+ if (!is_valid_bpf_tramp_flags(flags))
return -EINVAL;
- if (flags & BPF_TRAMP_F_CALL_ORIG)
- stack_size += 8; /* room for return value of orig_call */
+ /* room for return value of orig_call or fentry prog */
+ save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
+ if (save_ret)
+ stack_size += 8;
if (flags & BPF_TRAMP_F_IP_ARG)
stack_size += 8; /* room for IP address argument */
}
if (fentry->nr_progs)
- if (invoke_bpf(m, &prog, fentry, stack_size))
+ if (invoke_bpf(m, &prog, fentry, stack_size,
+ flags & BPF_TRAMP_F_RET_FENTRY_RET))
return -EINVAL;
if (fmod_ret->nr_progs) {
}
if (fexit->nr_progs)
- if (invoke_bpf(m, &prog, fexit, stack_size)) {
+ if (invoke_bpf(m, &prog, fexit, stack_size, false)) {
ret = -EINVAL;
goto cleanup;
}
ret = -EINVAL;
goto cleanup;
}
- /* restore original return value back into RAX */
- emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
}
+ /* restore return value of orig_call or fentry prog back into RAX */
+ if (save_ret)
+ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
EMIT1(0x5B); /* pop rbx */
EMIT1(0xC9); /* leave */
in_place ? DMA_BIDIRECTIONAL
: DMA_TO_DEVICE);
if (ret)
- goto e_ctx;
+ goto e_aad;
if (in_place) {
dst = src;
op.u.aes.size = 0;
ret = cmd_q->ccp->vdata->perform->aes(&op);
if (ret)
- goto e_dst;
+ goto e_final_wa;
if (aes->action == CCP_AES_ACTION_ENCRYPT) {
/* Put the ciphered tag after the ciphertext. */
ret = ccp_init_dm_workarea(&tag, cmd_q, authsize,
DMA_BIDIRECTIONAL);
if (ret)
- goto e_tag;
+ goto e_final_wa;
ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize);
- if (ret)
- goto e_tag;
+ if (ret) {
+ ccp_dm_free(&tag);
+ goto e_final_wa;
+ }
ret = crypto_memneq(tag.address, final_wa.address,
authsize) ? -EBADMSG : 0;
ccp_dm_free(&tag);
}
-e_tag:
+e_final_wa:
ccp_dm_free(&final_wa);
e_dst:
mutex_lock(&chip->i2c_lock);
ret = regmap_read(chip->regmap, inreg, ®_val);
mutex_unlock(&chip->i2c_lock);
- if (ret < 0) {
- /*
- * NOTE:
- * diagnostic already emitted; that's all we should
- * do unless gpio_*_value_cansleep() calls become different
- * from their nonsleeping siblings (and report faults).
- */
- return 0;
- }
+ if (ret < 0)
+ return ret;
return !!(reg_val & bit);
}
struct device_node *pctlnp = of_get_parent(np);
struct pinctrl_dev *pctldev = NULL;
struct rockchip_pin_bank *bank = NULL;
+ struct rockchip_pin_output_deferred *cfg;
static int gpio;
int id, ret;
if (ret)
return ret;
+ /*
+ * Prevent clashes with a deferred output setting
+ * being added right at this moment.
+ */
+ mutex_lock(&bank->deferred_lock);
+
ret = rockchip_gpiolib_register(bank);
if (ret) {
clk_disable_unprepare(bank->clk);
+ mutex_unlock(&bank->deferred_lock);
return ret;
}
+ while (!list_empty(&bank->deferred_output)) {
+ cfg = list_first_entry(&bank->deferred_output,
+ struct rockchip_pin_output_deferred, head);
+ list_del(&cfg->head);
+
+ ret = rockchip_gpio_direction_output(&bank->gpio_chip, cfg->pin, cfg->arg);
+ if (ret)
+ dev_warn(dev, "setting output pin %u to %u failed\n", cfg->pin, cfg->arg);
+
+ kfree(cfg);
+ }
+
+ mutex_unlock(&bank->deferred_lock);
+
platform_set_drvdata(pdev, bank);
dev_info(dev, "probed %pOF\n", np);
if (!privdata->cl_data)
return -ENOMEM;
- rc = devm_add_action_or_reset(&pdev->dev, amd_mp2_pci_remove, privdata);
+ mp2_select_ops(privdata);
+
+ rc = amd_sfh_hid_client_init(privdata);
if (rc)
return rc;
- mp2_select_ops(privdata);
-
- return amd_sfh_hid_client_init(privdata);
+ return devm_add_action_or_reset(&pdev->dev, amd_mp2_pci_remove, privdata);
}
static int __maybe_unused amd_mp2_pci_resume(struct device *dev)
/*
* MacBook JIS keyboard has wrong logical maximum
+ * Magic Keyboard JIS has wrong logical maximum
*/
static __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
struct apple_sc *asc = hid_get_drvdata(hdev);
+ if(*rsize >=71 && rdesc[70] == 0x65 && rdesc[64] == 0x65) {
+ hid_info(hdev,
+ "fixing up Magic Keyboard JIS report descriptor\n");
+ rdesc[64] = rdesc[70] = 0xe7;
+ }
+
if ((asc->quirks & APPLE_RDESC_JIS) && *rsize >= 60 &&
rdesc[53] == 0x65 && rdesc[59] == 0x65) {
hid_info(hdev,
{
struct betopff_device *betopff;
struct hid_report *report;
- struct hid_input *hidinput =
- list_first_entry(&hid->inputs, struct hid_input, list);
+ struct hid_input *hidinput;
struct list_head *report_list =
&hid->report_enum[HID_OUTPUT_REPORT].report_list;
- struct input_dev *dev = hidinput->input;
+ struct input_dev *dev;
int field_count = 0;
int error;
int i, j;
+ if (list_empty(&hid->inputs)) {
+ hid_err(hid, "no inputs found\n");
+ return -ENODEV;
+ }
+
+ hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+ dev = hidinput->input;
+
if (list_empty(report_list)) {
hid_err(hid, "no output reports found\n");
return -ENODEV;
}
ret = u2fzero_recv(dev, &req, &resp);
- if (ret < 0)
+
+ /* ignore errors or packets without data */
+ if (ret < offsetof(struct u2f_hid_msg, init.data))
return 0;
/* only take the minimum amount of data it is safe to take */
{ "Wacom Intuos Pro S", 31920, 19950, 8191, 63,
INTUOSP2S_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 7,
.touch_max = 10 };
+static const struct wacom_features wacom_features_0x3c6 =
+ { "Wacom Intuos BT S", 15200, 9500, 4095, 63,
+ INTUOSHT3_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 };
+static const struct wacom_features wacom_features_0x3c8 =
+ { "Wacom Intuos BT M", 21600, 13500, 4095, 63,
+ INTUOSHT3_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 };
static const struct wacom_features wacom_features_HID_ANY_ID =
{ "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID };
{ USB_DEVICE_WACOM(0x37A) },
{ USB_DEVICE_WACOM(0x37B) },
{ BT_DEVICE_WACOM(0x393) },
+ { BT_DEVICE_WACOM(0x3c6) },
+ { BT_DEVICE_WACOM(0x3c8) },
{ USB_DEVICE_WACOM(0x4001) },
{ USB_DEVICE_WACOM(0x4004) },
{ USB_DEVICE_WACOM(0x5000) },
}
}
-static void cma_cancel_listens(struct rdma_id_private *id_priv)
+static void _cma_cancel_listens(struct rdma_id_private *id_priv)
{
struct rdma_id_private *dev_id_priv;
+ lockdep_assert_held(&lock);
+
/*
* Remove from listen_any_list to prevent added devices from spawning
* additional listen requests.
*/
- mutex_lock(&lock);
list_del(&id_priv->list);
while (!list_empty(&id_priv->listen_list)) {
rdma_destroy_id(&dev_id_priv->id);
mutex_lock(&lock);
}
+}
+
+static void cma_cancel_listens(struct rdma_id_private *id_priv)
+{
+ mutex_lock(&lock);
+ _cma_cancel_listens(id_priv);
mutex_unlock(&lock);
}
{
switch (state) {
case RDMA_CM_ADDR_QUERY:
+ /*
+ * We can avoid doing the rdma_addr_cancel() based on state,
+ * only RDMA_CM_ADDR_QUERY has a work that could still execute.
+ * Notice that the addr_handler work could still be exiting
+ * outside this state, however due to the interaction with the
+ * handler_mutex the work is guaranteed not to touch id_priv
+ * during exit.
+ */
rdma_addr_cancel(&id_priv->id.route.addr.dev_addr);
break;
case RDMA_CM_ROUTE_QUERY:
static void destroy_mc(struct rdma_id_private *id_priv,
struct cma_multicast *mc)
{
+ bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN);
+
if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num))
ib_sa_free_multicast(mc->sa_mc);
cma_set_mgid(id_priv, (struct sockaddr *)&mc->addr,
&mgid);
- cma_igmp_send(ndev, &mgid, false);
+
+ if (!send_only)
+ cma_igmp_send(ndev, &mgid, false);
+
dev_put(ndev);
}
return 0;
err_listen:
- list_del(&id_priv->list);
+ _cma_cancel_listens(id_priv);
mutex_unlock(&lock);
if (to_destroy)
rdma_destroy_id(&to_destroy->id);
if (dst_addr->sa_family == AF_IB) {
ret = cma_resolve_ib_addr(id_priv);
} else {
+ /*
+ * The FSM can return back to RDMA_CM_ADDR_BOUND after
+ * rdma_resolve_ip() is called, eg through the error
+ * path in addr_handler(). If this happens the existing
+ * request must be canceled before issuing a new one.
+ * Since canceling a request is a bit slow and this
+ * oddball path is rare, keep track once a request has
+ * been issued. The track turns out to be a permanent
+ * state since this is the only cancel as it is
+ * immediately before rdma_resolve_ip().
+ */
+ if (id_priv->used_resolve_ip)
+ rdma_addr_cancel(&id->route.addr.dev_addr);
+ else
+ id_priv->used_resolve_ip = 1;
ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr,
&id->route.addr.dev_addr,
timeout_ms, addr_handler,
int ret;
if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) {
+ struct sockaddr_in any_in = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
+ };
+
/* For a well behaved ULP state will be RDMA_CM_IDLE */
- id->route.addr.src_addr.ss_family = AF_INET;
- ret = rdma_bind_addr(id, cma_src_addr(id_priv));
+ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in);
if (ret)
return ret;
if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND,
u8 afonly;
u8 timeout;
u8 min_rnr_timer;
+ u8 used_resolve_ip;
enum ib_gid_type gid_type;
/*
struct hfi1_ipoib_txq *txq = &priv->txqs[q];
u64 completed = atomic64_read(&txq->complete_txreqs);
- dd_dev_info(priv->dd, "timeout txq %llx q %u stopped %u stops %d no_desc %d ring_full %d\n",
- (unsigned long long)txq, q,
+ dd_dev_info(priv->dd, "timeout txq %p q %u stopped %u stops %d no_desc %d ring_full %d\n",
+ txq, q,
__netif_subqueue_stopped(dev, txq->q_idx),
atomic_read(&txq->stops),
atomic_read(&txq->no_desc),
atomic_read(&txq->ring_full));
- dd_dev_info(priv->dd, "sde %llx engine %u\n",
- (unsigned long long)txq->sde,
+ dd_dev_info(priv->dd, "sde %p engine %u\n",
+ txq->sde,
txq->sde ? txq->sde->this_idx : 0);
dd_dev_info(priv->dd, "flow %x\n", txq->flow.as_int);
dd_dev_info(priv->dd, "sent %llu completed %llu used %llu\n",
INIT_LIST_HEAD(&hr_cq->rq_list);
}
-static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
- struct hns_roce_ib_create_cq *ucmd)
+static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+ struct hns_roce_ib_create_cq *ucmd)
{
struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
- if (udata) {
- if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size))
- hr_cq->cqe_size = ucmd->cqe_size;
- else
- hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
- } else {
+ if (!udata) {
hr_cq->cqe_size = hr_dev->caps.cqe_sz;
+ return 0;
+ }
+
+ if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) {
+ if (ucmd->cqe_size != HNS_ROCE_V2_CQE_SIZE &&
+ ucmd->cqe_size != HNS_ROCE_V3_CQE_SIZE) {
+ ibdev_err(&hr_dev->ib_dev,
+ "invalid cqe size %u.\n", ucmd->cqe_size);
+ return -EINVAL;
+ }
+
+ hr_cq->cqe_size = ucmd->cqe_size;
+ } else {
+ hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
}
+
+ return 0;
}
int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
set_cq_param(hr_cq, attr->cqe, attr->comp_vector, &ucmd);
- set_cqe_size(hr_cq, udata, &ucmd);
+ ret = set_cqe_size(hr_cq, udata, &ucmd);
+ if (ret)
+ return ret;
ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
if (ret) {
dest = get_cqe_v2(hr_cq, (prod_index + nfreed) &
hr_cq->ib_cq.cqe);
owner_bit = hr_reg_read(dest, CQE_OWNER);
- memcpy(dest, cqe, sizeof(*cqe));
+ memcpy(dest, cqe, hr_cq->cqe_size);
hr_reg_write(dest, CQE_OWNER, owner_bit);
}
}
hr_qp->path_mtu = ib_mtu;
mtu = ib_mtu_enum_to_int(ib_mtu);
- if (WARN_ON(mtu < 0))
+ if (WARN_ON(mtu <= 0))
+ return -EINVAL;
+#define MAX_LP_MSG_LEN 65536
+ /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */
+ lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu);
+ if (WARN_ON(lp_pktn_ini >= 0xF))
return -EINVAL;
if (attr_mask & IB_QP_PATH_MTU) {
hr_reg_clear(qpc_mask, QPC_MTU);
}
-#define MAX_LP_MSG_LEN 65536
- /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */
- lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu);
-
hr_reg_write(context, QPC_LP_PKTN_INI, lp_pktn_ini);
hr_reg_clear(qpc_mask, QPC_LP_PKTN_INI);
original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT ||
last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE ||
last_ae == IRDMA_AE_BAD_CLOSE ||
- last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->reset)) {
+ last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) {
issue_close = 1;
iwqp->cm_id = NULL;
qp->term_flags = 0;
teardown_entry);
attr.qp_state = IB_QPS_ERR;
irdma_modify_qp(&cm_node->iwqp->ibqp, &attr, IB_QP_STATE, NULL);
- if (iwdev->reset)
+ if (iwdev->rf->reset)
irdma_cm_disconn(cm_node->iwqp);
irdma_rem_ref_cm_node(cm_node);
}
case IRDMA_AE_LLP_RECEIVED_MPA_CRC_ERROR:
qp->flush_code = FLUSH_GENERAL_ERR;
break;
+ case IRDMA_AE_LLP_TOO_MANY_RETRIES:
+ qp->flush_code = FLUSH_RETRY_EXC_ERR;
+ break;
+ case IRDMA_AE_AMP_MWBIND_INVALID_RIGHTS:
+ case IRDMA_AE_AMP_MWBIND_BIND_DISABLED:
+ case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS:
+ qp->flush_code = FLUSH_MW_BIND_ERR;
+ break;
default:
qp->flush_code = FLUSH_FATAL_ERR;
break;
irdma_puda_dele_rsrc(vsi, IRDMA_PUDA_RSRC_TYPE_IEQ, false);
if (irdma_initialize_ieq(iwdev)) {
- iwdev->reset = true;
+ iwdev->rf->reset = true;
rf->gen_ops.request_reset(rf);
}
}
case IEQ_CREATED:
if (!iwdev->roce_mode)
irdma_puda_dele_rsrc(&iwdev->vsi, IRDMA_PUDA_RSRC_TYPE_IEQ,
- iwdev->reset);
+ iwdev->rf->reset);
fallthrough;
case ILQ_CREATED:
if (!iwdev->roce_mode)
irdma_puda_dele_rsrc(&iwdev->vsi,
IRDMA_PUDA_RSRC_TYPE_ILQ,
- iwdev->reset);
+ iwdev->rf->reset);
break;
default:
ibdev_warn(&iwdev->ibdev, "bad init_state = %d\n", iwdev->init_state);
iwdev = to_iwdev(ibdev);
if (reset)
- iwdev->reset = true;
+ iwdev->rf->reset = true;
iwdev->iw_status = 0;
irdma_port_ibevent(iwdev);
bool roce_mode:1;
bool roce_dcqcn_en:1;
bool dcb:1;
- bool reset:1;
bool iw_ooo:1;
enum init_completion_state init_state;
FLUSH_REM_OP_ERR,
FLUSH_LOC_LEN_ERR,
FLUSH_FATAL_ERR,
+ FLUSH_RETRY_EXC_ERR,
+ FLUSH_MW_BIND_ERR,
};
enum irdma_cmpl_status {
struct irdma_qp *qp = sc_qp->qp_uk.back_qp;
struct ib_qp_attr attr;
- if (qp->iwdev->reset)
+ if (qp->iwdev->rf->reset)
return;
attr.qp_state = IB_QPS_ERR;
irdma_qp_rem_ref(&iwqp->ibqp);
wait_for_completion(&iwqp->free_qp);
irdma_free_lsmm_rsrc(iwqp);
- if (!iwdev->reset)
- irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp);
+ irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp);
if (!iwqp->user_mode) {
if (iwqp->iwscq) {
/* Kmode allocations */
int rsize;
- if (entries > rf->max_cqe) {
+ if (entries < 1 || entries > rf->max_cqe) {
err_code = -EINVAL;
goto cq_free_rsrc;
}
return IB_WC_LOC_LEN_ERR;
case FLUSH_GENERAL_ERR:
return IB_WC_WR_FLUSH_ERR;
+ case FLUSH_RETRY_EXC_ERR:
+ return IB_WC_RETRY_EXC_ERR;
+ case FLUSH_MW_BIND_ERR:
+ return IB_WC_MW_BIND_ERR;
case FLUSH_FATAL_ERR:
default:
return IB_WC_FATAL_ERR;
}
#define QIB_DIAGC_ATTR(N) \
- static_assert(&((struct qib_ibport *)0)->rvp.n_##N != (u64 *)NULL); \
+ static_assert(__same_type(((struct qib_ibport *)0)->rvp.n_##N, u64)); \
static struct qib_diagc_attr qib_diagc_attr_##N = { \
.attr = __ATTR(N, 0664, diagc_attr_show, diagc_attr_store), \
.counter = \
struct usnic_ib_vf {
struct usnic_ib_dev *pf;
- spinlock_t lock;
+ struct mutex lock;
struct usnic_vnic *vnic;
unsigned int qp_grp_ref_cnt;
struct usnic_ib_pd *pd;
}
vf->pf = pf;
- spin_lock_init(&vf->lock);
+ mutex_init(&vf->lock);
mutex_lock(&pf->usdev_lock);
list_add_tail(&vf->link, &pf->vf_dev_list);
/*
for (i = 0; dev_list[i]; i++) {
dev = dev_list[i];
vf = dev_get_drvdata(dev);
- spin_lock(&vf->lock);
+ mutex_lock(&vf->lock);
vnic = vf->vnic;
if (!usnic_vnic_check_room(vnic, res_spec)) {
usnic_dbg("Found used vnic %s from %s\n",
vf, pd, res_spec,
trans_spec);
- spin_unlock(&vf->lock);
+ mutex_unlock(&vf->lock);
goto qp_grp_check;
}
- spin_unlock(&vf->lock);
+ mutex_unlock(&vf->lock);
}
usnic_uiom_free_dev_list(dev_list);
/* Try to find resources on an unused vf */
list_for_each_entry(vf, &us_ibdev->vf_dev_list, link) {
- spin_lock(&vf->lock);
+ mutex_lock(&vf->lock);
vnic = vf->vnic;
if (vf->qp_grp_ref_cnt == 0 &&
usnic_vnic_check_room(vnic, res_spec) == 0) {
vf, pd, res_spec,
trans_spec);
- spin_unlock(&vf->lock);
+ mutex_unlock(&vf->lock);
goto qp_grp_check;
}
- spin_unlock(&vf->lock);
+ mutex_unlock(&vf->lock);
}
usnic_info("No free qp grp found on %s\n",
WARN_ON(qp_grp->state != IB_QPS_RESET);
- spin_lock(&vf->lock);
+ mutex_lock(&vf->lock);
usnic_ib_qp_grp_destroy(qp_grp);
- spin_unlock(&vf->lock);
+ mutex_unlock(&vf->lock);
}
static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd)
static struct platform_driver apple_dart_driver;
static const struct iommu_ops apple_dart_iommu_ops;
-static const struct iommu_flush_ops apple_dart_tlb_ops;
static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom)
{
apple_dart_domain_flush_tlb(to_dart_domain(domain));
}
-static void apple_dart_tlb_flush_all(void *cookie)
-{
- apple_dart_domain_flush_tlb(cookie);
-}
-
-static void apple_dart_tlb_flush_walk(unsigned long iova, size_t size,
- size_t granule, void *cookie)
-{
- apple_dart_domain_flush_tlb(cookie);
-}
-
-static const struct iommu_flush_ops apple_dart_tlb_ops = {
- .tlb_flush_all = apple_dart_tlb_flush_all,
- .tlb_flush_walk = apple_dart_tlb_flush_walk,
-};
-
static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain,
dma_addr_t iova)
{
.ias = 32,
.oas = 36,
.coherent_walk = 1,
- .tlb = &apple_dart_tlb_ops,
.iommu_dev = dart->dev,
};
return -EINVAL;
}
+static DEFINE_MUTEX(apple_dart_groups_lock);
+
+static void apple_dart_release_group(void *iommu_data)
+{
+ int i, sid;
+ struct apple_dart_stream_map *stream_map;
+ struct apple_dart_master_cfg *group_master_cfg = iommu_data;
+
+ mutex_lock(&apple_dart_groups_lock);
+
+ for_each_stream_map(i, group_master_cfg, stream_map)
+ for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS)
