Sibi Sankar <quic_sibis@quicinc.com> <sibis@codeaurora.org>
Sid Manning <quic_sidneym@quicinc.com> <sidneym@codeaurora.org>
Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu>
+Simon Horman <horms@kernel.org> <simon.horman@corigine.com>
+Simon Horman <horms@kernel.org> <simon.horman@netronome.com>
Simon Kelley <simon@thekelleys.org.uk>
Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
description: Whether to enable burnout current for EXT1.
adi,ext1-burnout-current-nanoamp:
- $ref: /schemas/types.yaml#/definitions/uint32
description:
Burnout current in nanoamps to be applied to EXT1.
enum: [0, 50, 500, 1000, 10000]
description: Whether to enable burnout current for EXT2.
adi,ext2-burnout-current-nanoamp:
- $ref: /schemas/types.yaml#/definitions/uint32
description: Burnout current in nanoamps to be applied to EXT2.
enum: [0, 50, 500, 1000, 10000]
default: 0
description: Whether to enable burnout current for VIOUT.
adi,viout-burnout-current-nanoamp:
- $ref: /schemas/types.yaml#/definitions/uint32
description: Burnout current in nanoamps to be applied to VIOUT.
enum: [0, 1000, 10000]
default: 0
Default is set to (hb_interval * path_max_retrans + rto_max)
nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds)
- default 0.3
+ default 3
nf_conntrack_sctp_timeout_shutdown_recd - INTEGER (seconds)
- default 0.3
+ default 3
nf_conntrack_sctp_timeout_shutdown_ack_sent - INTEGER (seconds)
default 3
F: include/linux/hisi_acc_qm.h
HISILICON ROCE DRIVER
-M: Haoyue Xu <xuhaoyue1@hisilicon.com>
M: Junxian Huang <huangjunxian6@hisilicon.com>
L: linux-rdma@vger.kernel.org
S: Maintained
MAPLE TREE
M: Liam R. Howlett <Liam.Howlett@oracle.com>
+L: maple-tree@lists.infradead.org
L: linux-mm@kvack.org
S: Supported
F: Documentation/core-api/maple_tree.rst
PCI DRIVER FOR SYNOPSYS DESIGNWARE
M: Jingoo Han <jingoohan1@gmail.com>
M: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
L: linux-pci@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml
S: Maintained
F: drivers/block/virtio_blk.c
F: drivers/scsi/virtio_scsi.c
-F: drivers/vhost/scsi.c
F: include/uapi/linux/virtio_blk.h
F: include/uapi/linux/virtio_scsi.h
F: include/uapi/linux/vhost.h
F: kernel/vhost_task.c
+VIRTIO HOST (VHOST-SCSI)
+M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
+M: Mike Christie <michael.christie@oracle.com>
+R: Paolo Bonzini <pbonzini@redhat.com>
+R: Stefan Hajnoczi <stefanha@redhat.com>
+L: virtualization@lists.linux-foundation.org
+S: Maintained
+F: drivers/vhost/scsi.c
+
VIRTIO I2C DRIVER
M: Conghui Chen <conghui.chen@intel.com>
M: Viresh Kumar <viresh.kumar@linaro.org>
VERSION = 6
PATCHLEVEL = 5
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
-
-#ifndef CONFIG_SMP
-/* Nothing to prefetch. */
-#define spin_lock_prefetch(lock) do { } while (0)
-#endif
extern inline void prefetch(const void *ptr)
{
__builtin_prefetch(ptr, 1, 3);
}
-#ifdef CONFIG_SMP
-extern inline void spin_lock_prefetch(const void *ptr)
-{
- __builtin_prefetch(ptr, 1, 3);
-}
-#endif
-
#endif /* __ASM_ALPHA_PROCESSOR_H */
#endif /* CONFIG_BLK_DEV_INITRD */
}
-int __init
-page_is_ram(unsigned long pfn)
+int page_is_ram(unsigned long pfn)
{
struct memclust_struct * cluster;
struct memdesc_struct * memdesc;
asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr));
}
-#define ARCH_HAS_SPINLOCK_PREFETCH
-static inline void spin_lock_prefetch(const void *ptr)
-{
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- "prfm pstl1strm, %a0",
- "nop") : : "p" (ptr));
-}
-
extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
extern void __init minsigstksz_setup(void);
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
#define PREFETCH_STRIDE L1_CACHE_BYTES
static inline void
ia64_lfetch_excl(ia64_lfhint_none, x);
}
-#define spin_lock_prefetch(x) prefetchw(x)
-
extern unsigned long boot_option_idle_override;
enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_FORCE_MWAIT,
#define cpu_has_rixi (cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
-#define ARCH_HAS_SPINLOCK_PREFETCH 1
-#define spin_lock_prefetch(x) prefetch(x)
#define PREFETCH_STRIDE 128
#ifdef __OCTEON__
#
config LIGHTWEIGHT_SPINLOCK_CHECK
bool "Enable lightweight spinlock checks"
- depends on SMP && !DEBUG_SPINLOCK
+ depends on DEBUG_KERNEL && SMP && !DEBUG_SPINLOCK
default y
help
Add checks with low performance impact to the spinlock functions
return NULL;
}
-int puts(const char *s)
+static int puts(const char *s)
{
const char *nuline = s;
return 0;
}
-int printf(const char *fmt, ...)