+ stream_map->dart->sid2group[sid] = NULL;
+
+ kfree(iommu_data);
+ mutex_unlock(&apple_dart_groups_lock);
+}
+
static struct iommu_group *apple_dart_device_group(struct device *dev)
{
- static DEFINE_MUTEX(lock);
int i, sid;
struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
struct apple_dart_stream_map *stream_map;
+ struct apple_dart_master_cfg *group_master_cfg;
struct iommu_group *group = NULL;
struct iommu_group *res = ERR_PTR(-EINVAL);
- mutex_lock(&lock);
+ mutex_lock(&apple_dart_groups_lock);
for_each_stream_map(i, cfg, stream_map) {
for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) {
#endif
group = generic_device_group(dev);
+ res = ERR_PTR(-ENOMEM);
+ if (!group)
+ goto out;
+
+ group_master_cfg = kzalloc(sizeof(*group_master_cfg), GFP_KERNEL);
+ if (!group_master_cfg) {
+ iommu_group_put(group);
+ goto out;
+ }
+
+ memcpy(group_master_cfg, cfg, sizeof(*group_master_cfg));
+ iommu_group_set_iommudata(group, group_master_cfg,
+ apple_dart_release_group);
+
for_each_stream_map(i, cfg, stream_map)
for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS)
stream_map->dart->sid2group[sid] = group;
res = group;
out:
- mutex_unlock(&lock);
+ mutex_unlock(&apple_dart_groups_lock);
return res;
}
reason = dmar_get_fault_reason(fault_reason, &fault_type);
if (fault_type == INTR_REMAP)
- pr_err("[INTR-REMAP] Request device [0x%02x:0x%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n",
+ pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n",
source_id >> 8, PCI_SLOT(source_id & 0xFF),
PCI_FUNC(source_id & 0xFF), addr >> 48,
fault_reason, reason);
else if (pasid == INVALID_IOASID)
- pr_err("[%s NO_PASID] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+ pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
type ? "DMA Read" : "DMA Write",
source_id >> 8, PCI_SLOT(source_id & 0xFF),
PCI_FUNC(source_id & 0xFF), addr,
fault_reason, reason);
else
- pr_err("[%s PASID 0x%x] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+ pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
type ? "DMA Read" : "DMA Write", pasid,
source_id >> 8, PCI_SLOT(source_id & 0xFF),
PCI_FUNC(source_id & 0xFF), addr,
continue;
length = 0;
switch (c) {
- /* SOF0: baseline JPEG */
- case SOF0:
+ /* JPEG_MARKER_SOF0: baseline JPEG */
+ case JPEG_MARKER_SOF0:
if (get_word_be(&jpeg_buffer, &word))
break;
length = (long)word - 2;
notfound = 0;
break;
- case DQT:
+ case JPEG_MARKER_DQT:
if (get_word_be(&jpeg_buffer, &word))
break;
length = (long)word - 2;
skip(&jpeg_buffer, length);
break;
- case DHT:
+ case JPEG_MARKER_DHT:
if (get_word_be(&jpeg_buffer, &word))
break;
length = (long)word - 2;
skip(&jpeg_buffer, length);
break;
- case SOS:
+ case JPEG_MARKER_SOS:
sos = jpeg_buffer.curr - 2; /* 0xffda */
break;
/* skip payload-less markers */
- case RST ... RST + 7:
- case SOI:
- case EOI:
- case TEM:
+ case JPEG_MARKER_RST ... JPEG_MARKER_RST + 7:
+ case JPEG_MARKER_SOI:
+ case JPEG_MARKER_EOI:
+ case JPEG_MARKER_TEM:
break;
/* skip uninteresting payload markers */
#define EXYNOS3250_IRQ_TIMEOUT 0x10000000
/* a selection of JPEG markers */
-#define TEM 0x01
-#define SOF0 0xc0
-#define DHT 0xc4
-#define RST 0xd0
-#define SOI 0xd8
-#define EOI 0xd9
-#define SOS 0xda
-#define DQT 0xdb
-#define DHP 0xde
+#define JPEG_MARKER_TEM 0x01
+#define JPEG_MARKER_SOF0 0xc0
+#define JPEG_MARKER_DHT 0xc4
+#define JPEG_MARKER_RST 0xd0
+#define JPEG_MARKER_SOI 0xd8
+#define JPEG_MARKER_EOI 0xd9
+#define JPEG_MARKER_SOS 0xda
+#define JPEG_MARKER_DQT 0xdb
+#define JPEG_MARKER_DHP 0xde
/* Flags that indicate a format can be used for capture/output */
#define SJPEG_FMT_FLAG_ENC_CAPTURE (1 << 0)
* @fmt: driver-specific format of this queue
* @w: image width
* @h: image height
- * @sos: SOS marker's position relative to the buffer beginning
- * @dht: DHT markers' positions relative to the buffer beginning
- * @dqt: DQT markers' positions relative to the buffer beginning
- * @sof: SOF0 marker's position relative to the buffer beginning
- * @sof_len: SOF0 marker's payload length (without length field itself)
+ * @sos: JPEG_MARKER_SOS's position relative to the buffer beginning
+ * @dht: JPEG_MARKER_DHT' positions relative to the buffer beginning
+ * @dqt: JPEG_MARKER_DQT' positions relative to the buffer beginning
+ * @sof: JPEG_MARKER_SOF0's position relative to the buffer beginning
+ * @sof_len: JPEG_MARKER_SOF0's payload length (without length field itself)
* @size: image buffer size in bytes
*/
struct s5p_jpeg_q_data {
// End transmit and repeat reset command so we exit sump mode
static const u8 COMMAND_RESET[] = { 0xff, 0xff, 0, 0, 0, 0, 0 };
static const u8 COMMAND_SMODE_ENTER[] = { 's' };
+static const u8 COMMAND_SMODE_EXIT[] = { 0 };
static const u8 COMMAND_TXSTART[] = { 0x26, 0x24, 0x25, 0x03 };
#define REPLY_XMITCOUNT 't'
buf[i] = cpu_to_be16(v);
}
- buf[count] = cpu_to_be16(0xffff);
+ buf[count] = 0xffff;
irtoy->tx_buf = buf;
irtoy->tx_len = size;
irtoy->emitted = 0;
+ // There is an issue where if the unit is receiving IR while the
+ // first TXSTART command is sent, the device might end up hanging
+ // with its led on. It does not respond to any command when this
+ // happens. To work around this, re-enter sample mode.
+ err = irtoy_command(irtoy, COMMAND_SMODE_EXIT,
+ sizeof(COMMAND_SMODE_EXIT), STATE_RESET);
+ if (err) {
+ dev_err(irtoy->dev, "exit sample mode: %d\n", err);
+ return err;
+ }
+
+ err = irtoy_command(irtoy, COMMAND_SMODE_ENTER,
+ sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND);
+ if (err) {
+ dev_err(irtoy->dev, "enter sample mode: %d\n", err);
+ return err;
+ }
+
err = irtoy_command(irtoy, COMMAND_TXSTART, sizeof(COMMAND_TXSTART),
STATE_TX);
kfree(buf);
spin_lock_irqsave(&host->irq_lock, flags);
- if (!host->data_status)
+ /*
+ * Only inject an error if we haven't already got an error or data over
+ * interrupt.
+ */
+ if (!host->data_status) {
host->data_status = SDMMC_INT_DCRC;
- set_bit(EVENT_DATA_ERROR, &host->pending_events);
- tasklet_schedule(&host->tasklet);
+ set_bit(EVENT_DATA_ERROR, &host->pending_events);
+ tasklet_schedule(&host->tasklet);
+ }
spin_unlock_irqrestore(&host->irq_lock, flags);
}
if (pending & DW_MCI_DATA_ERROR_FLAGS) {
+ spin_lock(&host->irq_lock);
+
/* if there is an error report DATA_ERROR */
mci_writel(host, RINTSTS, DW_MCI_DATA_ERROR_FLAGS);
host->data_status = pending;
smp_wmb(); /* drain writebuffer */
set_bit(EVENT_DATA_ERROR, &host->pending_events);
tasklet_schedule(&host->tasklet);
+
+ spin_unlock(&host->irq_lock);
}
if (pending & SDMMC_INT_DATA_OVER) {
/* Unknown why but without polling reset status, it will hang */
read_poll_timeout(reset_control_status, ret, ret == 0, 1, 100,
false, priv->rstc);
+ /* At least SDHI_VER_GEN2_SDR50 needs manual release of reset */
+ sd_ctrl_write16(host, CTL_RESET_SD, 0x0001);
priv->needs_adjust_hs400 = false;
renesas_sdhi_set_clock(host, host->clk_cache);
} else if (priv->scc_ctl) {
if (err)
return err;
- /* Port Control 2: don't force a good FCS, set the maximum frame size to
- * 10240 bytes, disable 802.1q tags checking, don't discard tagged or
+ /* Port Control 2: don't force a good FCS, set the MTU size to
+ * 10222 bytes, disable 802.1q tags checking, don't discard tagged or
* untagged frames on this port, do a destination address lookup on all
* received packets as usual, disable ARP mirroring and don't send a
* copy of all transmitted/received frames on this port to the CPU.
return err;
if (chip->info->ops->port_set_jumbo_size) {
- err = chip->info->ops->port_set_jumbo_size(chip, port, 10240);
+ err = chip->info->ops->port_set_jumbo_size(chip, port, 10218);
if (err)
return err;
}
struct mv88e6xxx_chip *chip = ds->priv;
if (chip->info->ops->port_set_jumbo_size)
- return 10240;
+ return 10240 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN;
else if (chip->info->ops->set_max_frame_size)
- return 1632;
- return 1522;
+ return 1632 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN;
+ return 1522 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN;
}
static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
struct mv88e6xxx_chip *chip = ds->priv;
int ret = 0;
+ if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+ new_mtu += EDSA_HLEN;
+
mv88e6xxx_reg_lock(chip);
if (chip->info->ops->port_set_jumbo_size)
ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu);
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.port_set_ether_type = mv88e6351_port_set_ether_type,
- .port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_limit = mv88e6097_port_pause_limit,
.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
.avb_ops = &mv88e6165_avb_ops,
.ptp_ops = &mv88e6165_ptp_ops,
.phylink_validate = mv88e6185_phylink_validate,
+ .set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
static const struct mv88e6xxx_ops mv88e6165_ops = {
#include <linux/timecounter.h>
#include <net/dsa.h>
+#define EDSA_HLEN 8
#define MV88E6XXX_N_FID 4096
/* PVT limits for 4-bit port and 5-bit switch */
u16 val;
int err;
+ mtu += ETH_HLEN + ETH_FCS_LEN;
+
err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &val);
if (err)
return err;
u16 reg;
int err;
+ size += VLAN_ETH_HLEN + ETH_FCS_LEN;
+
err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_CTL2, ®);
if (err)
return err;
bgmac->dma_dev = &pdev->dev;
ret = of_get_mac_address(np, bgmac->net_dev->dev_addr);
+ if (ret == -EPROBE_DEFER)
+ return ret;
+
if (ret)
dev_warn(&pdev->dev,
"MAC address not present in device tree\n");
if (phy_interface_mode_is_rgmii(phy_mode)) {
val = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
- val &= ~ENETC_PM0_IFM_EN_AUTO;
- val &= ENETC_PM0_IFM_IFMODE_MASK;
+ val &= ~(ENETC_PM0_IFM_EN_AUTO | ENETC_PM0_IFM_IFMODE_MASK);
val |= ENETC_PM0_IFM_IFMODE_GMII | ENETC_PM0_IFM_RG;
enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
}
u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */
u16 tqp_count[HNAE3_MAX_TC];
u16 tqp_offset[HNAE3_MAX_TC];
- unsigned long tc_en; /* bitmap of TC enabled */
u8 num_tc; /* Total number of enabled TCs */
bool mqprio_active;
};
return ret;
}
- for (i = 0; i < HNAE3_MAX_TC; i++) {
- if (!test_bit(i, &tc_info->tc_en))
- continue;
-
+ for (i = 0; i < tc_info->num_tc; i++)
netdev_set_tc_queue(netdev, i, tc_info->tqp_count[i],
tc_info->tqp_offset[i]);
- }
}
ret = netif_set_real_num_tx_queues(netdev, queue_size);
if (hns3_nic_resetting(netdev))
return -EBUSY;
+ if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) {
+ netdev_warn(netdev, "net open repeatedly!\n");
+ return 0;
+ }
+
netif_carrier_off(netdev);
ret = hns3_nic_set_real_num_queue(netdev);
struct hnae3_tc_info *tc_info = &kinfo->tc_info;
int i;
- for (i = 0; i < HNAE3_MAX_TC; i++) {
+ for (i = 0; i < tc_info->num_tc; i++) {
int j;
- if (!test_bit(i, &tc_info->tc_en))
- continue;
-
for (j = 0; j < tc_info->tqp_count[i]; j++) {
struct hnae3_queue *q;
#if IS_ENABLED(CONFIG_VLAN_8021Q)
/* Disable the vlan filter for selftest does not support it */
- if (h->ae_algo->ops->enable_vlan_filter)
+ if (h->ae_algo->ops->enable_vlan_filter &&
+ ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
h->ae_algo->ops->enable_vlan_filter(h, false);
#endif
h->ae_algo->ops->halt_autoneg(h, false);
#if IS_ENABLED(CONFIG_VLAN_8021Q)
- if (h->ae_algo->ops->enable_vlan_filter)
+ if (h->ae_algo->ops->enable_vlan_filter &&
+ ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
h->ae_algo->ops->enable_vlan_filter(h, true);
#endif
return ret;
}
-static int hclge_firmware_compat_config(struct hclge_dev *hdev)
+static int hclge_firmware_compat_config(struct hclge_dev *hdev, bool en)
{
struct hclge_firmware_compat_cmd *req;
struct hclge_desc desc;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_COMPAT_CFG, false);
- req = (struct hclge_firmware_compat_cmd *)desc.data;
+ if (en) {
+ req = (struct hclge_firmware_compat_cmd *)desc.data;
- hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1);
- hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1);
- if (hnae3_dev_phy_imp_supported(hdev))
- hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1);
- req->compat = cpu_to_le32(compat);
+ hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1);
+ hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1);
+ if (hnae3_dev_phy_imp_supported(hdev))
+ hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1);
+
+ req->compat = cpu_to_le32(compat);
+ }
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
/* ask the firmware to enable some features, driver can work without
* it.
*/
- ret = hclge_firmware_compat_config(hdev);
+ ret = hclge_firmware_compat_config(hdev, true);
if (ret)
dev_warn(&hdev->pdev->dev,
"Firmware compatible features not enabled(%d).\n",
void hclge_cmd_uninit(struct hclge_dev *hdev)
{
+ hclge_firmware_compat_config(hdev, false);
+
set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
/* wait to ensure that the firmware completes the possible left
* over commands.
}
hclge_tm_schd_info_update(hdev, num_tc);
+ if (num_tc > 1)
+ hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
+ else
+ hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
ret = hclge_ieee_ets_to_tm_info(hdev, ets);
if (ret)
u8 i, j, pfc_map, *prio_tc;
int ret;
- if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
- hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+ if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
return -EINVAL;
if (pfc->pfc_en == hdev->tm_info.pfc_en)
static void hclge_sync_mqprio_qopt(struct hnae3_tc_info *tc_info,
struct tc_mqprio_qopt_offload *mqprio_qopt)
{
- int i;
-
memset(tc_info, 0, sizeof(*tc_info));
tc_info->num_tc = mqprio_qopt->qopt.num_tc;
memcpy(tc_info->prio_tc, mqprio_qopt->qopt.prio_tc_map,
sizeof_field(struct hnae3_tc_info, tqp_count));
memcpy(tc_info->tqp_offset, mqprio_qopt->qopt.offset,
sizeof_field(struct hnae3_tc_info, tqp_offset));
-
- for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
- set_bit(tc_info->prio_tc[i], &tc_info->tc_en);
}
static int hclge_config_tc(struct hclge_dev *hdev,
return hclge_notify_init_up(hdev);
err_out:
- /* roll-back */
- memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info));
- if (hclge_config_tc(hdev, &kinfo->tc_info))
- dev_err(&hdev->pdev->dev,
- "failed to roll back tc configuration\n");
-
+ if (!tc) {
+ dev_warn(&hdev->pdev->dev,
+ "failed to destroy mqprio, will active after reset, ret = %d\n",
+ ret);
+ } else {
+ /* roll-back */
+ memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info));
+ if (hclge_config_tc(hdev, &kinfo->tc_info))
+ dev_err(&hdev->pdev->dev,
+ "failed to roll back tc configuration\n");
+ }
hclge_notify_init_up(hdev);
return ret;
sprintf(result[(*index)++], "%6u", para->rate);
}
-static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len)
+static int __hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *data_str,
+ char *buf, int len)
{
- char data_str[ARRAY_SIZE(tm_pg_items)][HCLGE_DBG_DATA_STR_LEN];
struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str;
u8 pg_id, sch_mode, weight, pri_bit_map, i, j;
int pos = 0;
int ret;
- for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++)
- result[i] = &data_str[i][0];
+ for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) {
+ result[i] = data_str;
+ data_str += HCLGE_DBG_DATA_STR_LEN;
+ }
hclge_dbg_fill_content(content, sizeof(content), tm_pg_items,
NULL, ARRAY_SIZE(tm_pg_items));
return 0;
}
+static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len)
+{
+ char *data_str;
+ int ret;
+
+ data_str = kcalloc(ARRAY_SIZE(tm_pg_items),
+ HCLGE_DBG_DATA_STR_LEN, GFP_KERNEL);
+
+ if (!data_str)
+ return -ENOMEM;
+
+ ret = __hclge_dbg_dump_tm_pg(hdev, data_str, buf, len);
+
+ kfree(data_str);
+
+ return ret;
+}
+
static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev, char *buf, int len)
{
struct hclge_tm_shaper_para shaper_para;
}
/* check if we just hit the duplicate */
- if (!ret) {
- dev_warn(&hdev->pdev->dev, "VF %u mac(%pM) exists\n",
- vport->vport_id, addr);
- return 0;
- }
-
- dev_err(&hdev->pdev->dev,
- "PF failed to add unicast entry(%pM) in the MAC table\n",
- addr);
+ if (!ret)
+ return -EEXIST;
return ret;
}
} else {
set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
&vport->state);
- break;
+
+ /* If one unicast mac address is existing in hardware,
+ * we need to try whether other unicast mac addresses
+ * are new addresses that can be added.
+ */
+ if (ret != -EEXIST)
+ break;
}
}
}
continue;
if (vport->vf_info.trusted) {
- uc_en = vport->vf_info.request_uc_en > 0;
- mc_en = vport->vf_info.request_mc_en > 0;
+ uc_en = vport->vf_info.request_uc_en > 0 ||
+ vport->overflow_promisc_flags &
+ HNAE3_OVERFLOW_UPE;
+ mc_en = vport->vf_info.request_mc_en > 0 ||
+ vport->overflow_promisc_flags &
+ HNAE3_OVERFLOW_MPE;
}
bc_en = vport->vf_info.request_bc_en > 0;
for (i = 0; i < HNAE3_MAX_TC; i++) {
if (hdev->hw_tc_map & BIT(i) && i < kinfo->tc_info.num_tc) {
- set_bit(i, &kinfo->tc_info.tc_en);
kinfo->tc_info.tqp_offset[i] = i * kinfo->rss_size;
kinfo->tc_info.tqp_count[i] = kinfo->rss_size;
} else {
/* Set to default queue if TC is disable */
- clear_bit(i, &kinfo->tc_info.tc_en);
kinfo->tc_info.tqp_offset[i] = 0;
kinfo->tc_info.tqp_count[i] = 1;
}
for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
hdev->tm_info.prio_tc[i] =
(i >= hdev->tm_info.num_tc) ? 0 : i;
-
- /* DCB is enabled if we have more than 1 TC or pfc_en is
- * non-zero.
- */
- if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en)
- hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
- else
- hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
}
static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
static void hclge_update_fc_mode_by_dcb_flag(struct hclge_dev *hdev)
{
- if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
+ if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en) {
if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
dev_warn(&hdev->pdev->dev,
- "DCB is disable, but last mode is FC_PFC\n");
+ "Only 1 tc used, but last mode is FC_PFC\n");
hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
} else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
}
}
-static void hclge_pfc_info_init(struct hclge_dev *hdev)
+void hclge_tm_pfc_info_update(struct hclge_dev *hdev)
{
if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
hclge_update_fc_mode(hdev);
hclge_tm_vport_info_update(hdev);
- hclge_pfc_info_init(hdev);
+ hclge_tm_pfc_info_update(hdev);
}
static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev)
hclge_tm_schd_info_init(hdev);
}
-void hclge_tm_pfc_info_update(struct hclge_dev *hdev)
-{
- /* DCB is enabled if we have more than 1 TC or pfc_en is
- * non-zero.
- */
- if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en)
- hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
- else
- hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
-
- hclge_pfc_info_init(hdev);
-}
-
int hclge_tm_init_hw(struct hclge_dev *hdev, bool init)
{
int ret;
if (ret)
return ret;
- if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE))
+ if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en)
return 0;
return hclge_tm_bp_setup(hdev);
if (dev_of_node(bus->parent)) {
if (!mdio_dev->subctrl_vbase) {
- dev_err(&bus->dev, "mdio sys ctl reg has not maped\n");
+ dev_err(&bus->dev, "mdio sys ctl reg has not mapped\n");
return -ENODEV;
}
return 0;
}
- if (adapter->failover_pending) {
- adapter->init_done_rc = -EAGAIN;
- netdev_dbg(netdev, "Failover pending, ignoring login response\n");
- complete(&adapter->init_done);
- /* login response buffer will be released on reset */
- return 0;
- }
-
netdev->mtu = adapter->req_mtu - ETH_HLEN;
netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
sizeof(info->bus_info));
}
-#define E100_PHY_REGS 0x1C
+#define E100_PHY_REGS 0x1D
static int e100_get_regs_len(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
- return 1 + E100_PHY_REGS + sizeof(nic->mem->dump_buf);
+
+ /* We know the number of registers, and the size of the dump buffer.
+ * Calculate the total size in bytes.
+ */
+ return (1 + E100_PHY_REGS) * sizeof(u32) + sizeof(nic->mem->dump_buf);
}
static void e100_get_regs(struct net_device *netdev,
buff[0] = ioread8(&nic->csr->scb.cmd_hi) << 24 |
ioread8(&nic->csr->scb.cmd_lo) << 16 |
ioread16(&nic->csr->scb.status);
- for (i = E100_PHY_REGS; i >= 0; i--)
- buff[1 + E100_PHY_REGS - i] =
- mdio_read(netdev, nic->mii.phy_id, i);
+ for (i = 0; i < E100_PHY_REGS; i++)
+ /* Note that we read the registers in reverse order. This
+ * ordering is the ABI apparently used by ethtool and other
+ * applications.
+ */
+ buff[1 + i] = mdio_read(netdev, nic->mii.phy_id,
+ E100_PHY_REGS - 1 - i);
memset(nic->mem->dump_buf, 0, sizeof(nic->mem->dump_buf));
e100_exec_cb(nic, NULL, e100_dump);
msleep(10);
- memcpy(&buff[2 + E100_PHY_REGS], nic->mem->dump_buf,
- sizeof(nic->mem->dump_buf));
+ memcpy(&buff[1 + E100_PHY_REGS], nic->mem->dump_buf,
+ sizeof(nic->mem->dump_buf));
}
static void e100_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
max_combined = ixgbe_max_rss_indices(adapter);
}
- return max_combined;
+ return min_t(int, max_combined, num_online_cpus());
}
static void ixgbe_get_channels(struct net_device *dev,
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct bpf_prog *old_prog;
bool need_reset;
+ int num_queues;
if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
return -EINVAL;
/* Kick start the NAPI context if there is an AF_XDP socket open
* on that queue id. This so that receiving will start.
*/
- if (need_reset && prog)
- for (i = 0; i < adapter->num_rx_queues; i++)
+ if (need_reset && prog) {
+ num_queues = min_t(int, adapter->num_rx_queues,
+ adapter->num_xdp_queues);
+ for (i = 0; i < num_queues; i++)
if (adapter->xdp_ring[i]->xsk_pool)
(void)ixgbe_xsk_wakeup(adapter->netdev, i,
XDP_WAKEUP_RX);
+ }
return 0;
}
#
obj-$(CONFIG_KS8842) += ks8842.o
-obj-$(CONFIG_KS8851) += ks8851.o
-ks8851-objs = ks8851_common.o ks8851_spi.o
-obj-$(CONFIG_KS8851_MLL) += ks8851_mll.o
-ks8851_mll-objs = ks8851_common.o ks8851_par.o
+obj-$(CONFIG_KS8851) += ks8851_common.o ks8851_spi.o
+obj-$(CONFIG_KS8851_MLL) += ks8851_common.o ks8851_par.o
obj-$(CONFIG_KSZ884X_PCI) += ksz884x.o
return 0;
}
+EXPORT_SYMBOL_GPL(ks8851_suspend);
int ks8851_resume(struct device *dev)
{
return 0;
}
+EXPORT_SYMBOL_GPL(ks8851_resume);
#endif
static int ks8851_register_mdiobus(struct ks8851_net *ks, struct device *dev)
err_reg_io:
return ret;
}
+EXPORT_SYMBOL_GPL(ks8851_probe_common);
int ks8851_remove_common(struct device *dev)
{
return 0;
}
+EXPORT_SYMBOL_GPL(ks8851_remove_common);
+
+MODULE_DESCRIPTION("KS8851 Network driver");
+MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
+MODULE_LICENSE("GPL");
&ionic_dbg_intr_stats_desc[i]);
(*buf)++;
}
- for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) {
- **buf = IONIC_READ_STAT64(&txqcq->napi_stats,
- &ionic_dbg_napi_stats_desc[i]);
- (*buf)++;
- }
- for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) {
- **buf = txqcq->napi_stats.work_done_cntr[i];
- (*buf)++;
- }
for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) {
**buf = txstats->sg_cntr[i];
(*buf)++;
timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
eee_tw_timer);
+ if (priv->hw->xpcs)
+ xpcs_config_eee(priv->hw->xpcs,
+ priv->plat->mult_fact_100ns,
+ true);
}
if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
config SUNVNET_COMMON
tristate "Common routines to support Sun Virtual Networking"
depends on SUN_LDOMS
+ depends on INET
default m
config SUNVNET
config DMASCC
tristate "High-speed (DMA) SCC driver for AX.25"
depends on ISA && AX25 && BROKEN_ON_SMP && ISA_DMA_API
+ depends on VIRT_TO_BUS
help
This is a driver for high-speed SCC boards, i.e. those supporting
DMA on one port. You usually use those boards to connect your
{
struct ipq4019_mdio_data *priv;
struct mii_bus *bus;
+ struct resource *res;
int ret;
bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*priv));
return PTR_ERR(priv->mdio_clk);
/* The platform resource is provided on the chipset IPQ5018 */
- priv->eth_ldo_rdy = devm_platform_ioremap_resource(pdev, 1);
+ /* This resource is optional */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (res)
+ priv->eth_ldo_rdy = devm_ioremap_resource(&pdev->dev, res);
bus->name = "ipq4019_mdio";
bus->read = ipq4019_mdio_read;
static int mscc_miim_probe(struct platform_device *pdev)
{
- struct mii_bus *bus;
struct mscc_miim_dev *dev;
+ struct resource *res;
+ struct mii_bus *bus;
int ret;
bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev));
return PTR_ERR(dev->regs);
}
- dev->phy_regs = devm_platform_ioremap_resource(pdev, 1);
- if (IS_ERR(dev->phy_regs)) {
- dev_err(&pdev->dev, "Unable to map internal phy registers\n");
- return PTR_ERR(dev->phy_regs);
+ /* This resource is optional */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (res) {
+ dev->phy_regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(dev->phy_regs)) {
+ dev_err(&pdev->dev, "Unable to map internal phy registers\n");
+ return PTR_ERR(dev->phy_regs);
+ }
}
ret = of_mdiobus_register(bus, pdev->dev.of_node);
/* Start MHI channels */
err = mhi_prepare_for_transfer(mhi_dev);
if (err)
- goto out_err;
+ return err;
/* Number of transfer descriptors determines size of the queue */
mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
return err;
return 0;
-
-out_err:
- free_netdev(ndev);
- return err;
}
static void mhi_net_dellink(struct mhi_device *mhi_dev, struct net_device *ndev)
#define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe
#define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf
#define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a
+#define MII_BCM7XXX_SHD_3_PCS_CTRL 0x0
+#define MII_BCM7XXX_SHD_3_PCS_STATUS 0x1
+#define MII_BCM7XXX_SHD_3_EEE_CAP 0x2
#define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3
+#define MII_BCM7XXX_SHD_3_EEE_LP 0x4
+#define MII_BCM7XXX_SHD_3_EEE_WK_ERR 0x5
#define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6
#define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400
#define MII_BCM7XXX_SHD_3_AN_STAT 0xb
return genphy_config_aneg(phydev);
}
-static int phy_set_clr_bits(struct phy_device *dev, int location,
- int set_mask, int clr_mask)
+static int __phy_set_clr_bits(struct phy_device *dev, int location,
+ int set_mask, int clr_mask)
{
int v, ret;
- v = phy_read(dev, location);
+ v = __phy_read(dev, location);
if (v < 0)
return v;
v &= ~clr_mask;
v |= set_mask;
- ret = phy_write(dev, location, v);
+ ret = __phy_write(dev, location, v);
if (ret < 0)
return ret;
return v;
}
+static int phy_set_clr_bits(struct phy_device *dev, int location,
+ int set_mask, int clr_mask)
+{
+ int ret;
+
+ mutex_lock(&dev->mdio.bus->mdio_lock);
+ ret = __phy_set_clr_bits(dev, location, set_mask, clr_mask);
+ mutex_unlock(&dev->mdio.bus->mdio_lock);
+
+ return ret;
+}
+
static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev)
{
int ret;
return bcm7xxx_28nm_ephy_apd_enable(phydev);
}
+#define MII_BCM7XXX_REG_INVALID 0xff
+
+static u8 bcm7xxx_28nm_ephy_regnum_to_shd(u16 regnum)
+{
+ switch (regnum) {
+ case MDIO_CTRL1:
+ return MII_BCM7XXX_SHD_3_PCS_CTRL;
+ case MDIO_STAT1:
+ return MII_BCM7XXX_SHD_3_PCS_STATUS;
+ case MDIO_PCS_EEE_ABLE:
+ return MII_BCM7XXX_SHD_3_EEE_CAP;
+ case MDIO_AN_EEE_ADV:
+ return MII_BCM7XXX_SHD_3_AN_EEE_ADV;
+ case MDIO_AN_EEE_LPABLE:
+ return MII_BCM7XXX_SHD_3_EEE_LP;
+ case MDIO_PCS_EEE_WK_ERR:
+ return MII_BCM7XXX_SHD_3_EEE_WK_ERR;
+ default:
+ return MII_BCM7XXX_REG_INVALID;
+ }
+}
+
+static bool bcm7xxx_28nm_ephy_dev_valid(int devnum)
+{
+ return devnum == MDIO_MMD_AN || devnum == MDIO_MMD_PCS;
+}
+
+static int bcm7xxx_28nm_ephy_read_mmd(struct phy_device *phydev,
+ int devnum, u16 regnum)
+{
+ u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum);
+ int ret;
+
+ if (!bcm7xxx_28nm_ephy_dev_valid(devnum) ||
+ shd == MII_BCM7XXX_REG_INVALID)
+ return -EOPNOTSUPP;
+
+ /* set shadow mode 2 */
+ ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+ MII_BCM7XXX_SHD_MODE_2, 0);
+ if (ret < 0)
+ return ret;
+
+ /* Access the desired shadow register address */
+ ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ ret = __phy_read(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT);
+
+reset_shadow_mode:
+ /* reset shadow mode 2 */
+ __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+ MII_BCM7XXX_SHD_MODE_2);
+ return ret;
+}
+
+static int bcm7xxx_28nm_ephy_write_mmd(struct phy_device *phydev,
+ int devnum, u16 regnum, u16 val)
+{
+ u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum);
+ int ret;
+
+ if (!bcm7xxx_28nm_ephy_dev_valid(devnum) ||
+ shd == MII_BCM7XXX_REG_INVALID)
+ return -EOPNOTSUPP;
+
+ /* set shadow mode 2 */
+ ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+ MII_BCM7XXX_SHD_MODE_2, 0);
+ if (ret < 0)
+ return ret;
+
+ /* Access the desired shadow register address */
+ ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ /* Write the desired value in the shadow register */
+ __phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, val);
+
+reset_shadow_mode:
+ /* reset shadow mode 2 */
+ return __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+ MII_BCM7XXX_SHD_MODE_2);
+}
+
static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev)
{
int ret;
.get_stats = bcm7xxx_28nm_get_phy_stats, \
.probe = bcm7xxx_28nm_probe, \
.remove = bcm7xxx_28nm_remove, \
+ .read_mmd = bcm7xxx_28nm_ephy_read_mmd, \
+ .write_mmd = bcm7xxx_28nm_ephy_write_mmd, \
}
#define BCM7XXX_40NM_EPHY(_oui, _name) \
err = device_register(&bus->dev);
if (err) {
pr_err("mii_bus %s failed to register\n", bus->id);
+ put_device(&bus->dev);
return -EINVAL;
}
return ret;
}
+static int gpy115_loopback(struct phy_device *phydev, bool enable)
+{
+ int ret;
+ int fw_minor;
+
+ if (enable)
+ return gpy_loopback(phydev, enable);
+
+ ret = phy_read(phydev, PHY_FWV);
+ if (ret < 0)
+ return ret;
+
+ fw_minor = FIELD_GET(PHY_FWV_MINOR_MASK, ret);
+ if (fw_minor > 0x0076)
+ return gpy_loopback(phydev, 0);
+
+ return genphy_soft_reset(phydev);
+}
+
static struct phy_driver gpy_drivers[] = {
{
PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx),
.handle_interrupt = gpy_handle_interrupt,
.set_wol = gpy_set_wol,
.get_wol = gpy_get_wol,
- .set_loopback = gpy_loopback,
+ .set_loopback = gpy115_loopback,
},
{
PHY_ID_MATCH_MODEL(PHY_ID_GPY115C),
.handle_interrupt = gpy_handle_interrupt,
.set_wol = gpy_set_wol,
.get_wol = gpy_get_wol,
- .set_loopback = gpy_loopback,
+ .set_loopback = gpy115_loopback,
},
{
.phy_id = PHY_ID_GPY211B,
static void smsc95xx_handle_link_change(struct net_device *net)
{
+ struct usbnet *dev = netdev_priv(net);
+
phy_print_status(net->phydev);
+ usbnet_defer_kevent(dev, EVENT_LINK_CHANGE);
}
static int smsc95xx_start_phy(struct usbnet *dev)
bcn_int -= data->bcn_delta;
data->bcn_delta = 0;
}
- hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
- ns_to_ktime(bcn_int * NSEC_PER_USEC));
+ hrtimer_forward_now(&data->beacon_timer,
+ ns_to_ktime(bcn_int * NSEC_PER_USEC));
return HRTIMER_RESTART;
}
pmu->name, pmu->num_events,
has_nmi ? ", using NMIs" : "");
+ kvm_host_pmu_init(pmu);
+
return 0;
out_destroy:
/**
* devm_pinctrl_unregister() - Resource managed version of pinctrl_unregister().
- * @dev: device for which which resource was allocated
+ * @dev: device for which resource was allocated
* @pctldev: the pinctrl device to unregister.
*/
void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev)
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3);
+ int err;
raw_spin_lock_irqsave(&gpio_dev->lock, flags);
pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
+ if (on)
+ err = enable_irq_wake(gpio_dev->irq);
+ else
+ err = disable_irq_wake(gpio_dev->irq);
+
+ if (err)
+ dev_err(&gpio_dev->pdev->dev, "failed to %s wake-up interrupt\n",
+ on ? "enable" : "disable");
+
return 0;
}
static int amd_gpio_probe(struct platform_device *pdev)
{
int ret = 0;
- int irq_base;
struct resource *res;
struct amd_gpio *gpio_dev;
struct gpio_irq_chip *girq;
if (!gpio_dev->base)
return -ENOMEM;
- irq_base = platform_get_irq(pdev, 0);
- if (irq_base < 0)
- return irq_base;
+ gpio_dev->irq = platform_get_irq(pdev, 0);
+ if (gpio_dev->irq < 0)
+ return gpio_dev->irq;
#ifdef CONFIG_PM_SLEEP
gpio_dev->saved_regs = devm_kcalloc(&pdev->dev, amd_pinctrl_desc.npins,
goto out2;
}
- ret = devm_request_irq(&pdev->dev, irq_base, amd_gpio_irq_handler,
+ ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
IRQF_SHARED, KBUILD_MODNAME, gpio_dev);
if (ret)
goto out2;
struct resource *res;
struct platform_device *pdev;
u32 *saved_regs;
+ int irq;
};
/* KERNCZ configuration*/
return false;
}
+static int rockchip_pinconf_defer_output(struct rockchip_pin_bank *bank,
+ unsigned int pin, u32 arg)
+{
+ struct rockchip_pin_output_deferred *cfg;
+
+ cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+ if (!cfg)
+ return -ENOMEM;
+
+ cfg->pin = pin;
+ cfg->arg = arg;
+
+ list_add_tail(&cfg->head, &bank->deferred_output);
+
+ return 0;
+}
+
/* set the pin config settings for a specified pin */
static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
unsigned long *configs, unsigned num_configs)
if (rc != RK_FUNC_GPIO)
return -EINVAL;
+ /*
+ * Check for gpio driver not being probed yet.
+ * The lock makes sure that either gpio-probe has completed
+ * or the gpio driver hasn't probed yet.
+ */
+ mutex_lock(&bank->deferred_lock);
+ if (!gpio || !gpio->direction_output) {
+ rc = rockchip_pinconf_defer_output(bank, pin - bank->pin_base, arg);
+ mutex_unlock(&bank->deferred_lock);
+ if (rc)
+ return rc;
+
+ break;
+ }
+ mutex_unlock(&bank->deferred_lock);
+
rc = gpio->direction_output(gpio, pin - bank->pin_base,
arg);
if (rc)
if (rc != RK_FUNC_GPIO)
return -EINVAL;
+ if (!gpio || !gpio->get) {
+ arg = 0;
+ break;
+ }
+
rc = gpio->get(gpio, pin - bank->pin_base);
if (rc < 0)
return rc;
pin_bank->name, pin);
pdesc++;
}
+
+ INIT_LIST_HEAD(&pin_bank->deferred_output);
+ mutex_init(&pin_bank->deferred_lock);
}
ret = rockchip_pinctrl_parse_dt(pdev, info);
return 0;
}
+static int rockchip_pinctrl_remove(struct platform_device *pdev)
+{
+ struct rockchip_pinctrl *info = platform_get_drvdata(pdev);
+ struct rockchip_pin_bank *bank;
+ struct rockchip_pin_output_deferred *cfg;
+ int i;
+
+ of_platform_depopulate(&pdev->dev);
+
+ for (i = 0; i < info->ctrl->nr_banks; i++) {
+ bank = &info->ctrl->pin_banks[i];
+
+ mutex_lock(&bank->deferred_lock);
+ while (!list_empty(&bank->deferred_output)) {
+ cfg = list_first_entry(&bank->deferred_output,
+ struct rockchip_pin_output_deferred, head);
+ list_del(&cfg->head);
+ kfree(cfg);
+ }
+ mutex_unlock(&bank->deferred_lock);
+ }
+
+ return 0;
+}
+
static struct rockchip_pin_bank px30_pin_banks[] = {
PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU,
IOMUX_SOURCE_PMU,
static struct platform_driver rockchip_pinctrl_driver = {
.probe = rockchip_pinctrl_probe,
+ .remove = rockchip_pinctrl_remove,
.driver = {
.name = "rockchip-pinctrl",
.pm = &rockchip_pinctrl_dev_pm_ops,
* @toggle_edge_mode: bit mask to toggle (falling/rising) edge mode
* @recalced_mask: bit mask to indicate a need to recalulate the mask
* @route_mask: bits describing the routing pins of per bank
+ * @deferred_output: gpio output settings to be done after gpio bank probed
+ * @deferred_lock: mutex for the deferred_output shared btw gpio and pinctrl
*/
struct rockchip_pin_bank {
struct device *dev;
u32 toggle_edge_mode;
u32 recalced_mask;
u32 route_mask;
+ struct list_head deferred_output;
+ struct mutex deferred_lock;
};
/**
unsigned int nconfigs;
};
+struct rockchip_pin_output_deferred {
+ struct list_head head;
+ unsigned int pin;
+ u32 arg;
+};
+
/**
* struct rockchip_pin_group: represent group of pins of a pinmux function.