+static int printf(const char *fmt, ...)
{
va_list args;
int i = 0;
}
#undef malloc
-void *malloc(size_t size)
+static void *malloc(size_t size)
{
return malloc_gzip(size);
}
#undef free
-void free(void *ptr)
+static void free(void *ptr)
{
return free_gzip(ptr);
}
free(phdrs);
}
-unsigned long decompress_kernel(unsigned int started_wide,
+asmlinkage unsigned long __visible decompress_kernel(unsigned int started_wide,
unsigned int command_line,
const unsigned int rd_start,
const unsigned int rd_end)
#define dma_outb outb
#define dma_inb inb
+extern unsigned long pcxl_dma_start;
+
/*
** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up
** (or rather not merge) DMAs into manageable chunks.
extern unsigned long sys_call_table[];
extern unsigned long return_address(unsigned int);
+struct ftrace_regs;
+extern void ftrace_function_trampoline(unsigned long parent,
+ unsigned long self_addr, unsigned long org_sp_gr3,
+ struct ftrace_regs *fregs);
#ifdef CONFIG_DYNAMIC_FTRACE
extern void ftrace_caller(void);
#include <asm/processor.h>
#include <asm/spinlock_types.h>
-#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */
-
static inline void arch_spin_val_check(int lock_val)
{
if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK))
#define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46
+#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */
+
+#ifndef __ASSEMBLY__
+
typedef struct {
#ifdef CONFIG_PA20
volatile unsigned int slock;
volatile unsigned int counter;
} arch_rwlock_t;
+#endif /* __ASSEMBLY__ */
+
#define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000
#define __ARCH_RW_LOCK_UNLOCKED { .lock_mutex = __ARCH_SPIN_LOCK_UNLOCKED, \
.counter = __ARCH_RW_LOCK_UNLOCKED__ }
#include <asm/traps.h>
#include <asm/thread_info.h>
#include <asm/alternative.h>
+#include <asm/spinlock_types.h>
#include <linux/linkage.h>
#include <linux/pgtable.h>
LDREG 0(\ptp),\pte
bb,<,n \pte,_PAGE_PRESENT_BIT,3f
b \fault
- stw \spc,0(\tmp)
+ stw \tmp1,0(\tmp)
99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
#endif
2: LDREG 0(\ptp),\pte
.endm
/* Release page_table_lock without reloading lock address.
- Note that the values in the register spc are limited to
- NR_SPACE_IDS (262144). Thus, the stw instruction always
- stores a nonzero value even when register spc is 64 bits.
We use an ordered store to ensure all prior accesses are
performed prior to releasing the lock. */
- .macro ptl_unlock0 spc,tmp
+ .macro ptl_unlock0 spc,tmp,tmp2
#ifdef CONFIG_TLB_PTLOCK
-98: or,COND(=) %r0,\spc,%r0
- stw,ma \spc,0(\tmp)
+98: ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmp2
+ or,COND(=) %r0,\spc,%r0
+ stw,ma \tmp2,0(\tmp)
99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
#endif
.endm
/* Release page_table_lock. */
- .macro ptl_unlock1 spc,tmp
+ .macro ptl_unlock1 spc,tmp,tmp2
#ifdef CONFIG_TLB_PTLOCK
98: get_ptl \tmp
- ptl_unlock0 \spc,\tmp
+ ptl_unlock0 \spc,\tmp,\tmp2
99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
#endif
.endm
idtlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
idtlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
mtsp t1, %sr1 /* Restore sr1 */
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
mtsp t1, %sr1 /* Restore sr1 */
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
idtlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
idtlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
iitlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
iitlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
mtsp t1, %sr1 /* Restore sr1 */
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
mtsp t1, %sr1 /* Restore sr1 */
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
iitlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
iitlbt pte,prot