* @name: name of the pin group, used to lookup the group.
static struct platform_driver sc7280_pinctrl_driver = {
.driver = {
.name = "sc7280-pinctrl",
+ .pm = &msm_pinctrl_dev_pm_ops,
.of_match_table = sc7280_pinctrl_of_match,
},
.probe = sc7280_pinctrl_probe,
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2012-2014, 2016-2021 The Linux Foundation. All rights reserved.
*/
#include <linux/gpio/driver.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/slab.h>
+#include <linux/spmi.h>
#include <linux/types.h>
#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
struct pinctrl_dev *ctrl;
struct gpio_chip chip;
struct irq_chip irq;
+ u8 usid;
+ u8 pid_base;
};
static const struct pinconf_generic_params pmic_gpio_bindings[] = {
unsigned int *parent_hwirq,
unsigned int *parent_type)
{
- *parent_hwirq = child_hwirq + 0xc0;
+ struct pmic_gpio_state *state = gpiochip_get_data(chip);
+
+ *parent_hwirq = child_hwirq + state->pid_base;
*parent_type = child_type;
return 0;
}
+static void *pmic_gpio_populate_parent_fwspec(struct gpio_chip *chip,
+ unsigned int parent_hwirq,
+ unsigned int parent_type)
+{
+ struct pmic_gpio_state *state = gpiochip_get_data(chip);
+ struct irq_fwspec *fwspec;
+
+ fwspec = kzalloc(sizeof(*fwspec), GFP_KERNEL);
+ if (!fwspec)
+ return NULL;
+
+ fwspec->fwnode = chip->irq.parent_domain->fwnode;
+
+ fwspec->param_count = 4;
+ fwspec->param[0] = state->usid;
+ fwspec->param[1] = parent_hwirq;
+ /* param[2] must be left as 0 */
+ fwspec->param[3] = parent_type;
+
+ return fwspec;
+}
+
static int pmic_gpio_probe(struct platform_device *pdev)
{
struct irq_domain *parent_domain;
struct pmic_gpio_pad *pad, *pads;
struct pmic_gpio_state *state;
struct gpio_irq_chip *girq;
+ const struct spmi_device *parent_spmi_dev;
int ret, npins, i;
u32 reg;
state->dev = &pdev->dev;
state->map = dev_get_regmap(dev->parent, NULL);
+ parent_spmi_dev = to_spmi_device(dev->parent);
+ state->usid = parent_spmi_dev->usid;
+ state->pid_base = reg >> 8;
pindesc = devm_kcalloc(dev, npins, sizeof(*pindesc), GFP_KERNEL);
if (!pindesc)
girq->fwnode = of_node_to_fwnode(state->dev->of_node);
girq->parent_domain = parent_domain;
girq->child_to_parent_hwirq = pmic_gpio_child_to_parent_hwirq;
- girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_fourcell;
+ girq->populate_parent_alloc_arg = pmic_gpio_populate_parent_fwspec;
girq->child_offset_to_irq = pmic_gpio_child_offset_to_irq;
girq->child_irq_domain_ops.translate = pmic_gpio_domain_translate;
mutex_lock(&matrix_dev->lock);
list_del(&matrix_mdev->node);
mutex_unlock(&matrix_dev->lock);
+ vfio_uninit_group_dev(&matrix_mdev->vdev);
kfree(matrix_mdev);
err_dec_available:
atomic_inc(&matrix_dev->available_instances);
mutex_lock(&matrix_dev->lock);
vfio_ap_mdev_reset_queues(matrix_mdev);
list_del(&matrix_mdev->node);
+ mutex_unlock(&matrix_dev->lock);
+ vfio_uninit_group_dev(&matrix_mdev->vdev);
kfree(matrix_mdev);
atomic_inc(&matrix_dev->available_instances);
- mutex_unlock(&matrix_dev->lock);
}
static ssize_t name_show(struct mdev_type *mtype,
if (!vpu->variant->irqs[i].handler)
continue;
- if (vpu->variant->num_clocks > 1) {
+ if (vpu->variant->num_irqs > 1) {
irq_name = vpu->variant->irqs[i].name;
irq = platform_get_irq_byname(vpu->pdev, irq_name);
} else {
sizeimage = bytesperline * height;
/* Chroma plane size. */
- sizeimage += bytesperline * height / 2;
+ sizeimage += bytesperline * ALIGN(height, 64) / 2;
break;
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
struct mlx5_vdpa_virtqueue *mvq;
+ if (!mvdev->actual_features)
+ return;
+
if (!is_index_valid(mvdev, idx))
return;
for (i = 0; i < ndev->mvdev.max_vqs; i++)
ndev->vqs[i].ready = false;
+
+ ndev->mvdev.cvq.ready = false;
}
static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
static int vduse_vdpa_reset(struct vdpa_device *vdpa)
{
struct vduse_dev *dev = vdpa_to_vduse(vdpa);
-
- if (vduse_dev_set_status(dev, 0))
- return -EIO;
+ int ret = vduse_dev_set_status(dev, 0);
vduse_dev_reset(dev);
- return 0;
+ return ret;
}
static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa)
vduse_irq_wq = alloc_workqueue("vduse-irq",
WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0);
- if (!vduse_irq_wq)
+ if (!vduse_irq_wq) {
+ ret = -ENOMEM;
goto err_wq;
+ }
ret = vduse_domain_init();
if (ret)
}
struct vfio_pci_walk_info {
- int (*fn)(struct pci_dev *, void *data);
+ int (*fn)(struct pci_dev *pdev, void *data);
void *data;
struct pci_dev *pdev;
bool slot;
u64 offset, map_size, map_iova = iova;
struct vdpa_map_file *map_file;
struct vm_area_struct *vma;
- int ret;
+ int ret = 0;
mmap_read_lock(dev->mm);
ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device);
BUG_ON(ret >= sizeof(compat));
+ /*
+ * On powerpc/pseries virtio devices are PCI devices so PCI
+ * vendor/device ids play the role of the "compatible" property.
+ * Simply don't init of_node in this case.
+ */
if (!of_device_is_compatible(np, compat)) {
- ret = -EINVAL;
+ ret = 0;
goto out;
}
config SIBYTE_WDOG
tristate "Sibyte SoC hardware watchdog"
- depends on CPU_SB1 || (MIPS && COMPILE_TEST)
+ depends on CPU_SB1
help
Watchdog driver for the built in watchdog hardware in Sibyte
SoC processors. There are apparently two watchdog timers
#define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */
-#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000')
-#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377')
-#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376')
-#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375')
+static const unsigned char VBSF_MOUNT_SIGNATURE[4] = "\000\377\376\375";
static int follow_symlinks;
module_param(follow_symlinks, int, 0444);
static int vboxsf_parse_monolithic(struct fs_context *fc, void *data)
{
- unsigned char *options = data;
-
- if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 &&
- options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 &&
- options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 &&
- options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) {
+ if (data && !memcmp(data, VBSF_MOUNT_SIGNATURE, 4)) {
vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n");
return -EINVAL;
}
* (level 0) and ascending to the root node (level 'num_levels - 1').
* Then at the end (level 'num_levels'), calculate the root hash.
*/
- blocks = (inode->i_size + params->block_size - 1) >>
+ blocks = ((u64)inode->i_size + params->block_size - 1) >>
params->log_blocksize;
for (level = 0; level <= params->num_levels; level++) {
err = build_merkle_tree_level(filp, level, blocks, params,
*/
/* Compute number of levels and the number of blocks in each level */
- blocks = (inode->i_size + params->block_size - 1) >> log_blocksize;
+ blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize;
pr_debug("Data is %lld bytes (%llu blocks)\n", inode->i_size, blocks);
while (blocks > 1) {
if (params->num_levels >= FS_VERITY_MAX_LEVELS) {
int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
-int kvm_pmu_probe_pmuver(void);
#else
struct kvm_pmu {
};
return 0;
}
-static inline int kvm_pmu_probe_pmuver(void) { return 0xf; }
-
#endif
#endif
* programs only. Should not be used with normal calls and indirect calls.
*/
#define BPF_TRAMP_F_SKIP_FRAME BIT(2)
-
/* Store IP address of the caller on the trampoline stack,
* so it's available for trampoline's programs.
*/
#define BPF_TRAMP_F_IP_ARG BIT(3)
+/* Return the return value of fentry prog. Only used by bpf_struct_ops. */
+#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4)
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
* bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2
unsigned long mmu_notifier_range_start;
unsigned long mmu_notifier_range_end;
#endif
- long tlbs_dirty;
struct list_head devices;
u64 manual_dirty_log_protect;
struct dentry *debugfs_dentry;
return NULL;
}
-static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
-{
- return vcpu->vcpu_idx;
-}
-
#define kvm_for_each_memslot(memslot, slots) \
for (memslot = &slots->memslots[0]; \
memslot < slots->memslots + slots->used_slots; memslot++) \
static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
#endif
+#ifdef CONFIG_KVM
+void kvm_host_pmu_init(struct arm_pmu *pmu);
+#else
+#define kvm_host_pmu_init(x) do { } while(0)
+#endif
+
/* Internal functions only for core arm_pmu code */
struct arm_pmu *armpmu_alloc(void);
struct arm_pmu *armpmu_alloc_atomic(void);
int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
u8 rt_family, unsigned char *flags, bool skip_oif);
int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
- int nh_weight, u8 rt_family);
+ int nh_weight, u8 rt_family, u32 nh_tclassid);
#endif /* _NET_FIB_H */
* Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag
* when they are able to replace in-use PTK keys according to the following
* requirements:
- * 1) They do not hand over frames decrypted with the old key to
- mac80211 once the call to set_key() with command %DISABLE_KEY has been
- completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key,
+ * 1) They do not hand over frames decrypted with the old key to mac80211
+ once the call to set_key() with command %DISABLE_KEY has been completed,
2) either drop or continue to use the old key for any outgoing frames queued
at the time of the key deletion (including re-transmits),
3) never send out a frame queued prior to the set_key() %SET_KEY command
- encrypted with the new key and
+ encrypted with the new key when also needing
+ @IEEE80211_KEY_FLAG_GENERATE_IV and
4) never send out a frame unencrypted when it should be encrypted.
Mac80211 will not queue any new frames for a deleted key to the driver.
*/
struct fib_nh_common *nhc = &nhi->fib_nhc;
int weight = nhg->nh_entries[i].weight;
- if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0)
+ if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0)
return -EMSGSIZE;
}
#include <uapi/linux/pkt_sched.h>
#define DEFAULT_TX_QUEUE_LEN 1000
+#define STAB_SIZE_LOG_MAX 30
struct qdisc_walker {
int stop;
u8 sk_prefer_busy_poll;
u16 sk_busy_poll_budget;
#endif
+ spinlock_t sk_peer_lock;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
+
long sk_rcvtimeo;
ktime_t sk_stamp;
#if BITS_PER_LONG==32
SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
-bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock);
+bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock);
+
+/**
+ * lock_sock_fast - fast version of lock_sock
+ * @sk: socket
+ *
+ * This version should be used for very small section, where process wont block
+ * return false if fast path is taken:
+ *
+ * sk_lock.slock locked, owned = 0, BH disabled
+ *
+ * return true if slow path is taken:
+ *
+ * sk_lock.slock unlocked, owned = 1, BH enabled
+ */
+static inline bool lock_sock_fast(struct sock *sk)
+{
+ /* The sk_lock has mutex_lock() semantics here. */
+ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+
+ return __lock_sock_fast(sk);
+}
+
+/* fast socket lock variant for caller already holding a [different] socket lock */
+static inline bool lock_sock_fast_nested(struct sock *sk)
+{
+ mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+
+ return __lock_sock_fast(sk);
+}
/**
* unlock_sock_fast - complement of lock_sock_fast
struct snd_rawmidi *rmidi;
struct snd_rawmidi_substream *input;
struct snd_rawmidi_substream *output;
+ unsigned int user_pversion; /* supported protocol version */
};
struct snd_rawmidi_str {
#define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int)
#define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info)
+#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int)
#define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params)
#define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status)
#define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int)
const struct btf_type *mtype, *ptype;
struct bpf_prog *prog;
u32 moff;
+ u32 flags;
moff = btf_member_bit_offset(t, member) / 8;
ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
+ flags = st_ops->func_models[i].ret_size > 0 ?
+ BPF_TRAMP_F_RET_FENTRY_RET : 0;
err = arch_prepare_bpf_trampoline(NULL, image,
st_map->image + PAGE_SIZE,
- &st_ops->func_models[i], 0,
- tprogs, NULL);
+ &st_ops->func_models[i],
+ flags, tprogs, NULL);
if (err < 0)
goto reset_unlock;
{
if (atomic_long_add_return(pages, &bpf_jit_current) >
(bpf_jit_limit >> PAGE_SHIFT)) {
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!bpf_capable()) {
atomic_long_sub(pages, &bpf_jit_current);
return -EPERM;
}
void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
{
- /* Don't associate the sock with unrelated interrupted task's cgroup. */
- if (in_interrupt())
- return;
+ struct cgroup *cgroup;
rcu_read_lock();
+ /* Don't associate the sock with unrelated interrupted task's cgroup. */
+ if (in_interrupt()) {
+ cgroup = &cgrp_dfl_root.cgrp;
+ cgroup_get(cgroup);
+ goto out;
+ }
+
while (true) {
struct css_set *cset;
cset = task_css_set(current);
if (likely(cgroup_tryget(cset->dfl_cgrp))) {
- skcd->cgroup = cset->dfl_cgrp;
- cgroup_bpf_get(cset->dfl_cgrp);
+ cgroup = cset->dfl_cgrp;
break;
}
cpu_relax();
}
+out:
+ skcd->cgroup = cgroup;
+ cgroup_bpf_get(cgroup);
rcu_read_unlock();
}
__skb->gso_segs = skb_shinfo(skb)->gso_segs;
}
+static struct proto bpf_dummy_proto = {
+ .name = "bpf_dummy",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct sock),
+};
+
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
break;
}
- sk = kzalloc(sizeof(struct sock), GFP_USER);
+ sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1);
if (!sk) {
kfree(data);
kfree(ctx);
return -ENOMEM;
}
- sock_net_set(sk, net);
sock_init_data(NULL, sk);
skb = build_skb(data, 0);
if (!skb) {
kfree(data);
kfree(ctx);
- kfree(sk);
+ sk_free(sk);
return -ENOMEM;
}
skb->sk = sk;
if (dev && dev != net->loopback_dev)
dev_put(dev);
kfree_skb(skb);
- bpf_sk_storage_free(sk);
- kfree(sk);
+ sk_free(sk);
kfree(ctx);
return ret;
}
int ifindex,
struct br_ip *saddr)
{
- lockdep_assert_held_once(&brmctx->br->multicast_lock);
-
write_seqcount_begin(&querier->seq);
querier->port_ifidx = ifindex;
memcpy(&querier->addr, saddr, sizeof(*saddr));
brmctx->ip4_other_query.delay_time = 0;
brmctx->ip4_querier.port_ifidx = 0;
- seqcount_init(&brmctx->ip4_querier.seq);
+ seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock);
brmctx->multicast_igmp_version = 2;
#if IS_ENABLED(CONFIG_IPV6)
brmctx->multicast_mld_version = 1;
brmctx->ip6_other_query.delay_time = 0;
brmctx->ip6_querier.port_ifidx = 0;
- seqcount_init(&brmctx->ip6_querier.seq);
+ seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
#endif
timer_setup(&brmctx->ip4_mc_router_timer,
struct bridge_mcast_querier {
struct br_ip addr;
int port_ifidx;
- seqcount_t seq;
+ seqcount_spinlock_t seq;
};
/* IGMP/MLD statistics */
if (addr_len > MAX_ADDR_LEN)
return -EINVAL;
+ ha = list_first_entry(&list->list, struct netdev_hw_addr, list);
+ if (ha && !memcmp(addr, ha->addr, addr_len) &&
+ (!addr_type || addr_type == ha->type))
+ goto found_it;
+
while (*ins_point) {
int diff;
} else if (diff > 0) {
ins_point = &parent->rb_right;
} else {
+found_it:
if (exclusive)
return -EEXIST;
if (global) {
}
EXPORT_SYMBOL(sock_setsockopt);
+static const struct cred *sk_get_peer_cred(struct sock *sk)
+{
+ const struct cred *cred;
+
+ spin_lock(&sk->sk_peer_lock);
+ cred = get_cred(sk->sk_peer_cred);
+ spin_unlock(&sk->sk_peer_lock);
+
+ return cred;
+}
static void cred_to_ucred(struct pid *pid, const struct cred *cred,
struct ucred *ucred)
struct ucred peercred;
if (len > sizeof(peercred))
len = sizeof(peercred);
+
+ spin_lock(&sk->sk_peer_lock);
cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
+ spin_unlock(&sk->sk_peer_lock);
+
if (copy_to_user(optval, &peercred, len))
return -EFAULT;
goto lenout;
case SO_PEERGROUPS:
{
+ const struct cred *cred;
int ret, n;
- if (!sk->sk_peer_cred)
+ cred = sk_get_peer_cred(sk);
+ if (!cred)
return -ENODATA;
- n = sk->sk_peer_cred->group_info->ngroups;
+ n = cred->group_info->ngroups;
if (len < n * sizeof(gid_t)) {
len = n * sizeof(gid_t);
+ put_cred(cred);
return put_user(len, optlen) ? -EFAULT : -ERANGE;
}
len = n * sizeof(gid_t);
- ret = groups_to_user((gid_t __user *)optval,
- sk->sk_peer_cred->group_info);
+ ret = groups_to_user((gid_t __user *)optval, cred->group_info);
+ put_cred(cred);
if (ret)
return ret;
goto lenout;
sk->sk_frag.page = NULL;
}
- if (sk->sk_peer_cred)
- put_cred(sk->sk_peer_cred);
+ /* We do not need to acquire sk->sk_peer_lock, we are the last user. */
+ put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
+
if (likely(sk->sk_net_refcnt))
put_net(sock_net(sk));
sk_prot_free(sk->sk_prot_creator, sk);
sk->sk_peer_pid = NULL;
sk->sk_peer_cred = NULL;
+ spin_lock_init(&sk->sk_peer_lock);
+
sk->sk_write_pending = 0;
sk->sk_rcvlowat = 1;
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
}
EXPORT_SYMBOL(release_sock);
-/**
- * lock_sock_fast - fast version of lock_sock
- * @sk: socket
- *
- * This version should be used for very small section, where process wont block
- * return false if fast path is taken:
- *
- * sk_lock.slock locked, owned = 0, BH disabled
- *
- * return true if slow path is taken:
- *
- * sk_lock.slock unlocked, owned = 1, BH enabled
- */
-bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
+bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
{
- /* The sk_lock has mutex_lock() semantics here. */
- mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
-
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
spin_unlock_bh(&sk->sk_lock.slock);
return true;
}
-EXPORT_SYMBOL(lock_sock_fast);
+EXPORT_SYMBOL(__lock_sock_fast);
int sock_gettstamp(struct socket *sock, void __user *userstamp,
bool timeval, bool time32)
#if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6)
int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
- int nh_weight, u8 rt_family)
+ int nh_weight, u8 rt_family, u32 nh_tclassid)
{
const struct net_device *dev = nhc->nhc_dev;
struct rtnexthop *rtnh;
rtnh->rtnh_flags = flags;
+ if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid))
+ goto nla_put_failure;
+
/* length of rtnetlink header + attributes */
rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
}
for_nexthops(fi) {
- if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight,
- AF_INET) < 0)
- goto nla_put_failure;
+ u32 nh_tclassid = 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
- if (nh->nh_tclassid &&
- nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
- goto nla_put_failure;
+ nh_tclassid = nh->nh_tclassid;
#endif
+ if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight,
+ AF_INET, nh_tclassid) < 0)
+ goto nla_put_failure;
} endfor_nexthops(fi);
mp_end:
static struct nf_hook_ops *rawtable_ops __read_mostly;
-static int __net_init iptable_raw_table_init(struct net *net)
+static int iptable_raw_table_init(struct net *net)
{
struct ipt_replace *repl;
const struct xt_table *table = &packet_raw;
__be16 dport;
u8 tos;
int err, is_udplite = IS_UDPLITE(sk);
- int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
+ int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
struct sk_buff *skb;
struct ip_options_data opt_copy;
}
up->len += size;
- if (!(up->corkflag || (flags&MSG_MORE)))
+ if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE)))
ret = udp_push_pending_frames(sk);
if (!ret)
ret = size;
switch (optname) {
case UDP_CORK:
if (val != 0) {
- up->corkflag = 1;
+ WRITE_ONCE(up->corkflag, 1);
} else {
- up->corkflag = 0;
+ WRITE_ONCE(up->corkflag, 0);
lock_sock(sk);
push_pending_frames(sk);
release_sock(sk);
switch (optname) {
case UDP_CORK:
- val = up->corkflag;
+ val = READ_ONCE(up->corkflag);
break;
case UDP_ENCAP:
* things we don't know, ie. tcp syn flag or ports). If the
* rule is also a fragment-specific rule, non-fragments won't
* match it. */
+ acpar.fragoff = 0;
acpar.hotdrop = false;
acpar.state = state;
goto nla_put_failure;
if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common,
- rt->fib6_nh->fib_nh_weight, AF_INET6) < 0)
+ rt->fib6_nh->fib_nh_weight, AF_INET6,
+ 0) < 0)
goto nla_put_failure;
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings, fib6_siblings) {
if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
sibling->fib6_nh->fib_nh_weight,
- AF_INET6) < 0)
+ AF_INET6, 0) < 0)
goto nla_put_failure;
}
int addr_len = msg->msg_namelen;
bool connected = false;
int ulen = len;
- int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
+ int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
int err;
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
atomic_set(&newtbl->entries, 0);
spin_lock_init(&newtbl->gates_lock);
spin_lock_init(&newtbl->walk_lock);
- rhashtable_init(&newtbl->rhead, &mesh_rht_params);
+ if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) {
+ kfree(newtbl);
+ return NULL;
+ }
return newtbl;
}
/*
* Copyright 2012-2013, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de>
* Copyright 2012-2013, cozybit Inc.