- ptl_unlock1 spc,t0
+ ptl_unlock1 spc,t0,t1
rfir
nop
idtlbt pte,prot
- ptl_unlock0 spc,t0
+ ptl_unlock0 spc,t0,t1
rfir
nop
#else
mtsp t1, %sr1 /* Restore sr1 */
- ptl_unlock0 spc,t0
+ ptl_unlock0 spc,t0,t1
rfir
nop
idtlbt pte,prot
- ptl_unlock0 spc,t0
+ ptl_unlock0 spc,t0,t1
rfir
nop
#endif
static DEFINE_SPINLOCK(pdc_lock);
#endif
-unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8);
-unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8);
+static unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8);
+static unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8);
#ifdef CONFIG_64BIT
#define WIDE_FIRMWARE 0x1
/**
* pdc_cpu_rendezvous_lock - Lock PDC while transitioning to rendezvous state
*/
-void pdc_cpu_rendezvous_lock(void)
+void pdc_cpu_rendezvous_lock(void) __acquires(&pdc_lock)
{
spin_lock(&pdc_lock);
}
/**
* pdc_cpu_rendezvous_unlock - Unlock PDC after reaching rendezvous state
*/
-void pdc_cpu_rendezvous_unlock(void)
+void pdc_cpu_rendezvous_unlock(void) __releases(&pdc_lock)
{
spin_unlock(&pdc_lock);
}
static ftrace_func_t ftrace_func;
-void notrace __hot ftrace_function_trampoline(unsigned long parent,
+asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent,
unsigned long self_addr,
unsigned long org_sp_gr3,
struct ftrace_regs *fregs)
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
+#include <linux/libgcc.h>
#include <linux/string.h>
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL($$divI_14);
EXPORT_SYMBOL($$divI_15);
-extern void __ashrdi3(void);
-extern void __ashldi3(void);
-extern void __lshrdi3(void);
-extern void __muldi3(void);
-extern void __ucmpdi2(void);
-
EXPORT_SYMBOL(__ashrdi3);
EXPORT_SYMBOL(__ashldi3);
EXPORT_SYMBOL(__lshrdi3);
static unsigned long pcxl_used_bytes __read_mostly;
static unsigned long pcxl_used_pages __read_mostly;
-extern unsigned long pcxl_dma_start; /* Start of pcxl dma mapping area */
+unsigned long pcxl_dma_start __ro_after_init; /* pcxl dma mapping area start */
static DEFINE_SPINLOCK(pcxl_res_lock);
static char *pcxl_res_map;
static int pcxl_res_hint;
pcxl_res_map = (char *)__get_free_pages(GFP_KERNEL,
get_order(pcxl_res_size));
memset(pcxl_res_map, 0, pcxl_res_size);
- proc_gsc_root = proc_mkdir("gsc", NULL);
+ proc_gsc_root = proc_mkdir("bus/gsc", NULL);
if (!proc_gsc_root)
printk(KERN_WARNING
"pcxl_dma_init: Unable to create gsc /proc dir entry\n");
return -ENODEV;
kpdtd_task = kthread_run(pdt_mainloop, NULL, "kpdtd");
- if (IS_ERR(kpdtd_task))
- return PTR_ERR(kpdtd_task);
- return 0;
+ return PTR_ERR_OR_ZERO(kpdtd_task);
}
late_initcall(pdt_initcall);
static int perf_processor_interface __read_mostly = UNKNOWN_INTF;
static int perf_enabled __read_mostly;
static DEFINE_SPINLOCK(perf_lock);
-struct parisc_device *cpu_device __read_mostly;
+static struct parisc_device *cpu_device __read_mostly;
/* RDRs to write for PCX-W */
static const int perf_rdrs_W[] =
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/pdc.h>
+#include <asm/smp.h>
#include <asm/pdcpat.h>
#include <asm/irq.h> /* for struct irq_region */
#include <asm/parisc-device.h>
static char __initdata command_line[COMMAND_LINE_SIZE];
-/* Intended for ccio/sba/cpu statistics under /proc/bus/{runway|gsc} */
-struct proc_dir_entry * proc_runway_root __read_mostly = NULL;
-struct proc_dir_entry * proc_gsc_root __read_mostly = NULL;
-struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL;
-
static void __init setup_cmdline(char **cmdline_p)
{
extern unsigned int boot_args[];
.show = show_cpuinfo
};
-static void __init parisc_proc_mkdir(void)
-{
- /*
- ** Can't call proc_mkdir() until after proc_root_init() has been
- ** called by start_kernel(). In other words, this code can't
- ** live in arch/.../setup.c because start_parisc() calls
- ** start_kernel().