+ * Copyright (C) 2021 Intel Corporation
*/
#include "mesh.h"
/* only transmit to PS STA with announced, non-zero awake window */
if (test_sta_flag(sta, WLAN_STA_PS_STA) &&
- (!elems->awake_window || !le16_to_cpu(*elems->awake_window)))
+ (!elems->awake_window || !get_unaligned_le16(elems->awake_window)))
return;
if (!test_sta_flag(sta, WLAN_STA_MPSP_OWNER))
int mcast_rate;
bool use_basicrate = false;
- if (ieee80211_is_tx_data(txrc->skb) &&
- info->flags & IEEE80211_TX_CTL_NO_ACK)
- return false;
-
if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) {
__rate_control_send_low(txrc->hw, sband, pubsta, info,
txrc->rate_idx_mask);
if (!bssid)
return false;
if (ether_addr_equal(sdata->vif.addr, hdr->addr2) ||
- ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2))
+ ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2) ||
+ !is_valid_ether_addr(hdr->addr2))
return false;
if (ieee80211_is_beacon(hdr->frame_control))
return true;
}
vht_mcs = iterator.this_arg[4] >> 4;
+ if (vht_mcs > 11)
+ vht_mcs = 0;
vht_nss = iterator.this_arg[4] & 0xF;
+ if (!vht_nss || vht_nss > 8)
+ vht_nss = 1;
break;
/*
if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head))
goto out;
+ /* If n == 2, the "while (*frag_tail)" loop above didn't execute
+ * and frag_tail should be &skb_shinfo(head)->frag_list.
+ * However, ieee80211_amsdu_prepare_head() can reallocate it.
+ * Reload frag_tail to have it pointing to the correct place.
+ */
+ if (n == 2)
+ frag_tail = &skb_shinfo(head)->frag_list;
+
/*
* Pad out the previous subframe to a multiple of 4 by adding the
* padding to the next one, that's being added. Note that head->len
return RX_DROP_UNUSABLE;
}
+ /* reload hdr - skb might have been reallocated */
+ hdr = (void *)rx->skb->data;
+
data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len;
if (!rx->sta || data_len < 0)
return RX_DROP_UNUSABLE;
return RX_DROP_UNUSABLE;
}
+ /* reload hdr - skb might have been reallocated */
+ hdr = (void *)rx->skb->data;
+
data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len;
if (!rx->sta || data_len < 0)
return RX_DROP_UNUSABLE;
struct sock *sk;
net = sock_net(in_skb->sk);
- msk = mptcp_token_get_sock(req->id.idiag_cookie[0]);
+ msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]);
if (!msk)
goto out_nosk;
list_for_each_entry(entry, &pernet->local_addr_list, list) {
if (addresses_equal(&entry->addr, &addr.addr, true)) {
- ret = mptcp_nl_addr_backup(net, &entry->addr, bkup);
- if (ret)
- return ret;
+ mptcp_nl_addr_backup(net, &entry->addr, bkup);
if (bkup)
entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow = lock_sock_fast(ssk);
+ bool slow = lock_sock_fast_nested(ssk);
sock_orphan(ssk);
unlock_sock_fast(ssk, slow);
void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
struct mptcp_sock *msk);
bool mptcp_token_exists(u32 token);
-struct mptcp_sock *mptcp_token_get_sock(u32 token);
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token);
struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
long *s_num);
void mptcp_token_destroy(struct mptcp_sock *msk);
struct mptcp_sock *msk;
int local_id;
- msk = mptcp_token_get_sock(subflow_req->token);
+ msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token);
if (!msk) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
return NULL;
e->valid = 0;
- msk = mptcp_token_get_sock(e->token);
+ msk = mptcp_token_get_sock(net, e->token);
if (!msk) {
spin_unlock_bh(&join_entry_locks[i]);
return false;
}
- /* If this fails, the token got re-used in the mean time by another
- * mptcp socket in a different netns, i.e. entry is outdated.
- */
- if (!net_eq(sock_net((struct sock *)msk), net))
- goto err_put;
-
subflow_req->remote_nonce = e->remote_nonce;
subflow_req->local_nonce = e->local_nonce;
subflow_req->backup = e->backup;
subflow_req->msk = msk;
spin_unlock_bh(&join_entry_locks[i]);
return true;
-
-err_put:
- spin_unlock_bh(&join_entry_locks[i]);
- sock_put((struct sock *)msk);
- return false;
}
void __init mptcp_join_cookie_init(void)
/**
* mptcp_token_get_sock - retrieve mptcp connection sock using its token
+ * @net: restrict to this namespace
* @token: token of the mptcp connection to retrieve
*
* This function returns the mptcp connection structure with the given token.
*
* returns NULL if no connection with the given token value exists.
*/
-struct mptcp_sock *mptcp_token_get_sock(u32 token)
+struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token)
{
struct hlist_nulls_node *pos;
struct token_bucket *bucket;
again:
sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
msk = mptcp_sk(sk);
- if (READ_ONCE(msk->token) != token)
+ if (READ_ONCE(msk->token) != token ||
+ !net_eq(sock_net(sk), net))
continue;
+
if (!refcount_inc_not_zero(&sk->sk_refcnt))
goto not_found;
- if (READ_ONCE(msk->token) != token) {
+
+ if (READ_ONCE(msk->token) != token ||
+ !net_eq(sock_net(sk), net)) {
sock_put(sk);
goto again;
}
GFP_USER);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req);
mptcp_token_init_request((struct request_sock *)req);
+ sock_net_set((struct sock *)req, &init_net);
return req;
}
KUNIT_ASSERT_EQ(test, 0,
mptcp_token_new_request((struct request_sock *)req));
KUNIT_EXPECT_NE(test, 0, (int)req->token);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token));
/* cleanup */
mptcp_token_destroy_request((struct request_sock *)req);
msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk);
refcount_set(&((struct sock *)msk)->sk_refcnt, 1);
+ sock_net_set((struct sock *)msk, &init_net);
return msk;
}
mptcp_token_new_connect((struct sock *)icsk));
KUNIT_EXPECT_NE(test, 0, (int)ctx->token);
KUNIT_EXPECT_EQ(test, ctx->token, msk->token);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token));
KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt));
mptcp_token_destroy(msk);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token));
}
static void mptcp_token_test_accept(struct kunit *test)
mptcp_token_new_request((struct request_sock *)req));
msk->token = req->token;
mptcp_token_accept(req, msk);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
/* this is now a no-op */
mptcp_token_destroy_request((struct request_sock *)req);
- KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token));
/* cleanup */
mptcp_token_destroy(msk);
/* simulate race on removal */
refcount_set(&sk->sk_refcnt, 0);
- KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token));
+ KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token));
/* cleanup */
mptcp_token_destroy(msk);
{
size_t hsize;
- /* We must fit both into u32 in jhash and size_t */
+ /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */
if (hbits > 31)
return 0;
hsize = jhash_size(hbits);
- if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *)
+ if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *)
< hsize)
return 0;
int idx;
/* Compute size and mask */
+ if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
+ pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
+ ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
+ }
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1;
static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
+/* serialize hash resizes and nf_ct_iterate_cleanup */
+static DEFINE_MUTEX(nf_conntrack_mutex);
+
#define GC_SCAN_INTERVAL (120u * HZ)
#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
-#define MAX_CHAINLEN 64u
+#define MIN_CHAINLEN 8u
+#define MAX_CHAINLEN (32u - MIN_CHAINLEN)
static struct conntrack_gc_work conntrack_gc_work;
static siphash_key_t nf_conntrack_hash_rnd __read_mostly;
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid,
const struct net *net)
{
struct {
struct nf_conntrack_man src;
union nf_inet_addr dst_addr;
+ unsigned int zone;
u32 net_mix;
u16 dport;
u16 proto;
/* The direction must be ignored, so handle usable members manually. */
combined.src = tuple->src;
combined.dst_addr = tuple->dst.u3;
+ combined.zone = zoneid;
combined.net_mix = net_hash_mix(net);
combined.dport = (__force __u16)tuple->dst.u.all;
combined.proto = tuple->dst.protonum;
static u32 __hash_conntrack(const struct net *net,
const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid,
unsigned int size)
{
- return reciprocal_scale(hash_conntrack_raw(tuple, net), size);
+ return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size);
}
static u32 hash_conntrack(const struct net *net,
- const struct nf_conntrack_tuple *tuple)
+ const struct nf_conntrack_tuple *tuple,
+ unsigned int zoneid)
{
- return scale_hash(hash_conntrack_raw(tuple, net));
+ return scale_hash(hash_conntrack_raw(tuple, zoneid, net));
}
static bool nf_ct_get_tuple_ports(const struct sk_buff *skb,
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL));
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
clean_from_lists(ct);
nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple)
{
- return __nf_conntrack_find_get(net, zone, tuple,
- hash_conntrack_raw(tuple, net));
+ unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL);
+ struct nf_conntrack_tuple_hash *thash;
+
+ thash = __nf_conntrack_find_get(net, zone, tuple,
+ hash_conntrack_raw(tuple, zone_id, net));
+
+ if (thash)
+ return thash;
+
+ rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY);
+ if (rid != zone_id)
+ return __nf_conntrack_find_get(net, zone, tuple,
+ hash_conntrack_raw(tuple, rid, net));
+ return thash;
}
EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
+ unsigned int max_chainlen;
unsigned int chainlen = 0;
unsigned int sequence;
int err = -EEXIST;
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL));
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+ max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN);
+
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
int
__nf_conntrack_confirm(struct sk_buff *skb)
{
+ unsigned int chainlen = 0, sequence, max_chainlen;
const struct nf_conntrack_zone *zone;
- unsigned int chainlen = 0, sequence;
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
hash = scale_hash(hash);
reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
-
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY));
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* We're not in hash table, and we refuse to set up related
goto dying;
}
+ max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN);
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN)
+ if (chainlen++ > max_chainlen)
goto chaintoolong;
}
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
- if (chainlen++ > MAX_CHAINLEN) {
+ if (chainlen++ > max_chainlen) {
chaintoolong:
nf_ct_add_to_dying_list(ct);
NF_CT_STAT_INC(net, chaintoolong);
rcu_read_lock();
begin:
nf_conntrack_get_ht(&ct_hash, &hsize);
- hash = __hash_conntrack(net, tuple, hsize);
+ hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize);
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
struct nf_conntrack_tuple_hash *h;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_zone tmp;
+ u32 hash, zone_id, rid;
struct nf_conn *ct;
- u32 hash;
if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
dataoff, state->pf, protonum, state->net,
/* look for tuple match */
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
- hash = hash_conntrack_raw(&tuple, state->net);
+
+ zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL);
+ hash = hash_conntrack_raw(&tuple, zone_id, state->net);
h = __nf_conntrack_find_get(state->net, zone, &tuple, hash);
+
+ if (!h) {
+ rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY);
+ if (zone_id != rid) {
+ u32 tmp = hash_conntrack_raw(&tuple, rid, state->net);
+
+ h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp);
+ }
+ }
+
if (!h) {
h = init_conntrack(state->net, tmpl, &tuple,
skb, dataoff, hash);
spinlock_t *lockp;
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
+ struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket];
+
+ if (hlist_nulls_empty(hslot))
+ continue;
+
lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
local_bh_disable();
nf_conntrack_lock(lockp);
- if (*bucket < nf_conntrack_htable_size) {
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
- continue;
- /* All nf_conn objects are added to hash table twice, one
- * for original direction tuple, once for the reply tuple.
- *
- * Exception: In the IPS_NAT_CLASH case, only the reply
- * tuple is added (the original tuple already existed for
- * a different object).
- *
- * We only need to call the iterator once for each
- * conntrack, so we just use the 'reply' direction
- * tuple while iterating.
- */
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- goto found;
- }
+ hlist_nulls_for_each_entry(h, n, hslot, hnnode) {
+ if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
+ continue;
+ /* All nf_conn objects are added to hash table twice, one
+ * for original direction tuple, once for the reply tuple.
+ *
+ * Exception: In the IPS_NAT_CLASH case, only the reply
+ * tuple is added (the original tuple already existed for
+ * a different object).
+ *
+ * We only need to call the iterator once for each
+ * conntrack, so we just use the 'reply' direction
+ * tuple while iterating.
+ */
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (iter(ct, data))
+ goto found;
}
spin_unlock(lockp);
local_bh_enable();
static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data),
void *data, u32 portid, int report)
{
- unsigned int bucket = 0, sequence;
+ unsigned int bucket = 0;
struct nf_conn *ct;
might_sleep();
- for (;;) {
- sequence = read_seqcount_begin(&nf_conntrack_generation);
-
- while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) {
- /* Time to push up daises... */
+ mutex_lock(&nf_conntrack_mutex);
+ while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) {
+ /* Time to push up daises... */
- nf_ct_delete(ct, portid, report);
- nf_ct_put(ct);
- cond_resched();
- }
-
- if (!read_seqcount_retry(&nf_conntrack_generation, sequence))
- break;
- bucket = 0;
+ nf_ct_delete(ct, portid, report);
+ nf_ct_put(ct);
+ cond_resched();
}
+ mutex_unlock(&nf_conntrack_mutex);
}
struct iter_data {
if (!hash)
return -ENOMEM;
+ mutex_lock(&nf_conntrack_mutex);
old_size = nf_conntrack_htable_size;
if (old_size == hashsize) {
+ mutex_unlock(&nf_conntrack_mutex);
kvfree(hash);
return 0;
}
for (i = 0; i < nf_conntrack_htable_size; i++) {
while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
+ unsigned int zone_id;
+
h = hlist_nulls_entry(nf_conntrack_hash[i].first,
struct nf_conntrack_tuple_hash, hnnode);
ct = nf_ct_tuplehash_to_ctrack(h);
hlist_nulls_del_rcu(&h->hnnode);
+
+ zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h));
bucket = __hash_conntrack(nf_ct_net(ct),
- &h->tuple, hashsize);
+ &h->tuple, zone_id, hashsize);
hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
nf_conntrack_all_unlock();
local_bh_enable();
+ mutex_unlock(&nf_conntrack_mutex);
+
synchronize_net();
kvfree(old_hash);
return 0;
/* We keep an extra hash for each conntrack, for fast searching. */
static unsigned int
-hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct net *net,
+ const struct nf_conntrack_zone *zone,
+ const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
struct {
struct nf_conntrack_man src;
u32 net_mix;
u32 protonum;
+ u32 zone;
} __aligned(SIPHASH_ALIGNMENT) combined;
get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
/* Original src, to ensure we map it consistently if poss. */
combined.src = tuple->src;
- combined.net_mix = net_hash_mix(n);
+ combined.net_mix = net_hash_mix(net);
combined.protonum = tuple->dst.protonum;
+ /* Zone ID can be used provided its valid for both directions */
+ if (zone->dir == NF_CT_DEFAULT_ZONE_DIR)
+ combined.zone = zone->id;
+
hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd);
return reciprocal_scale(hash, nf_nat_htable_size);
struct nf_conntrack_tuple *result,
const struct nf_nat_range2 *range)
{
- unsigned int h = hash_by_src(net, tuple);
+ unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn *ct;
hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) {
unsigned int srchash;
spinlock_t *lock;
- srchash = hash_by_src(net,
+ srchash = hash_by_src(net, nf_ct_zone(ct),
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS];
spin_lock_bh(lock);
{
unsigned int h;
- h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
hlist_del_rcu(&ct->nat_bysource);
spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
#include <net/netfilter/nf_nat_masquerade.h>
+struct masq_dev_work {
+ struct work_struct work;
+ struct net *net;
+ union nf_inet_addr addr;
+ int ifindex;
+ int (*iter)(struct nf_conn *i, void *data);
+};
+
+#define MAX_MASQ_WORKER_COUNT 16
+
static DEFINE_MUTEX(masq_mutex);
static unsigned int masq_refcnt __read_mostly;
+static atomic_t masq_worker_count __read_mostly;
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
-static int device_cmp(struct nf_conn *i, void *ifindex)
+static void iterate_cleanup_work(struct work_struct *work)
+{
+ struct masq_dev_work *w;
+
+ w = container_of(work, struct masq_dev_work, work);
+
+ nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0);
+
+ put_net(w->net);
+ kfree(w);
+ atomic_dec(&masq_worker_count);
+ module_put(THIS_MODULE);
+}
+
+/* Iterate conntrack table in the background and remove conntrack entries
+ * that use the device/address being removed.
+ *
+ * In case too many work items have been queued already or memory allocation
+ * fails iteration is skipped, conntrack entries will time out eventually.
+ */
+static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr,
+ int ifindex,
+ int (*iter)(struct nf_conn *i, void *data),
+ gfp_t gfp_flags)
+{
+ struct masq_dev_work *w;
+
+ if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT)
+ return;
+
+ net = maybe_get_net(net);
+ if (!net)
+ return;
+
+ if (!try_module_get(THIS_MODULE))
+ goto err_module;
+
+ w = kzalloc(sizeof(*w), gfp_flags);
+ if (w) {
+ /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */
+ atomic_inc(&masq_worker_count);
+
+ INIT_WORK(&w->work, iterate_cleanup_work);
+ w->ifindex = ifindex;
+ w->net = net;
+ w->iter = iter;
+ if (addr)
+ w->addr = *addr;
+ schedule_work(&w->work);
+ return;
+ }
+
+ module_put(THIS_MODULE);
+ err_module:
+ put_net(net);
+}
+
+static int device_cmp(struct nf_conn *i, void *arg)
{
const struct nf_conn_nat *nat = nfct_nat(i);
+ const struct masq_dev_work *w = arg;
if (!nat)
return 0;
- return nat->masq_index == (int)(long)ifindex;
+ return nat->masq_index == w->ifindex;
}
static int masq_device_event(struct notifier_block *this,
* and forget them.
*/
- nf_ct_iterate_cleanup_net(net, device_cmp,
- (void *)(long)dev->ifindex, 0, 0);
+ nf_nat_masq_schedule(net, NULL, dev->ifindex,
+ device_cmp, GFP_KERNEL);
}
return NOTIFY_DONE;
static int inet_cmp(struct nf_conn *ct, void *ptr)
{
- struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
- struct net_device *dev = ifa->ifa_dev->dev;
struct nf_conntrack_tuple *tuple;
+ struct masq_dev_work *w = ptr;
- if (!device_cmp(ct, (void *)(long)dev->ifindex))
+ if (!device_cmp(ct, ptr))
return 0;
tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
- return ifa->ifa_address == tuple->dst.u3.ip;
+ return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3);
}
static int masq_inet_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
- struct net *net = dev_net(idev->dev);
+ const struct in_ifaddr *ifa = ptr;
+ const struct in_device *idev;
+ const struct net_device *dev;
+ union nf_inet_addr addr;
+
+ if (event != NETDEV_DOWN)
+ return NOTIFY_DONE;
/* The masq_dev_notifier will catch the case of the device going
* down. So if the inetdev is dead and being destroyed we have
* no work to do. Otherwise this is an individual address removal
* and we have to perform the flush.