- */
- switch (boot_cpu_data.cpu_type) {
- case pcxl:
- case pcxl2:
- if (NULL == proc_gsc_root)
- {
- proc_gsc_root = proc_mkdir("bus/gsc", NULL);
- }
- break;
- case pcxt_:
- case pcxu:
- case pcxu_:
- case pcxw:
- case pcxw_:
- case pcxw2:
- if (NULL == proc_runway_root)
- {
- proc_runway_root = proc_mkdir("bus/runway", NULL);
- }
- break;
- case mako:
- case mako2:
- if (NULL == proc_mckinley_root)
- {
- proc_mckinley_root = proc_mkdir("bus/mckinley", NULL);
- }
- break;
- default:
- /* FIXME: this was added to prevent the compiler
- * complaining about missing pcx, pcxs and pcxt
- * I'm assuming they have neither gsc nor runway */
- break;
- }
-}
-
static struct resource central_bus = {
.name = "Central Bus",
.start = F_EXTEND(0xfff80000),
{
u32 osid = (OS_ID_LINUX << 16);
- parisc_proc_mkdir();
parisc_init_resources();
do_device_inventory(); /* probe for hardware */
regs->gr[31] -= 8; /* delayed branching */
/* Get assembler opcode of code in delay branch */
- uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4);
+ uaddr = (u32 __user *) ((regs->gr[31] & ~3) + 4);
err = get_user(opcode, uaddr);
if (err)
return;
#include <linux/elf-randomize.h>
/*
- * Construct an artificial page offset for the mapping based on the virtual
+ * Construct an artificial page offset for the mapping based on the physical
* address of the kernel file mapping variable.
- * If filp is zero the calculated pgoff value aliases the memory of the given
- * address. This is useful for io_uring where the mapping shall alias a kernel
- * address and a userspace adress where both the kernel and the userspace
- * access the same memory region.
*/
-#define GET_FILP_PGOFF(filp, addr) \
- ((filp ? (((unsigned long) filp->f_mapping) >> 8) \
- & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) \
- + (addr >> PAGE_SHIFT))
+#define GET_FILP_PGOFF(filp) \
+ (filp ? (((unsigned long) filp->f_mapping) >> 8) \
+ & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL)
static unsigned long shared_align_offset(unsigned long filp_pgoff,
unsigned long pgoff)
do_color_align = 0;
if (filp || (flags & MAP_SHARED))
do_color_align = 1;
- filp_pgoff = GET_FILP_PGOFF(filp, addr);
+ filp_pgoff = GET_FILP_PGOFF(filp);
if (flags & MAP_FIXED) {
/* Even MAP_FIXED mappings must reside within TASK_SIZE */
#include <asm/assembly.h>
#include <asm/processor.h>
#include <asm/cache.h>
+#include <asm/spinlock_types.h>
#include <linux/linkage.h>
stw \reg1, 0(%sr2,\reg2)
.endm
+ /* raise exception if spinlock content is not zero or
+ * __ARCH_SPIN_LOCK_UNLOCKED_VAL */
+ .macro spinlock_check spin_val,tmpreg
+#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK
+ ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmpreg
+ andcm,= \spin_val, \tmpreg, %r0
+ .word SPINLOCK_BREAK_INSN
+#endif
+ .endm
+
.text
.import syscall_exit,code
lws_exit_noerror:
lws_pagefault_enable %r1,%r21
- stw,ma %r20, 0(%sr2,%r20)
+ ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21
+ stw,ma %r21, 0(%sr2,%r20)
ssm PSW_SM_I, %r0
b lws_exit
copy %r0, %r21
lws_pagefault:
lws_pagefault_enable %r1,%r21
- stw,ma %r20, 0(%sr2,%r20)
+ ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21
+ stw,ma %r21, 0(%sr2,%r20)
ssm PSW_SM_I, %r0
ldo 3(%r0),%r28
b lws_exit
/* Try to acquire the lock */
LDCW 0(%sr2,%r20), %r28
+ spinlock_check %r28, %r21
comclr,<> %r0, %r28, %r0
b,n lws_wouldblock
/* Try to acquire the lock */
LDCW 0(%sr2,%r20), %r28
+ spinlock_check %r28, %r21
comclr,<> %r0, %r28, %r0
b,n lws_wouldblock
/* Try to acquire the lock */
LDCW 0(%sr2,%r20), %r28
+ spinlock_check %r28, %r21
comclr,<> %r0, %r28, %r0
b,n lws_wouldblock
/* Try to acquire the lock */
LDCW 0(%sr2,%r20), %r28
+ spinlock_check %r28, %r21
comclr,<> %r0, %r28, %r0
b,n lws_wouldblock
/* lws locks */
.rept 256
/* Keep locks aligned at 16-bytes */
- .word 1
+ .word __ARCH_SPIN_LOCK_UNLOCKED_VAL
.word 0
.word 0
.word 0
#include <linux/signal.h>
#include <linux/ratelimit.h>
#include <linux/uaccess.h>
+#include <linux/sysctl.h>
#include <asm/unaligned.h>
#include <asm/hardirq.h>
#include <asm/traps.h>
// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
+#include <linux/libgcc.h>
union ull_union {
unsigned long long ull;
} ui;
};
-int __ucmpdi2(unsigned long long a, unsigned long long b)
+word_type __ucmpdi2(unsigned long long a, unsigned long long b)
{
union ull_union au = {.ull = a};
union ull_union bu = {.ull = b};
* For implementation see handle_interruption() in traps.c
*/
static const char * const trap_description[] = {
- [1] "High-priority machine check (HPMC)",
- [2] "Power failure interrupt",
- [3] "Recovery counter trap",
- [5] "Low-priority machine check",
- [6] "Instruction TLB miss fault",
- [7] "Instruction access rights / protection trap",
- [8] "Illegal instruction trap",
- [9] "Break instruction trap",
- [10] "Privileged operation trap",
- [11] "Privileged register trap",
- [12] "Overflow trap",
- [13] "Conditional trap",
- [14] "FP Assist Exception trap",
- [15] "Data TLB miss fault",
- [16] "Non-access ITLB miss fault",
- [17] "Non-access DTLB miss fault",
- [18] "Data memory protection/unaligned access trap",
- [19] "Data memory break trap",
- [20] "TLB dirty bit trap",
- [21] "Page reference trap",
- [22] "Assist emulation trap",
- [25] "Taken branch trap",
- [26] "Data memory access rights trap",
- [27] "Data memory protection ID trap",
- [28] "Unaligned data reference trap",
+ [1] = "High-priority machine check (HPMC)",
+ [2] = "Power failure interrupt",
+ [3] = "Recovery counter trap",
+ [5] = "Low-priority machine check",
+ [6] = "Instruction TLB miss fault",
+ [7] = "Instruction access rights / protection trap",
+ [8] = "Illegal instruction trap",
+ [9] = "Break instruction trap",
+ [10] = "Privileged operation trap",
+ [11] = "Privileged register trap",
+ [12] = "Overflow trap",
+ [13] = "Conditional trap",
+ [14] = "FP Assist Exception trap",
+ [15] = "Data TLB miss fault",
+ [16] = "Non-access ITLB miss fault",
+ [17] = "Non-access DTLB miss fault",
+ [18] = "Data memory protection/unaligned access trap",
+ [19] = "Data memory break trap",
+ [20] = "TLB dirty bit trap",
+ [21] = "Page reference trap",
+ [22] = "Assist emulation trap",
+ [25] = "Taken branch trap",
+ [26] = "Data memory access rights trap",
+ [27] = "Data memory protection ID trap",
+ [28] = "Unaligned data reference trap",
};
const char *trap_name(unsigned long code)
void *parisc_vmalloc_start __ro_after_init;
EXPORT_SYMBOL(parisc_vmalloc_start);
-#ifdef CONFIG_PA11
-unsigned long pcxl_dma_start __ro_after_init;
-#endif
-
void __init mem_init(void)
{
/* Do sanity checks on IPC (compat) structures */
*/
void __iomem *ioremap(unsigned long phys_addr, unsigned long size)
{
- void __iomem *addr;
+ uintptr_t addr;
struct vm_struct *area;
unsigned long offset, last_addr;
pgprot_t pgprot;
if (!area)
return NULL;
- addr = (void __iomem *) area->addr;
- if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
- phys_addr, pgprot)) {
- vunmap(addr);
+ addr = (uintptr_t) area->addr;
+ if (ioremap_page_range(addr, addr + size, phys_addr, pgprot)) {
+ vunmap(area->addr);
return NULL;
}
*/
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
static inline void prefetch(const void *x)
{
__asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x));
}
-#define spin_lock_prefetch(x) prefetchw(x)
-
/* asm stubs */
extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
#define flush_icache_user_page(vma, pg, addr, len) \
flush_icache_mm(vma->vm_mm, 0)
+#ifdef CONFIG_64BIT
+#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end)
+#endif
+
#ifndef CONFIG_SMP
#define flush_icache_all() local_flush_icache_all()
* Relaxed I/O memory access primitives. These follow the Device memory
* ordering rules but do not guarantee any ordering relative to Normal memory
* accesses. These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
- * fences are required to enforce this ordering.