*/
+ idev = ifa->ifa_dev;
if (idev->dead)
return NOTIFY_DONE;
- if (event == NETDEV_DOWN)
- nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0);
+ memset(&addr, 0, sizeof(addr));
+
+ addr.ip = ifa->ifa_address;
+
+ dev = idev->dev;
+ nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex,
+ inet_cmp, GFP_KERNEL);
return NOTIFY_DONE;
}
};
#if IS_ENABLED(CONFIG_IPV6)
-static atomic_t v6_worker_count __read_mostly;
-
static int
nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev,
const struct in6_addr *daddr, unsigned int srcprefs,
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6);
-struct masq_dev_work {
- struct work_struct work;
- struct net *net;
- struct in6_addr addr;
- int ifindex;
-};
-
-static int inet6_cmp(struct nf_conn *ct, void *work)
-{
- struct masq_dev_work *w = (struct masq_dev_work *)work;
- struct nf_conntrack_tuple *tuple;
-
- if (!device_cmp(ct, (void *)(long)w->ifindex))
- return 0;
-
- tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-
- return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6);
-}
-
-static void iterate_cleanup_work(struct work_struct *work)
-{
- struct masq_dev_work *w;
-
- w = container_of(work, struct masq_dev_work, work);
-
- nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0);
-
- put_net(w->net);
- kfree(w);
- atomic_dec(&v6_worker_count);
- module_put(THIS_MODULE);
-}
-
/* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep).
*
* Defer it to the system workqueue.
{
struct inet6_ifaddr *ifa = ptr;
const struct net_device *dev;
- struct masq_dev_work *w;
- struct net *net;
+ union nf_inet_addr addr;
- if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16)
+ if (event != NETDEV_DOWN)
return NOTIFY_DONE;
dev = ifa->idev->dev;
- net = maybe_get_net(dev_net(dev));
- if (!net)
- return NOTIFY_DONE;
- if (!try_module_get(THIS_MODULE))
- goto err_module;
+ memset(&addr, 0, sizeof(addr));
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (w) {
- atomic_inc(&v6_worker_count);
-
- INIT_WORK(&w->work, iterate_cleanup_work);
- w->ifindex = dev->ifindex;
- w->net = net;
- w->addr = ifa->addr;
- schedule_work(&w->work);
+ addr.in6 = ifa->addr;
- return NOTIFY_DONE;
- }
-
- module_put(THIS_MODULE);
- err_module:
- put_net(net);
+ nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp,
+ GFP_ATOMIC);
return NOTIFY_DONE;
}
if (ops->privsize != NULL)
size = ops->privsize(nla, &desc);
alloc_size = sizeof(*set) + size + udlen;
- if (alloc_size < size)
+ if (alloc_size < size || alloc_size > INT_MAX)
return -ENOMEM;
set = kvzalloc(alloc_size, GFP_KERNEL);
if (!set)
table->use--;
nf_tables_chain_destroy(&ctx);
}
- list_del(&table->list);
nf_tables_table_destroy(&ctx);
}
if (nft_table_has_owner(table))
continue;
+ list_del(&table->list);
+
__nft_release_table(net, table);
}
}
static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
+ struct nft_table *table, *to_delete[8];
struct nftables_pernet *nft_net;
struct netlink_notify *n = ptr;
- struct nft_table *table, *nt;
struct net *net = n->net;
- bool release = false;
+ unsigned int deleted;
+ bool restart = false;
if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER)
return NOTIFY_DONE;
nft_net = nft_pernet(net);
+ deleted = 0;
mutex_lock(&nft_net->commit_mutex);
+again:
list_for_each_entry(table, &nft_net->tables, list) {
if (nft_table_has_owner(table) &&
n->portid == table->nlpid) {
__nft_release_hook(net, table);
- release = true;
+ list_del_rcu(&table->list);
+ to_delete[deleted++] = table;
+ if (deleted >= ARRAY_SIZE(to_delete))
+ break;
}
}
- if (release) {
+ if (deleted) {
+ restart = deleted >= ARRAY_SIZE(to_delete);
synchronize_rcu();
- list_for_each_entry_safe(table, nt, &nft_net->tables, list) {
- if (nft_table_has_owner(table) &&
- n->portid == table->nlpid)
- __nft_release_table(net, table);
- }
+ while (deleted)
+ __nft_release_table(net, to_delete[--deleted]);
+
+ if (restart)
+ goto again;
}
mutex_unlock(&nft_net->commit_mutex);
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_log.h>
/* Used for matches where *info is larger than X byte */
#define NFT_MATCH_LARGE_THRESH 192
nft_compat_wait_for_destructors();
ret = xt_check_target(&par, size, proto, inv);
- if (ret < 0)
+ if (ret < 0) {
+ if (ret == -ENOENT) {
+ const char *modname = NULL;
+
+ if (strcmp(target->name, "LOG") == 0)
+ modname = "nf_log_syslog";
+ else if (strcmp(target->name, "NFLOG") == 0)
+ modname = "nfnetlink_log";
+
+ if (modname &&
+ nft_request_module(ctx->net, "%s", modname) == -EAGAIN)
+ return -EAGAIN;
+ }
+
return ret;
+ }
/* The standard target cannot be used */
if (!target->target)
static int log_tg_check(const struct xt_tgchk_param *par)
{
const struct xt_log_info *loginfo = par->targinfo;
+ int ret;
if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6)
return -EINVAL;
return -EINVAL;
}
- return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ if (ret != 0 && !par->nft_compat) {
+ request_module("%s", "nf_log_syslog");
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG);
+ }
+
+ return ret;
}
static void log_tg_destroy(const struct xt_tgdtor_param *par)
static int nflog_tg_check(const struct xt_tgchk_param *par)
{
const struct xt_nflog_info *info = par->targinfo;
+ int ret;
if (info->flags & ~XT_NFLOG_MASK)
return -EINVAL;
if (info->prefix[sizeof(info->prefix) - 1] != '\0')
return -EINVAL;
- return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ if (ret != 0 && !par->nft_compat) {
+ request_module("%s", "nfnetlink_log");
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ }
+
+ return ret;
}
static void nflog_tg_destroy(const struct xt_tgdtor_param *par)
arg->count = arg->skip;
+ rcu_read_lock();
idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) {
/* don't return filters that are being deleted */
if (!refcount_inc_not_zero(&f->refcnt))
continue;
+ rcu_read_unlock();
+
if (arg->fn(tp, f, arg) < 0) {
__fl_put(f);
arg->stop = 1;
+ rcu_read_lock();
break;
}
__fl_put(f);
arg->count++;
+ rcu_read_lock();
}
+ rcu_read_unlock();
arg->cookie = id;
}
return stab;
}
+ if (s->size_log > STAB_SIZE_LOG_MAX ||
+ s->cell_log > STAB_SIZE_LOG_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table");
+ return ERR_PTR(-EINVAL);
+ }
+
stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL);
if (!stab)
return ERR_PTR(-ENOMEM);
ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch);
/* Break out if chunk length is less then minimal. */
- if (ntohs(ch->length) < sizeof(_ch))
+ if (!ch || ntohs(ch->length) < sizeof(_ch))
break;
ch_end = offset + SCTP_PAD4(ntohs(ch->length));
static void init_peercred(struct sock *sk)
{
- put_pid(sk->sk_peer_pid);
- if (sk->sk_peer_cred)
- put_cred(sk->sk_peer_cred);
+ const struct cred *old_cred;
+ struct pid *old_pid;
+
+ spin_lock(&sk->sk_peer_lock);
+ old_pid = sk->sk_peer_pid;
+ old_cred = sk->sk_peer_cred;
sk->sk_peer_pid = get_pid(task_tgid(current));
sk->sk_peer_cred = get_current_cred();
+ spin_unlock(&sk->sk_peer_lock);
+
+ put_pid(old_pid);
+ put_cred(old_cred);
}
static void copy_peercred(struct sock *sk, struct sock *peersk)
{
- put_pid(sk->sk_peer_pid);
- if (sk->sk_peer_cred)
- put_cred(sk->sk_peer_cred);
+ const struct cred *old_cred;
+ struct pid *old_pid;
+
+ if (sk < peersk) {
+ spin_lock(&sk->sk_peer_lock);
+ spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+ } else {
+ spin_lock(&peersk->sk_peer_lock);
+ spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+ }
+ old_pid = sk->sk_peer_pid;
+ old_cred = sk->sk_peer_cred;
sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
+
+ spin_unlock(&sk->sk_peer_lock);
+ spin_unlock(&peersk->sk_peer_lock);
+
+ put_pid(old_pid);
+ put_cred(old_cred);
}
static int unix_listen(struct socket *sock, int backlog)
static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type)
{
- struct sock *sk = NULL;
struct unix_sock *u;
+ struct sock *sk;
+ int err;
atomic_long_inc(&unix_nr_socks);
- if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
- goto out;
+ if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) {
+ err = -ENFILE;
+ goto err;
+ }
if (type == SOCK_STREAM)
sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
else /*dgram and seqpacket */
sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
- if (!sk)
- goto out;
+ if (!sk) {
+ err = -ENOMEM;
+ goto err;
+ }
sock_init_data(sock, sk);
init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
memset(&u->scm_stat, 0, sizeof(struct scm_stat));
unix_insert_socket(unix_sockets_unbound(sk), sk);
-out:
- if (sk == NULL)
- atomic_long_dec(&unix_nr_socks);
- else {
- local_bh_disable();
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
- local_bh_enable();
- }
+
+ local_bh_disable();
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ local_bh_enable();
+
return sk;
+
+err:
+ atomic_long_dec(&unix_nr_socks);
+ return ERR_PTR(err);
}
static int unix_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
+ struct sock *sk;
+
if (protocol && protocol != PF_UNIX)
return -EPROTONOSUPPORT;
return -ESOCKTNOSUPPORT;
}
- return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM;
+ sk = unix_create1(net, sock, kern, sock->type);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ return 0;
}
static int unix_release(struct socket *sock)
we will have to recheck all again in any case.
*/
- err = -ENOMEM;
-
/* create new sock for complete connection */
newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
- if (newsk == NULL)
+ if (IS_ERR(newsk)) {
+ err = PTR_ERR(newsk);
+ newsk = NULL;
goto out;
+ }
+
+ err = -ENOMEM;
/* Allocate skb for sending to listening sock */
skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
return -EINVAL;
}
}
+ case SNDRV_RAWMIDI_IOCTL_USER_PVERSION:
+ if (get_user(rfile->user_pversion, (unsigned int __user *)arg))
+ return -EFAULT;
+ return 0;
+
case SNDRV_RAWMIDI_IOCTL_PARAMS:
{
struct snd_rawmidi_params params;
if (copy_from_user(¶ms, argp, sizeof(struct snd_rawmidi_params)))
return -EFAULT;
+ if (rfile->user_pversion < SNDRV_PROTOCOL_VERSION(2, 0, 2)) {
+ params.mode = 0;
+ memset(params.reserved, 0, sizeof(params.reserved));
+ }
switch (params.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
if (rfile->output == NULL)
if (pointer_update)
pcsp_pointer_update(chip);
- hrtimer_forward(handle, hrtimer_get_expires(handle), ns_to_ktime(ns));
+ hrtimer_forward_now(handle, ns_to_ktime(ns));
return HRTIMER_RESTART;
}
/* This is just for v2/v3 protocol. */
for (i = 0; i < data_blocks; ++i) {
- *frames = (be32_to_cpu(buffer[1]) << 16) |
- (be32_to_cpu(buffer[2]) >> 16);
+ *frames = be32_to_cpu(buffer[1]);
+ *frames <<= 16;
+ *frames |= be32_to_cpu(buffer[2]) >> 16;
+ ++frames;
buffer += data_block_quadlets;
- frames++;
}
}
model = val;
}
- /*
- * Mackie Onyx Satellite with base station has a quirk to report a wrong
- * value in 'dbs' field of CIP header against its format information.
- */
- if (vendor == VENDOR_LOUD && model == MODEL_SATELLITE)
+ if (vendor == VENDOR_LOUD) {
+ // Mackie Onyx Satellite with base station has a quirk to report a wrong
+ // value in 'dbs' field of CIP header against its format information.
oxfw->quirks |= SND_OXFW_QUIRK_WRONG_DBS;
+ // OXFW971-based models may transfer events by blocking method.
+ if (!(oxfw->quirks & SND_OXFW_QUIRK_JUMBO_PAYLOAD))
+ oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION;
+ }
+
return 0;
}
return azx_get_pos_posbuf(chip, azx_dev);
}
-static void azx_shutdown_chip(struct azx *chip)
+static void __azx_shutdown_chip(struct azx *chip, bool skip_link_reset)
{
azx_stop_chip(chip);
- azx_enter_link_reset(chip);
+ if (!skip_link_reset)
+ azx_enter_link_reset(chip);
azx_clear_irq_pending(chip);
display_power(chip, false);
}
static DEFINE_MUTEX(card_list_lock);
static LIST_HEAD(card_list);
+static void azx_shutdown_chip(struct azx *chip)
+{
+ __azx_shutdown_chip(chip, false);
+}
+
static void azx_add_card_list(struct azx *chip)
{
struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
return;
chip = card->private_data;
if (chip && chip->running)
- azx_shutdown_chip(chip);
+ __azx_shutdown_chip(chip, true);
}
/* PCI IDs */
snd_hda_jack_add_kctl(codec, DOLPHIN_LO_PIN_NID, "Line Out", true,
SND_JACK_HEADPHONE, NULL);
+ snd_hda_jack_add_kctl(codec, DOLPHIN_AMIC_PIN_NID, "Microphone", true,
+ SND_JACK_MICROPHONE, NULL);
+
cs8409_fix_caps(codec, DOLPHIN_HP_PIN_NID);
cs8409_fix_caps(codec, DOLPHIN_LO_PIN_NID);
cs8409_fix_caps(codec, DOLPHIN_AMIC_PIN_NID);
hda_fixup_thinkpad_acpi(codec, fix, action);
}
+/* Fixup for Lenovo Legion 15IMHg05 speaker output on headset removal. */
+static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ spec->gen.suppress_auto_mute = 1;
+ break;
+ }
+}
+
/* for alc295_fixup_hp_top_speakers */
#include "hp_x360_helper.c"
ALC623_FIXUP_LENOVO_THINKSTATION_P340,
ALC255_FIXUP_ACER_HEADPHONE_AND_MIC,
ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST,
+ ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS,
+ ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
+ ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
+ ALC287_FIXUP_13S_GEN2_SPEAKERS
};
static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
},
+ [ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS] = {
+ .type = HDA_FIXUP_VERBS,
+ //.v.verbs = legion_15imhg05_coefs,
+ .v.verbs = (const struct hda_verb[]) {
+ // set left speaker Legion 7i.
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x41 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xc },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x1a },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ // set right speaker Legion 7i.
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x42 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xc },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2a },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+ {}
+ },
+ .chained = true,
+ .chain_id = ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
+ },
+ [ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_legion_15imhg05_speakers,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE,
+ },
+ [ALC287_FIXUP_YOGA7_14ITL_SPEAKERS] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ // set left speaker Yoga 7i.
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x41 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xc },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x1a },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ // set right speaker Yoga 7i.
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x46 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xc },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2a },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+ {}
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE,
+ },
+ [ALC287_FIXUP_13S_GEN2_SPEAKERS] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x41 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x42 },
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x2 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x0 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 },
+ {}
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF),
SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP),
+ SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS),
+ SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
+ SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
+ SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
#define PCXHR_DSP 2
#if (PCXHR_DSP_OFFSET_MAX > PCXHR_PLX_OFFSET_MIN)
-#undef PCXHR_REG_TO_PORT(x)
+#error PCXHR_REG_TO_PORT(x)
#else
#define PCXHR_REG_TO_PORT(x) ((x)>PCXHR_DSP_OFFSET_MAX ? PCXHR_PLX : PCXHR_DSP)
#endif
if (ret < 0)
goto err_pm_get_sync;
+ /*
+ * Register platform component before registering cpu dai for there
+ * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+ */
+ ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret);
+ goto err_pm_get_sync;
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component,
&fsl_esai_dai, 1);
if (ret) {
INIT_WORK(&esai_priv->work, fsl_esai_hw_reset);
- ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE);
- if (ret) {
- dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret);
- goto err_pm_get_sync;
- }
-
return ret;
err_pm_get_sync:
pm_runtime_enable(&pdev->dev);
regcache_cache_only(micfil->regmap, true);
+ /*
+ * Register platform component before registering cpu dai for there
+ * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+ */
+ ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to pcm register\n");
+ return ret;
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_micfil_component,
&fsl_micfil_dai, 1);
if (ret) {
dev_err(&pdev->dev, "failed to register component %s\n",
fsl_micfil_component.name);
- return ret;
}
- ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
- if (ret)
- dev_err(&pdev->dev, "failed to pcm register\n");
-
return ret;
}
if (ret < 0)
goto err_pm_get_sync;
- ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
- &sai->cpu_dai_drv, 1);
- if (ret)
- goto err_pm_get_sync;
-
+ /*
+ * Register platform component before registering cpu dai for there
+ * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+ */
if (sai->soc_data->use_imx_pcm) {
ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
if (ret)
goto err_pm_get_sync;
}
+ ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
+ &sai->cpu_dai_drv, 1);
+ if (ret)
+ goto err_pm_get_sync;
+
return ret;
err_pm_get_sync:
pm_runtime_enable(&pdev->dev);
regcache_cache_only(spdif_priv->regmap, true);
- ret = devm_snd_soc_register_component(&pdev->dev, &fsl_spdif_component,
- &spdif_priv->cpu_dai_drv, 1);
+ /*
+ * Register platform component before registering cpu dai for there
+ * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+ */
+ ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE);
if (ret) {
- dev_err(&pdev->dev, "failed to register DAI: %d\n", ret);
+ dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n");
goto err_pm_disable;
}
- ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE);
+ ret = devm_snd_soc_register_component(&pdev->dev, &fsl_spdif_component,
+ &spdif_priv->cpu_dai_drv, 1);
if (ret) {
- dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n");
+ dev_err(&pdev->dev, "failed to register DAI: %d\n", ret);
goto err_pm_disable;
}
pm_runtime_enable(dev);
regcache_cache_only(xcvr->regmap, true);
+ /*
+ * Register platform component before registering cpu dai for there
+ * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+ */
+ ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0);
+ if (ret) {
+ dev_err(dev, "failed to pcm register\n");
+ return ret;
+ }
+
ret = devm_snd_soc_register_component(dev, &fsl_xcvr_comp,
&fsl_xcvr_dai, 1);
if (ret) {
dev_err(dev, "failed to register component %s\n",
fsl_xcvr_comp.name);
- return ret;
}
- ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0);
- if (ret)
- dev_err(dev, "failed to pcm register\n");
-
return ret;
}
cpus + *cpu_id, cpu_dai_num,
codecs, codec_num,
NULL, &sdw_ops);
+ /*
+ * SoundWire DAILINKs use 'stream' functions and Bank Switch operations
+ * based on wait_for_completion(), tag them as 'nonatomic'.