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
*/
/* FIXME: These are now the same as asm-generic */
#define __io_rbr() do {} while (0)
#endif
/*
- * I/O memory access primitives. Reads are ordered relative to any
- * following Normal memory access. Writes are ordered relative to any prior
- * Normal memory access. The memory barriers here are necessary as RISC-V
+ * I/O memory access primitives. Reads are ordered relative to any following
+ * Normal memory read and delay() loop. Writes are ordered relative to any
+ * prior Normal memory write. The memory barriers here are necessary as RISC-V
* doesn't define any ordering between the memory space and the I/O space.
*/
#define __io_br() do {} while (0)
-#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory")
-#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
+#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
#define __io_aw() mmiowb_set_pending()
#define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
#define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP)
extern pgd_t swapper_pg_dir[];
+extern pgd_t trampoline_pg_dir[];
+extern pgd_t early_pg_dir[];
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_present(pmd_t pmd)
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+extern bool pgtable_l4_enabled, pgtable_l5_enabled;
+
#define IOREMAP_MAX_ORDER (PUD_SHIFT)
#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
- return true;
+ return pgtable_l4_enabled || pgtable_l5_enabled;
}
#define arch_vmap_pmd_supported arch_vmap_pmd_supported
#include <asm/smp.h>
#include <asm/pgtable.h>
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+ return phys_id == cpuid_to_hartid_map(cpu);
+}
+
/*
* Returns the hart ID of the given device tree node, or -ENODEV if the node
* isn't an enabled and valid RISC-V hart node.
kbuf.buffer = initrd;
kbuf.bufsz = kbuf.memsz = initrd_len;
kbuf.buf_align = PAGE_SIZE;
- kbuf.top_down = false;
+ kbuf.top_down = true;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
if (ret)
* sym, instead of searching the whole relsec.
*/
case R_RISCV_PCREL_HI20:
+ case R_RISCV_CALL_PLT:
case R_RISCV_CALL:
*(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) |
ENCODE_UJTYPE_IMM(val - addr);
return -ENOENT;
}
-bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
-{
- return phys_id == cpuid_to_hartid_map(cpu);
-}
-
static void ipi_stop(void)
{
set_cpu_online(smp_processor_id(), false);
#include <linux/kfence.h>
#include <asm/fixmap.h>
-#include <asm/tlbflush.h>
-#include <asm/sections.h>
-#include <asm/soc.h>
#include <asm/io.h>
-#include <asm/ptdump.h>
#include <asm/numa.h>
+#include <asm/pgtable.h>
+#include <asm/ptdump.h>
+#include <asm/sections.h>
+#include <asm/soc.h>
+#include <asm/tlbflush.h>
#include "../kernel/head.h"
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
phys_ram_end = memblock_end_of_DRAM();
+
+ /*
+ * Make sure we align the start of the memory on a PMD boundary so that
+ * at worst, we map the linear mapping with PMD mappings.
+ */
if (!IS_ENABLED(CONFIG_XIP_KERNEL))
- phys_ram_base = memblock_start_of_DRAM();
+ phys_ram_base = memblock_start_of_DRAM() & PMD_MASK;
/*
* In 64-bit, any use of __va/__pa before this point is wrong as we
* region is not and then we have to go down to the PUD level.
*/
-extern pgd_t early_pg_dir[PTRS_PER_PGD];
pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;
*/
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
static inline void prefetch(const void *x)
{
: "r" (x));
}
-#define spin_lock_prefetch(x) prefetchw(x)
-
#define HAVE_ARCH_PICK_MMAP_LAYOUT
int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap);
set_idt_entry(X86_TRAP_PF, boot_page_fault);
#ifdef CONFIG_AMD_MEM_ENCRYPT
- set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+ /*
+ * Clear the second stage #VC handler in case guest types
+ * needing #VC have not been detected.
+ */
+ if (sev_status & BIT(1))
+ set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+ else
+ set_idt_entry(X86_TRAP_VC, NULL);
#endif
load_boot_idt(&boot_idt_desc);
bp->cc_blob_address = 0;
/*
+ * Do an initial SEV capability check before snp_init() which
+ * loads the CPUID page and the same checks afterwards are done
+ * without the hypervisor and are trustworthy.
+ *
+ * If the HV fakes SEV support, the guest will crash'n'burn
+ * which is good enough.
+ */
+
+ /* Check for the SME/SEV support leaf */
+ eax = 0x80000000;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (eax < 0x8000001f)
+ return;
+
+ /*
+ * Check for the SME/SEV feature:
+ * CPUID Fn8000_001F[EAX]
+ * - Bit 0 - Secure Memory Encryption support
+ * - Bit 1 - Secure Encrypted Virtualization support
+ * CPUID Fn8000_001F[EBX]
+ * - Bits 5:0 - Pagetable bit position used to indicate encryption
+ */
+ eax = 0x8000001f;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ /* Check whether SEV is supported */
+ if (!(eax & BIT(1)))
+ return;
+
+ /*
* Setup/preliminary detection of SNP. This will be sanity-checked
* against CPUID/MSR values later.