+ */
+ dai_links[*be_index].nonatomic = true;
ret = set_codec_init_func(card, link, dai_links + (*be_index)++,
playback, group_id);
# SPDX-License-Identifier: GPL-2.0-only
config SND_SOC_MEDIATEK
tristate
+ select REGMAP_MMIO
config SND_SOC_MT2701
tristate "ASoC support for Mediatek MT2701 chip"
config SND_SOC_MT8195
tristate "ASoC support for Mediatek MT8195 chip"
depends on ARCH_MEDIATEK || COMPILE_TEST
+ depends on COMMON_CLK
select SND_SOC_MEDIATEK
+ select MFD_SYSCON if SND_SOC_MT6359
help
This adds ASoC platform driver support for Mediatek MT8195 chip
that can be used with other codecs.
devm_kcalloc(dev, afe->reg_back_up_list_num,
sizeof(unsigned int), GFP_KERNEL);
- for (i = 0; i < afe->reg_back_up_list_num; i++)
- regmap_read(regmap, afe->reg_back_up_list[i],
- &afe->reg_back_up[i]);
+ if (afe->reg_back_up) {
+ for (i = 0; i < afe->reg_back_up_list_num; i++)
+ regmap_read(regmap, afe->reg_back_up_list[i],
+ &afe->reg_back_up[i]);
+ }
afe->suspended = true;
afe->runtime_suspend(dev);
afe->runtime_resume(dev);
- if (!afe->reg_back_up)
+ if (!afe->reg_back_up) {
dev_dbg(dev, "%s no reg_backup\n", __func__);
-
- for (i = 0; i < afe->reg_back_up_list_num; i++)
- mtk_regmap_write(regmap, afe->reg_back_up_list[i],
- afe->reg_back_up[i]);
+ } else {
+ for (i = 0; i < afe->reg_back_up_list_num; i++)
+ mtk_regmap_write(regmap, afe->reg_back_up_list[i],
+ afe->reg_back_up[i]);
+ }
afe->suspended = false;
return 0;
return snd_soc_component_set_jack(cmpnt_codec, &priv->hdmi_jack, NULL);
}
-static int mt8195_hdmitx_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
- struct snd_pcm_hw_params *params)
+static int mt8195_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
+ struct snd_pcm_hw_params *params)
{
/* fix BE i2s format to 32bit, clean param mask first */
.no_pcm = 1,
.dpcm_playback = 1,
.ops = &mt8195_dptx_ops,
- .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup,
+ .be_hw_params_fixup = mt8195_dptx_hw_params_fixup,
SND_SOC_DAILINK_REG(DPTX_BE),
},
[DAI_LINK_ETDM1_IN_BE] = {
SND_SOC_DAIFMT_NB_NF |
SND_SOC_DAIFMT_CBS_CFS,
.dpcm_playback = 1,
- .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup,
SND_SOC_DAILINK_REG(ETDM3_OUT_BE),
},
[DAI_LINK_PCM1_BE] = {
dev_warn(dev, "error: %d failed to prepare DSP for device removal",
ret);
- snd_sof_fw_unload(sdev);
snd_sof_ipc_free(sdev);
snd_sof_free_debug(sdev);
snd_sof_free_trace(sdev);
snd_sof_remove(sdev);
/* release firmware */
- release_firmware(pdata->fw);
- pdata->fw = NULL;
+ snd_sof_fw_unload(sdev);
return 0;
}
/* on i.MX8 there is 1 to 1 match between type and BAR idx */
static int imx8_get_bar_index(struct snd_sof_dev *sdev, u32 type)
{
- return type;
+ /* Only IRAM and SRAM bars are valid */
+ switch (type) {
+ case SOF_FW_BLK_TYPE_IRAM:
+ case SOF_FW_BLK_TYPE_SRAM:
+ return type;
+ default:
+ return -EINVAL;
+ }
}
static void imx8_ipc_msg_data(struct snd_sof_dev *sdev,
/* on i.MX8 there is 1 to 1 match between type and BAR idx */
static int imx8m_get_bar_index(struct snd_sof_dev *sdev, u32 type)
{
- return type;
+ /* Only IRAM and SRAM bars are valid */
+ switch (type) {
+ case SOF_FW_BLK_TYPE_IRAM:
+ case SOF_FW_BLK_TYPE_SRAM:
+ return type;
+ default:
+ return -EINVAL;
+ }
}
static void imx8m_ipc_msg_data(struct snd_sof_dev *sdev,
ret = request_firmware(&plat_data->fw, fw_filename, sdev->dev);
if (ret < 0) {
- dev_err(sdev->dev, "error: request firmware %s failed err: %d\n",
- fw_filename, ret);
dev_err(sdev->dev,
- "you may need to download the firmware from https://github.com/thesofproject/sof-bin/\n");
+ "error: sof firmware file is missing, you might need to\n");
+ dev_err(sdev->dev,
+ " download it from https://github.com/thesofproject/sof-bin/\n");
goto err;
} else {
dev_dbg(sdev->dev, "request_firmware %s successful\n",
void snd_sof_fw_unload(struct snd_sof_dev *sdev)
{
/* TODO: support module unloading at runtime */
+ release_firmware(sdev->pdata->fw);
+ sdev->pdata->fw = NULL;
}
EXPORT_SYMBOL(snd_sof_fw_unload);
return;
if (sdev->dtrace_is_enabled) {
- dev_err(sdev->dev, "error: waking up any trace sleepers\n");
sdev->dtrace_error = true;
wake_up(&sdev->trace_sleep);
}
* 0x0049fbb0: 8000f2d0 0049fc00 6f6c6c61 00632e63
*/
for (i = 0; i < stack_words; i += 4) {
- hex_dump_to_buffer(stack + i * 4, 16, 16, 4,
+ hex_dump_to_buffer(stack + i, 16, 16, 4,
buf, sizeof(buf), false);
- dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i, buf);
+ dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i * 4, buf);
}
}
return 0;
}
-static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
+static int usb_audio_resume(struct usb_interface *intf)
{
struct snd_usb_audio *chip = usb_get_intfdata(intf);
struct snd_usb_stream *as;
* we just notify and restart the mixers
*/
list_for_each_entry(mixer, &chip->mixer_list, list) {
- err = snd_usb_mixer_resume(mixer, reset_resume);
+ err = snd_usb_mixer_resume(mixer);
if (err < 0)
goto err_out;
}
atomic_dec(&chip->active); /* allow autopm after this point */
return err;
}
-
-static int usb_audio_resume(struct usb_interface *intf)
-{
- return __usb_audio_resume(intf, false);
-}
-
-static int usb_audio_reset_resume(struct usb_interface *intf)
-{
- return __usb_audio_resume(intf, true);
-}
#else
#define usb_audio_suspend NULL
#define usb_audio_resume NULL
-#define usb_audio_reset_resume NULL
+#define usb_audio_resume NULL
#endif /* CONFIG_PM */
static const struct usb_device_id usb_audio_ids [] = {
.disconnect = usb_audio_disconnect,
.suspend = usb_audio_suspend,
.resume = usb_audio_resume,
- .reset_resume = usb_audio_reset_resume,
+ .reset_resume = usb_audio_resume,
.id_table = usb_audio_ids,
.supports_autosuspend = 1,
};
return 0;
}
-static int default_mixer_reset_resume(struct usb_mixer_elem_list *list)
-{
- int err;
-
- if (list->resume) {
- err = list->resume(list);
- if (err < 0)
- return err;
- }
- return restore_mixer_value(list);
-}
-
-int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume)
+int snd_usb_mixer_resume(struct usb_mixer_interface *mixer)
{
struct usb_mixer_elem_list *list;
- usb_mixer_elem_resume_func_t f;
int id, err;
/* restore cached mixer values */
for (id = 0; id < MAX_ID_ELEMS; id++) {
for_each_mixer_elem(list, mixer, id) {
- if (reset_resume)
- f = list->reset_resume;
- else
- f = list->resume;
- if (f) {
- err = f(list);
+ if (list->resume) {
+ err = list->resume(list);
if (err < 0)
return err;
}
list->id = unitid;
list->dump = snd_usb_mixer_dump_cval;
#ifdef CONFIG_PM
- list->resume = NULL;
- list->reset_resume = default_mixer_reset_resume;
+ list->resume = restore_mixer_value;
#endif
}
bool is_std_info;
usb_mixer_elem_dump_func_t dump;
usb_mixer_elem_resume_func_t resume;
- usb_mixer_elem_resume_func_t reset_resume;
};
/* iterate over mixer element list of the given unit id */
#ifdef CONFIG_PM
int snd_usb_mixer_suspend(struct usb_mixer_interface *mixer);
-int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume);
+int snd_usb_mixer_resume(struct usb_mixer_interface *mixer);
#endif
int snd_usb_set_cur_mix_value(struct usb_mixer_elem_info *cval, int channel,
*listp = list;
list->mixer = mixer;
list->id = id;
- list->reset_resume = resume;
+ list->resume = resume;
kctl = snd_ctl_new1(knew, list);
if (!kctl) {
kfree(list);
static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name,
int *out_btf_sec_id, int *out_btf_id)
{
- int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0;
+ int i, j, n, m, btf_id = 0;
const struct btf_type *t;
const struct btf_var_secinfo *vi;
const char *name;
+ if (!obj->btf) {
+ pr_warn("failed to find BTF info for object '%s'\n", obj->filename);
+ return -EINVAL;
+ }
+
+ n = btf__get_nr_types(obj->btf);
for (i = 1; i <= n; i++) {
t = btf__type_by_id(obj->btf, i);
The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html
-The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
+The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information.
User can specify how to sort offsets for cacheline.
Following fields are available and governs the final
-output fields set for caheline offsets output:
+output fields set for cacheline offsets output:
tid - coalesced by process TIDs
pid - coalesced by process PIDs
"Transactions" events correspond to the start or end of transactions. The
'flags' field can be used in perf script to determine whether the event is a
-tranasaction start, commit or abort.
+transaction start, commit or abort.
Note that "instructions", "branches" and "transactions" events depend on code
flow packets which can be disabled by using the config term "branch=0". Refer
-f::
--force::
- Don't complan, do it.
+ Don't complain, do it.
REPORT OPTIONS
--------------
Traces meant to be processed using a script should be recorded with
the above option: -a to enable system-wide collection.
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
----
Traces meant to be processed using a script should be recorded with
the above option: -a to enable system-wide collection.
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
----
Print metrics or metricgroups specified in a comma separated list.
For a group all metrics from the group are added.
The events from the metrics are automatically measured.
-See perf list output for the possble metrics and metricgroups.
+See perf list output for the possible metrics and metricgroups.
-A::
--no-aggr::
-----------------------------------
Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
-methology to break down CPU pipeline execution into 4 bottlenecks:
+methodology to break down CPU pipeline execution into 4 bottlenecks:
frontend bound, backend bound, bad speculation, retiring.
For more details on Topdown see [1][5]
#include <linux/coresight-pmu.h>
#include <linux/zalloc.h>
-#include "../../util/auxtrace.h"
-#include "../../util/debug.h"
-#include "../../util/evlist.h"
-#include "../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/debug.h"
+#include "../../../util/evlist.h"
+#include "../../../util/pmu.h"
#include "cs-etm.h"
#include "arm-spe.h"
#include <linux/zalloc.h>
#include "cs-etm.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/auxtrace.h"
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/perf_api_probe.h"
-#include "../../util/evsel_config.h"
-#include "../../util/pmu.h"
-#include "../../util/cs-etm.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/perf_api_probe.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/pmu.h"
+#include "../../../util/cs-etm.h"
#include <internal/lib.h> // page_size
-#include "../../util/session.h"
+#include "../../../util/session.h"
#include <errno.h>
#include <stdlib.h>
// SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
#include <linux/string.h>
#include "arm-spe.h"
-#include "../../util/pmu.h"
+#include "../../../util/pmu.h"
struct perf_event_attr
*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
// SPDX-License-Identifier: GPL-2.0
#include <elfutils/libdwfl.h>
-#include "../../util/unwind-libdw.h"
-#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../../util/unwind-libdw.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/event.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
#include <errno.h>
#include <libunwind.h>
#include "perf_regs.h"
-#include "../../util/unwind.h"
-#include "../../util/debug.h"
+#include "../../../util/unwind.h"
+#include "../../../util/debug.h"
int libunwind__arch_reg_id(int regnum)
{
u8 die = ((struct iio_root_port *)evsel->priv)->die;
struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
- if (count->run && count->ena) {
+ if (count && count->run && count->ena) {
if (evsel->prev_raw_counts && !out->force_header) {
struct perf_counts_values *prev_count =
perf_counts(evsel->prev_raw_counts, die, 0);
goto out;
} else if (verbose)
iostat_list(evsel_list, &stat_config);
+ if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target))
+ target.system_wide = true;
}
if (add_default_attributes())
{
"EventCode": "0x4e010",
"EventName": "PM_GCT_NOSLOT_IC_L3MISS",
- "BriefDescription": "Gct empty for this thread due to icach l3 miss",
+ "BriefDescription": "Gct empty for this thread due to icache l3 miss",
"PublicDescription": ""
},
{
struct thread *thread, struct state *state)
{
struct addr_location al;
- unsigned char buf1[BUFSZ];
- unsigned char buf2[BUFSZ];
+ unsigned char buf1[BUFSZ] = {0};
+ unsigned char buf2[BUFSZ] = {0};
size_t ret_len;
u64 objdump_addr;
const char *objdump_name;
/* For bsearch. We try to unwind functions in shared object. */
#include <stdlib.h>
+/*
+ * The test will assert frames are on the stack but tail call optimizations lose
+ * the frame of the caller. Clang can disable this optimization on a called
+ * function but GCC currently (11/2020) lacks this attribute. The barrier is
+ * used to inhibit tail calls in these cases.
+ */
+#ifdef __has_attribute
+#if __has_attribute(disable_tail_calls)
+#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls))
+#define NO_TAIL_CALL_BARRIER
+#endif
+#endif
+#ifndef NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory");
+#endif
+
static int mmap_handler(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
return strcmp((const char *) symbol, funcs[idx]);
}
-noinline int test_dwarf_unwind__thread(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread)
{
struct perf_sample sample;
unsigned long cnt = 0;
static int global_unwind_retval = -INT_MAX;
-noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2)
{
/* Any possible value should be 'thread' */
struct thread *thread = *(struct thread **)p1;
return p1 - p2;
}
-noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread)
{
struct thread *array[2] = {thread, thread};
void *fp = &bsearch;
return global_unwind_retval;
}
-noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread)
{
- return test_dwarf_unwind__krava_3(thread);
+ int ret;
+
+ ret = test_dwarf_unwind__krava_3(thread);
+ NO_TAIL_CALL_BARRIER;
+ return ret;
}
-noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread)
{
- return test_dwarf_unwind__krava_2(thread);
+ int ret;
+
+ ret = test_dwarf_unwind__krava_2(thread);
+ NO_TAIL_CALL_BARRIER;
+ return ret;
}
int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
section->name, item->name);
ret = fn(key, value, data);
if (ret < 0) {
- pr_err("Error: wrong config key-value pair %s=%s\n",
+ pr_err("Error in the given config file: wrong config key-value pair %s=%s\n",
key, value);
/*
* Can't be just a 'break', as perf_config_set__for_each_entry()
$(TRUNNER_BPF_PROGS_DIR)/%.c \
$(TRUNNER_BPF_PROGS_DIR)/*.h \
$$(INCLUDE_DIR)/vmlinux.h \
- $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT)
+ $(wildcard $(BPFDIR)/bpf_*.h) \
+ | $(TRUNNER_OUTPUT) $$(BPFOBJ)
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
$(TRUNNER_BPF_CFLAGS))
ip netns add "${NS2}"
ip netns add "${NS3}"
+ # rp_filter gets confused by what these tests are doing, so disable it
+ ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
+ ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
+ ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
+ ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0
+ ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0
+ ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0
+
ip link add veth1 type veth peer name veth2
ip link add veth3 type veth peer name veth4
ip link add veth5 type veth peer name veth6
ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF}
ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF}
- # rp_filter gets confused by what these tests are doing, so disable it
- ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
-
TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX)
sleep 1 # reduce flakiness
/x86_64/smm_test
/x86_64/state_test
/x86_64/svm_vmcall_test
+/x86_64/svm_int_ctl_test
/x86_64/sync_regs_test
/x86_64/tsc_msrs_test
/x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
printf(" -v: specify the number of vCPUs to run.\n");
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
" them into a separate region of memory for each vCPU.\n");
- printf(" -s: specify the type of memory that should be used to\n"
- " back the guest data region.\n\n");
- backing_src_help();
+ backing_src_help("-s");
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
struct test_params params = {
- .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .backing_src = DEFAULT_VM_MEM_SRC,
.vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
.vcpus = 1,
};
return NULL;
}
- if (!pollfd[0].revents & POLLIN)
+ if (!(pollfd[0].revents & POLLIN))
continue;
r = read(uffd, &msg, sizeof(msg));
{
puts("");
printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
- " [-b memory] [-t type] [-v vcpus] [-o]\n", name);
+ " [-b memory] [-s type] [-v vcpus] [-o]\n", name);
guest_modes_help();
printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
" UFFD registration mode: 'MISSING' or 'MINOR'.\n");
printf(" -b: specify the size of the memory region which should be\n"
" demand paged by each vCPU. e.g. 10M or 3G.\n"
" Default: 1G\n");
- printf(" -t: The type of backing memory to use. Default: anonymous\n");
- backing_src_help();
+ backing_src_help("-s");
printf(" -v: specify the number of vCPUs to run.\n");
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
" them into a separate region of memory for each vCPU.\n");
{
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
struct test_params p = {
- .src_type = VM_MEM_SRC_ANONYMOUS,
+ .src_type = DEFAULT_VM_MEM_SRC,
.partition_vcpu_memory_access = true,
};
int opt;
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) {
+ while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) {
switch (opt) {
case 'm':
guest_modes_cmdline(optarg);
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
- case 't':
+ case 's':
p.src_type = parse_backing_src_type(optarg);
break;
case 'v':
if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR &&
!backing_src_is_shared(p.src_type)) {
- TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t");
+ TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s");
}
for_each_guest_mode(run_test, &p);
toggle_dirty_logging(vm, slots, false);
}
-static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
- uint64_t nr_pages)
+static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots)
{
- uint64_t slot_pages = nr_pages / slots;
int i;
for (i = 0; i < slots; i++) {
int slot = PERF_TEST_MEM_SLOT_INDEX + i;
- unsigned long *slot_bitmap = bitmap + i * slot_pages;
- kvm_vm_get_dirty_log(vm, slot, slot_bitmap);
+ kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
}
}
-static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
- uint64_t nr_pages)
+static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
+ int slots, uint64_t pages_per_slot)
{
- uint64_t slot_pages = nr_pages / slots;
int i;
for (i = 0; i < slots; i++) {
int slot = PERF_TEST_MEM_SLOT_INDEX + i;
- unsigned long *slot_bitmap = bitmap + i * slot_pages;
- kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages);
+ kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
}
}
+static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot)
+{
+ unsigned long **bitmaps;
+ int i;
+
+ bitmaps = malloc(slots * sizeof(bitmaps[0]));
+ TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array.");
+
+ for (i = 0; i < slots; i++) {
+ bitmaps[i] = bitmap_zalloc(pages_per_slot);
+ TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap.");
+ }
+
+ return bitmaps;
+}
+
+static void free_bitmaps(unsigned long *bitmaps[], int slots)
+{
+ int i;
+
+ for (i = 0; i < slots; i++)
+ free(bitmaps[i]);
+
+ free(bitmaps);
+}
+
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *p = arg;
pthread_t *vcpu_threads;
struct kvm_vm *vm;
- unsigned long *bmap;
+ unsigned long **bitmaps;
uint64_t guest_num_pages;
uint64_t host_num_pages;
+ uint64_t pages_per_slot;
int vcpu_id;
struct timespec start;
struct timespec ts_diff;
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
- bmap = bitmap_zalloc(host_num_pages);
+ pages_per_slot = host_num_pages / p->slots;
+
+ bitmaps = alloc_bitmaps(p->slots, pages_per_slot);
if (dirty_log_manual_caps) {
cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
clock_gettime(CLOCK_MONOTONIC, &start);
- get_dirty_log(vm, p->slots, bmap, host_num_pages);
+ get_dirty_log(vm, bitmaps, p->slots);
ts_diff = timespec_elapsed(start);
get_dirty_log_total = timespec_add(get_dirty_log_total,
ts_diff);
if (dirty_log_manual_caps) {
clock_gettime(CLOCK_MONOTONIC, &start);
- clear_dirty_log(vm, p->slots, bmap, host_num_pages);
+ clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot);
ts_diff = timespec_elapsed(start);
clear_dirty_log_total = timespec_add(clear_dirty_log_total,
ts_diff);
clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
}
- free(bmap);
+ free_bitmaps(bitmaps, p->slots);
free(vcpu_threads);
perf_test_destroy_vm(vm);
}
printf(" -v: specify the number of vCPUs to run.\n");
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
" them into a separate region of memory for each vCPU.\n");
- printf(" -s: specify the type of memory that should be used to\n"
- " back the guest data region.\n\n");
+ backing_src_help("-s");
printf(" -x: Split the memory region into this number of memslots.\n"
- " (default: 1)");
- backing_src_help();
+ " (default: 1)\n");
puts("");
exit(0);
}
.iterations = TEST_HOST_LOOP_N,
.wr_fract = 1,
.partition_vcpu_memory_access = true,
- .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .backing_src = DEFAULT_VM_MEM_SRC,
.slots = 1,
};
int opt;
NUM_SRC_TYPES,
};
+#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS
+
struct vm_mem_backing_src_alias {
const char *name;
uint32_t flag;
size_t get_def_hugetlb_pagesz(void);
const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
size_t get_backing_src_pagesz(uint32_t i);
-void backing_src_help(void);
+void backing_src_help(const char *flag);
enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
long get_run_delay(void);
}
}
-typedef unsigned long v1di __attribute__ ((vector_size (8)));
+#define GET_XMM(__xmm) \
+({ \
+ unsigned long __val; \
+ asm volatile("movq %%"#__xmm", %0" : "=r"(__val) : : #__xmm); \
+ __val; \
+})
+
static inline unsigned long get_xmm(int n)
{
assert(n >= 0 && n <= 7);
- register v1di xmm0 __asm__("%xmm0");
- register v1di xmm1 __asm__("%xmm1");
- register v1di xmm2 __asm__("%xmm2");
- register v1di xmm3 __asm__("%xmm3");
- register v1di xmm4 __asm__("%xmm4");
- register v1di xmm5 __asm__("%xmm5");
- register v1di xmm6 __asm__("%xmm6");
- register v1di xmm7 __asm__("%xmm7");
switch (n) {
case 0:
- return (unsigned long)xmm0;
+ return GET_XMM(xmm0);
case 1:
- return (unsigned long)xmm1;
+ return GET_XMM(xmm1);
case 2:
- return (unsigned long)xmm2;
+ return GET_XMM(xmm2);
case 3:
- return (unsigned long)xmm3;
+ return GET_XMM(xmm3);
case 4:
- return (unsigned long)xmm4;
+ return GET_XMM(xmm4);
case 5:
- return (unsigned long)xmm5;
+ return GET_XMM(xmm5);
case 6:
- return (unsigned long)xmm6;
+ return GET_XMM(xmm6);
case 7:
- return (unsigned long)xmm7;
+ return GET_XMM(xmm7);
}
+
+ /* never reached */
return 0;
}
" (default: 1G)\n");
printf(" -v: specify the number of vCPUs to run\n"
" (default: 1)\n");
- printf(" -s: specify the type of memory that should be used to\n"
- " back the guest data region.\n"
- " (default: anonymous)\n\n");
- backing_src_help();
+ backing_src_help("-s");
puts("");
}
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
struct test_params p = {
.test_mem_size = DEFAULT_TEST_MEM_SIZE,
- .src_type = VM_MEM_SRC_ANONYMOUS,
+ .src_type = DEFAULT_VM_MEM_SRC,
};
int opt;
}
}
-void backing_src_help(void)
+static void print_available_backing_src_types(const char *prefix)
{
int i;
- printf("Available backing src types:\n");
+ printf("%sAvailable backing src types:\n", prefix);
+
for (i = 0; i < NUM_SRC_TYPES; i++)
- printf("\t%s\n", vm_mem_backing_src_alias(i)->name);
+ printf("%s %s\n", prefix, vm_mem_backing_src_alias(i)->name);
+}
+
+void backing_src_help(const char *flag)
+{
+ printf(" %s: specify the type of memory that should be used to\n"
+ " back the guest data region. (default: %s)\n",
+ flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name);
+ print_available_backing_src_types(" ");
}
enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name)
if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name))
return i;
- backing_src_help();
+ print_available_backing_src_types("");
TEST_FAIL("Unknown backing src type: %s", type_name);
return -1;
}
* CPU affinity.