*/
snp = snp_init(bp);
- /* Check for the SME/SEV support leaf */
+ /* Now repeat the checks with the SNP CPUID table. */
+
+ /* Recheck the SME/SEV support leaf */
eax = 0x80000000;
ecx = 0;
native_cpuid(&eax, &ebx, &ecx, &edx);
return;
/*
- * Check for the SME/SEV feature:
+ * Recheck for the SME/SEV feature:
* CPUID Fn8000_001F[EAX]
* - Bit 0 - Secure Memory Encryption support
* - Bit 1 - Secure Encrypted Virtualization support
/* Round the lowest possible end address up to a PMD boundary. */
end = (start + len + PMD_SIZE - 1) & PMD_MASK;
- if (end >= TASK_SIZE_MAX)
- end = TASK_SIZE_MAX;
+ if (end >= DEFAULT_MAP_WINDOW)
+ end = DEFAULT_MAP_WINDOW;
end -= len;
if (end > start) {
#include <asm/mpspec.h>
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
+#include <asm/irq_vectors.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
extern int acpi_use_timer_override;
extern int acpi_fix_pin2_polarity;
extern int acpi_disable_cmcff;
+extern bool acpi_int_src_ovr[NR_IRQS_LEGACY];
extern u8 acpi_sci_flags;
extern u32 acpi_sci_override_gsi;
#define FUNCTION_PADDING
#endif
-#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BULID_VDSO)
+#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
# define __FUNC_ALIGN __ALIGN; FUNCTION_PADDING
#else
# define __FUNC_ALIGN __ALIGN
#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
#ifdef CONFIG_X86_32
# define BASE_PREFETCH ""
"m" (*(const char *)x));
}
-static inline void spin_lock_prefetch(const void *x)
-{
- prefetchw(x);
-}
-
#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
TOP_OF_KERNEL_STACK_PADDING)
#define GDT_ENTRY_INVALID_SEG 0
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && !defined(BUILD_VDSO32_64)
/*
* The layout of the per-CPU GDT under Linux:
*
int acpi_ioapic;
int acpi_strict;
int acpi_disable_cmcff;
+bool acpi_int_src_ovr[NR_IRQS_LEGACY];
/* ACPI SCI override configuration */
u8 acpi_sci_flags __initdata;
acpi_table_print_madt_entry(&header->common);
+ if (intsrc->source_irq < NR_IRQS_LEGACY)
+ acpi_int_src_ovr[intsrc->source_irq] = true;
+
if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) {
acpi_sci_ioapic_setup(intsrc->source_irq,
intsrc->inti_flags & ACPI_MADT_POLARITY_MASK,
static const int amd_zenbleed[] =
AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
+ AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf),
AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
static const int amd_div0[] =
struct block_device *bdev = bio->bi_bdev;
struct request_queue *q = bdev_get_queue(bdev);
blk_status_t status = BLK_STS_IOERR;
- struct blk_plug *plug;
might_sleep();
- plug = blk_mq_plug(bio);
- if (plug && plug->nowait)
- bio->bi_opf |= REQ_NOWAIT;
-
/*
* For a REQ_NOWAIT based request, return -EOPNOTSUPP
* if queue does not support NOWAIT.