*/
vm = vm_create_default(VCPU_ID, 0, guest_code);
+ ucall_init(vm, NULL);
pthread_create(&migration_thread, NULL, migration_worker, 0);
uint64_t st_time;
};
-static int64_t smccc(uint32_t func, uint32_t arg)
+static int64_t smccc(uint32_t func, uint64_t arg)
{
unsigned long ret;
asm volatile(
- "mov x0, %1\n"
+ "mov w0, %w1\n"
"mov x1, %2\n"
"hvc #0\n"
"mov %0, x0\n"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_int_ctl_test
+ *
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "apic.h"
+
+#define VCPU_ID 0
+
+static struct kvm_vm *vm;
+
+bool vintr_irq_called;
+bool intr_irq_called;
+
+#define VINTR_IRQ_NUMBER 0x20
+#define INTR_IRQ_NUMBER 0x30
+
+static void vintr_irq_handler(struct ex_regs *regs)
+{
+ vintr_irq_called = true;
+}
+
+static void intr_irq_handler(struct ex_regs *regs)
+{
+ x2apic_write_reg(APIC_EOI, 0x00);
+ intr_irq_called = true;
+}
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+ /* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC,
+ * and since L1 didn't enable virtual interrupt masking,
+ * L2 should receive it and not L1.
+ *
+ * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ
+ * so it should also receive it after the following 'sti'.
+ */
+ x2apic_write_reg(APIC_ICR,
+ APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER);
+
+ __asm__ __volatile__(
+ "sti\n"
+ "nop\n"
+ );
+
+ GUEST_ASSERT(vintr_irq_called);
+ GUEST_ASSERT(intr_irq_called);
+
+ __asm__ __volatile__(
+ "vmcall\n"
+ );
+}
+
+static void l1_guest_code(struct svm_test_data *svm)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ struct vmcb *vmcb = svm->vmcb;
+
+ x2apic_enable();
+
+ /* Prepare for L2 execution. */
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ /* No virtual interrupt masking */
+ vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
+
+ /* No intercepts for real and virtual interrupts */
+ vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR);
+
+ /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */
+ vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT);
+ vmcb->control.int_vector = VINTR_IRQ_NUMBER;
+
+ run_guest(vmcb, svm->vmcb_gpa);
+ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t svm_gva;
+
+ nested_svm_check_supported();
+
+ vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler);
+ vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler);
+
+ vcpu_alloc_svm(vm, &svm_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, svm_gva);
+
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s", (const char *)uc.args[0]);
+ break;
+ /* NOT REACHED */
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+ }
+done:
+ kvm_vm_free(vm);
+ return 0;
+}
--- /dev/null
+#!/bin/bash
+#
+# Test connection tracking zone and NAT source port reallocation support.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Don't increase too much, 2000 clients should work
+# just fine but script can then take several minutes with
+# KASAN/debug builds.
+maxclients=100
+
+have_iperf=1
+ret=0
+
+# client1---.
+# veth1-.
+# |
+# NAT Gateway --veth0--> Server
+# | |
+# veth2-' |
+# client2---' |
+# .... |
+# clientX----vethX---'
+
+# All clients share identical IP address.
+# NAT Gateway uses policy routing and conntrack zones to isolate client
+# namespaces. Each client connects to Server, each with colliding tuples:
+# clientsaddr:10000 -> serveraddr:dport
+# NAT Gateway is supposed to do port reallocation for each of the
+# connections.
+
+sfx=$(mktemp -u "XXXXXXXX")
+gw="ns-gw-$sfx"
+cl1="ns-cl1-$sfx"
+cl2="ns-cl2-$sfx"
+srv="ns-srv-$sfx"
+
+v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null)
+v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null)
+v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null)
+v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null)
+v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null)
+v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null)
+
+cleanup()
+{
+ ip netns del $gw
+ ip netns del $srv
+ for i in $(seq 1 $maxclients); do
+ ip netns del ns-cl$i-$sfx 2>/dev/null
+ done
+
+ sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null
+ sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null
+ sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null
+ sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null
+ sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null
+ sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+conntrack -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without conntrack tool"
+ exit $ksft_skip
+fi
+
+iperf3 -v >/dev/null 2>&1
+if [ $? -ne 0 ];then
+ have_iperf=0
+fi
+
+ip netns add "$gw"
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace $gw"
+ exit $ksft_skip
+fi
+ip -net "$gw" link set lo up
+
+trap cleanup EXIT
+
+ip netns add "$srv"
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create server netns $srv"
+ exit $ksft_skip
+fi
+
+ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv"
+ip -net "$gw" link set veth0 up
+ip -net "$srv" link set lo up
+ip -net "$srv" link set eth0 up
+
+sysctl -q net.ipv6.neigh.default.gc_thresh1=512 2>/dev/null
+sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null
+sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh1=512 2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null
+sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null
+
+for i in $(seq 1 $maxclients);do
+ cl="ns-cl$i-$sfx"
+
+ ip netns add "$cl"
+ if [ $? -ne 0 ];then
+ echo "SKIP: Could not create client netns $cl"
+ exit $ksft_skip
+ fi
+ ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1
+ if [ $? -ne 0 ];then
+ echo "SKIP: No virtual ethernet pair device support in kernel"
+ exit $ksft_skip
+ fi
+done
+
+for i in $(seq 1 $maxclients);do
+ cl="ns-cl$i-$sfx"
+ echo netns exec "$cl" ip link set lo up
+ echo netns exec "$cl" ip link set eth0 up
+ echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2
+ echo netns exec "$gw" ip link set veth$i up
+ echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2
+ echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0
+
+ # clients have same IP addresses.
+ echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0
+ echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0
+ echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0
+ echo netns exec "$cl" ip route add default via dead:1::2 dev eth0
+
+ # NB: same addresses on client-facing interfaces.
+ echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i
+ echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i
+
+ # gw: policy routing
+ echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i))
+ echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i))
+ echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i))
+ echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i))
+ echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i))
+done | ip -batch /dev/stdin
+
+ip -net "$gw" addr add 10.3.0.1/24 dev veth0
+ip -net "$gw" addr add dead:3::1/64 dev veth0
+
+ip -net "$srv" addr add 10.3.0.99/24 dev eth0
+ip -net "$srv" addr add dead:3::99/64 dev eth0
+
+ip netns exec $gw nft -f /dev/stdin<<EOF
+table inet raw {
+ map iiftomark {
+ type ifname : mark
+ }
+
+ map iiftozone {
+ typeof iifname : ct zone
+ }
+
+ set inicmp {
+ flags dynamic
+ type ipv4_addr . ifname . ipv4_addr
+ }
+ set inflows {
+ flags dynamic
+ type ipv4_addr . inet_service . ifname . ipv4_addr . inet_service
+ }
+
+ set inflows6 {
+ flags dynamic
+ type ipv6_addr . inet_service . ifname . ipv6_addr . inet_service
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority -64000; policy accept;
+ ct original zone set meta iifname map @iiftozone
+ meta mark set meta iifname map @iiftomark
+
+ tcp flags & (syn|ack) == ack add @inflows { ip saddr . tcp sport . meta iifname . ip daddr . tcp dport counter }
+ add @inflows6 { ip6 saddr . tcp sport . meta iifname . ip6 daddr . tcp dport counter }
+ ip protocol icmp add @inicmp { ip saddr . meta iifname . ip daddr counter }
+ }
+
+ chain nat_postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ ct mark set meta mark meta oifname veth0 masquerade
+ }
+
+ chain mangle_prerouting {
+ type filter hook prerouting priority -100; policy accept;
+ ct direction reply meta mark set ct mark
+ }
+}
+EOF
+
+( echo add element inet raw iiftomark \{
+ for i in $(seq 1 $((maxclients-1))); do
+ echo \"veth$i\" : $i,
+ done
+ echo \"veth$maxclients\" : $maxclients \}
+ echo add element inet raw iiftozone \{
+ for i in $(seq 1 $((maxclients-1))); do
+ echo \"veth$i\" : $i,
+ done
+ echo \"veth$maxclients\" : $maxclients \}
+) | ip netns exec $gw nft -f /dev/stdin
+
+ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null
+
+# useful for debugging: allows to use 'ping' from clients to gateway.
+ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null
+ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null
+
+for i in $(seq 1 $maxclients); do
+ cl="ns-cl$i-$sfx"
+ ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 &
+ if [ $? -ne 0 ]; then
+ echo FAIL: Ping failure from $cl 1>&2
+ ret=1
+ break
+ fi
+done
+
+wait
+
+for i in $(seq 1 $maxclients); do
+ ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }"
+ if [ $? -ne 0 ];then
+ ret=1
+ echo "FAIL: counter icmp mismatch for veth$i" 1>&2
+ ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2
+ break
+ fi
+done
+
+ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }"
+if [ $? -ne 0 ];then
+ ret=1
+ echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }"
+ ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2
+fi
+
+if [ $ret -eq 0 ]; then
+ echo "PASS: ping test from all $maxclients namespaces"
+fi
+
+if [ $have_iperf -eq 0 ];then
+ echo "SKIP: iperf3 not installed"
+ if [ $ret -ne 0 ];then
+ exit $ret
+ fi
+ exit $ksft_skip
+fi
+
+ip netns exec $srv iperf3 -s > /dev/null 2>&1 &
+iperfpid=$!
+sleep 1
+
+for i in $(seq 1 $maxclients); do
+ if [ $ret -ne 0 ]; then
+ break
+ fi
+ cl="ns-cl$i-$sfx"
+ ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null
+ if [ $? -ne 0 ]; then
+ echo FAIL: Failure to connect for $cl 1>&2
+ ip netns exec $gw conntrack -S 1>&2
+ ret=1
+ fi
+done
+if [ $ret -eq 0 ];then
+ echo "PASS: iperf3 connections for all $maxclients net namespaces"
+fi
+
+kill $iperfpid
+wait
+
+for i in $(seq 1 $maxclients); do
+ ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null
+ if [ $? -ne 0 ];then
+ ret=1
+ echo "FAIL: can't find expected tcp entry for veth$i" 1>&2
+ break
+ fi
+done
+if [ $ret -eq 0 ];then
+ echo "PASS: Found client connection for all $maxclients net namespaces"
+fi
+
+ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null
+if [ $? -ne 0 ];then
+ ret=1
+ echo "FAIL: cannot find return entry on veth0" 1>&2
+fi
+
+exit $ret
--- /dev/null
+#!/bin/bash
+
+# Test insertion speed for packets with identical addresses/ports
+# that are all placed in distinct conntrack zones.
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns="ns-$sfx"
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+zones=20000
+have_ct_tool=0
+ret=0
+
+cleanup()
+{
+ ip netns del $ns
+}
+
+ip netns add $ns
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace $gw"
+ exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+conntrack -V > /dev/null 2>&1
+if [ $? -eq 0 ];then
+ have_ct_tool=1
+fi
+
+ip -net "$ns" link set lo up
+
+test_zones() {
+ local max_zones=$1
+
+ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600
+ip netns exec $ns nft -f /dev/stdin<<EOF
+flush ruleset
+table inet raw {
+ map rndzone {
+ typeof numgen inc mod $max_zones : ct zone
+ }
+
+ chain output {
+ type filter hook output priority -64000; policy accept;
+ udp dport 12345 ct zone set numgen inc mod 65536 map @rndzone
+ }
+}
+EOF
+ (
+ echo "add element inet raw rndzone {"
+ for i in $(seq 1 $max_zones);do
+ echo -n "$i : $i"
+ if [ $i -lt $max_zones ]; then
+ echo ","
+ else
+ echo "}"
+ fi
+ done
+ ) | ip netns exec $ns nft -f /dev/stdin
+
+ local i=0
+ local j=0
+ local outerstart=$(date +%s%3N)
+ local stop=$outerstart
+
+ while [ $i -lt $max_zones ]; do
+ local start=$(date +%s%3N)
+ i=$((i + 10000))
+ j=$((j + 1))
+ dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+ if [ $? -ne 0 ] ;then
+ ret=1
+ break
+ fi
+
+ stop=$(date +%s%3N)
+ local duration=$((stop-start))
+ echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+ done
+
+ if [ $have_ct_tool -eq 1 ]; then
+ local count=$(ip netns exec "$ns" conntrack -C)
+ local duration=$((stop-outerstart))
+
+ if [ $count -eq $max_zones ]; then
+ echo "PASS: inserted $count entries from packet path in $duration ms total"
+ else
+ ip netns exec $ns conntrack -S 1>&2
+ echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries"
+ ret=1
+ fi
+ fi
+
+ if [ $ret -ne 0 ];then
+ echo "FAIL: insert $max_zones entries from packet path" 1>&2
+ fi
+}
+
+test_conntrack_tool() {
+ local max_zones=$1
+
+ ip netns exec $ns conntrack -F >/dev/null 2>/dev/null
+
+ local outerstart=$(date +%s%3N)
+ local start=$(date +%s%3N)
+ local stop=$start
+ local i=0
+ while [ $i -lt $max_zones ]; do
+ i=$((i + 1))
+ ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \
+ --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1
+ if [ $? -ne 0 ];then
+ ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \
+ --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null
+ echo "FAIL: conntrack -I returned an error"
+ ret=1
+ break
+ fi
+
+ if [ $((i%10000)) -eq 0 ];then
+ stop=$(date +%s%3N)
+
+ local duration=$((stop-start))
+ echo "PASS: added 10000 entries in $duration ms (now $i total)"
+ start=$stop
+ fi
+ done
+
+ local count=$(ip netns exec "$ns" conntrack -C)
+ local duration=$((stop-outerstart))
+
+ if [ $count -eq $max_zones ]; then
+ echo "PASS: inserted $count entries via ctnetlink in $duration ms"
+ else
+ ip netns exec $ns conntrack -S 1>&2
+ echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)"
+ ret=1
+ fi
+}
+
+test_zones $zones
+
+if [ $have_ct_tool -eq 1 ];then
+ test_conntrack_tool $zones
+else
+ echo "SKIP: Could not run ctnetlink insertion test without conntrack tool"
+ if [ $ret -eq 0 ];then
+ exit $ksft_skip
+ fi
+fi
+
+exit $ret
{
}
-static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
+static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
{
- if (unlikely(!cpus))
+ const struct cpumask *cpus;
+
+ if (likely(cpumask_available(tmp)))
+ cpus = tmp;
+ else
cpus = cpu_online_mask;
if (cpumask_empty(cpus))
continue;
kvm_make_request(req, vcpu);
- cpu = vcpu->cpu;
if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
continue;
- if (tmp != NULL && cpu != -1 && cpu != me &&
- kvm_request_needs_ipi(vcpu, req))
- __cpumask_set_cpu(cpu, tmp);
+ /*
+ * tmp can be "unavailable" if cpumasks are allocated off stack
+ * as allocation of the mask is deliberately not fatal and is
+ * handled by falling back to kicking all online CPUs.
+ */
+ if (!cpumask_available(tmp))
+ continue;
+
+ /*
+ * Note, the vCPU could get migrated to a different pCPU at any
+ * point after kvm_request_needs_ipi(), which could result in
+ * sending an IPI to the previous pCPU. But, that's ok because
+ * the purpose of the IPI is to ensure the vCPU returns to
+ * OUTSIDE_GUEST_MODE, which is satisfied if the vCPU migrates.
+ * Entering READING_SHADOW_PAGE_TABLES after this point is also
+ * ok, as the requirement is only that KVM wait for vCPUs that
+ * were reading SPTEs _before_ any changes were finalized. See
+ * kvm_vcpu_kick() for more details on handling requests.
+ */
+ if (kvm_request_needs_ipi(vcpu, req)) {
+ cpu = READ_ONCE(vcpu->cpu);
+ if (cpu != -1 && cpu != me)
+ __cpumask_set_cpu(cpu, tmp);
+ }
}
called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
- /*
- * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in
- * kvm_make_all_cpus_request.
- */
- long dirty_count = smp_load_acquire(&kvm->tlbs_dirty);
-
++kvm->stat.generic.remote_tlb_flush_requests;
+
/*
* We want to publish modifications to the page tables before reading
* mode. Pairs with a memory barrier in arch-specific code.
if (!kvm_arch_flush_remote_tlb(kvm)
|| kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.generic.remote_tlb_flush;
- cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
#endif
}
}
- if (range->flush_on_ret && (ret || kvm->tlbs_dirty))
+ if (range->flush_on_ret && ret)
kvm_flush_remote_tlbs(kvm);
if (locked)
static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- unsigned int old, val, shrink;
+ unsigned int old, val, shrink, grow_start;
old = val = vcpu->halt_poll_ns;
shrink = READ_ONCE(halt_poll_ns_shrink);
+ grow_start = READ_ONCE(halt_poll_ns_grow_start);
if (shrink == 0)
val = 0;
else
val /= shrink;
+ if (val < grow_start)
+ val = 0;
+
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
}
*/
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
- int me;
- int cpu = vcpu->cpu;
+ int me, cpu;
if (kvm_vcpu_wake_up(vcpu))
return;
+ /*
+ * Note, the vCPU could get migrated to a different pCPU at any point
+ * after kvm_arch_vcpu_should_kick(), which could result in sending an
+ * IPI to the previous pCPU. But, that's ok because the purpose of the
+ * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the
+ * vCPU also requires it to leave IN_GUEST_MODE.
+ */
me = get_cpu();
- if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
- if (kvm_arch_vcpu_should_kick(vcpu))
+ if (kvm_arch_vcpu_should_kick(vcpu)) {
+ cpu = READ_ONCE(vcpu->cpu);
+ if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
smp_send_reschedule(cpu);
+ }
put_cpu();
}
EXPORT_SYMBOL_GPL(kvm_vcpu_kick);