plug->rq_count = 0;
plug->multiple_queues = false;
plug->has_elevator = false;
- plug->nowait = false;
INIT_LIST_HEAD(&plug->cb_list);
/*
if (qos[QOS_MIN] > qos[QOS_MAX])
goto einval;
- if (enable) {
+ if (enable && !ioc->enabled) {
blk_stat_enable_accounting(disk->queue);
blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue);
ioc->enabled = true;
- } else {
+ } else if (!enable && ioc->enabled) {
+ blk_stat_disable_accounting(disk->queue);
blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue);
ioc->enabled = false;
}
task_io_account_write(bio->bi_iter.bi_size);
}
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio->bi_opf |= REQ_NOWAIT;
+
if (iocb->ki_flags & IOCB_HIPRI) {
- bio->bi_opf |= REQ_POLLED | REQ_NOWAIT;
+ bio->bi_opf |= REQ_POLLED;
submit_bio(bio);
WRITE_ONCE(iocb->private, bio);
} else {
- if (iocb->ki_flags & IOCB_NOWAIT)
- bio->bi_opf |= REQ_NOWAIT;
submit_bio(bio);
}
return -EIOCBQUEUED;
{
unsigned int i, npages = bo->base.size >> PAGE_SHIFT;
+ if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
+ set_pages_array_wb(bo->pages, bo->base.size >> PAGE_SHIFT);
+
for (i = 0; i < npages; i++)
put_page(bo->pages[i]);
if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
drm_clflush_pages(bo->pages, bo->base.size >> PAGE_SHIFT);
+ if (bo->flags & DRM_IVPU_BO_WC)
+ set_pages_array_wc(bo->pages, bo->base.size >> PAGE_SHIFT);
+ else if (bo->flags & DRM_IVPU_BO_UNCACHED)
+ set_pages_array_uc(bo->pages, bo->base.size >> PAGE_SHIFT);
+
prot = ivpu_bo_pgprot(bo, PAGE_KERNEL);
bo->kvaddr = vmap(bo->pages, bo->base.size >> PAGE_SHIFT, VM_MAP, prot);
if (!bo->kvaddr) {
struct qaic_manage_trans_dma_xfer *in_trans,
struct ioctl_resources *resources, struct dma_xfer *xfer)
{
+ u64 xfer_start_addr, remaining, end, total;
unsigned long need_pages;
struct page **page_list;
unsigned long nr_pages;
struct sg_table *sgt;
- u64 xfer_start_addr;
int ret;
int i;
- xfer_start_addr = in_trans->addr + resources->xferred_dma_size;
+ if (check_add_overflow(in_trans->addr, resources->xferred_dma_size, &xfer_start_addr))
+ return -EINVAL;
- need_pages = DIV_ROUND_UP(in_trans->size + offset_in_page(xfer_start_addr) -
- resources->xferred_dma_size, PAGE_SIZE);
+ if (in_trans->size < resources->xferred_dma_size)
+ return -EINVAL;
+ remaining = in_trans->size - resources->xferred_dma_size;
+ if (remaining == 0)
+ return 0;
+
+ if (check_add_overflow(xfer_start_addr, remaining, &end))
+ return -EINVAL;
+
+ total = remaining + offset_in_page(xfer_start_addr);
+ if (total >= SIZE_MAX)
+ return -EINVAL;
+
+ need_pages = DIV_ROUND_UP(total, PAGE_SIZE);
nr_pages = need_pages;
ret = sg_alloc_table_from_pages(sgt, page_list, nr_pages,
offset_in_page(xfer_start_addr),
- in_trans->size - resources->xferred_dma_size, GFP_KERNEL);
+ remaining, GFP_KERNEL);
if (ret) {
ret = -ENOMEM;
goto free_sgt;
QAIC_MANAGE_EXT_MSG_LENGTH)
return -ENOMEM;
- if (in_trans->addr + in_trans->size < in_trans->addr || !in_trans->size)
- return -EINVAL;
-
xfer = kmalloc(sizeof(*xfer), GFP_KERNEL);
if (!xfer)
return -ENOMEM;
bo->dbc = dbc;
srcu_read_unlock(&dbc->ch_lock, rcu_id);
drm_gem_object_put(obj);
+ kfree(slice_ent);
srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
{ }
};
+static const struct dmi_system_id tongfang_gm_rg[] = {
+ {
+ .ident = "TongFang GMxRGxx/XMG CORE 15 (M22)/TUXEDO Stellaris 15 Gen4 AMD",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"),
+ },
+ },
+ { }
+};
+
+static const struct dmi_system_id maingear_laptop[] = {
+ {
+ .ident = "MAINGEAR Vector Pro 2 15",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Micro Electronics Inc"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-15A3070T"),
+ }
+ },
+ {
+ .ident = "MAINGEAR Vector Pro 2 17",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Micro Electronics Inc"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-17A3070T"),
+ },
+ },
+ { }
+};
+
+static const struct dmi_system_id pcspecialist_laptop[] = {
+ {
+ .ident = "PCSpecialist Elimina Pro 16 M",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Elimina Pro 16 M"),
+ },
+ },
+ { }
+};
+
static const struct dmi_system_id lg_laptop[] = {
{
.ident = "LG Electronics 17U70P",
static const struct irq_override_cmp override_table[] = {
{ medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
{ asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
+ { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
+ { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
+ { pcspecialist_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
{ lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
};
return entry->override;
}
+#ifdef CONFIG_X86
+ /*
+ * Always use the MADT override info, except for the i8042 PS/2 ctrl
+ * IRQs (1 and 12). For these the DSDT IRQ settings should sometimes
+ * be used otherwise PS/2 keyboards / mice will not work.
+ */
+ if (gsi != 1 && gsi != 12)
+ return true;
+
+ /* If the override comes from an INT_SRC_OVR MADT entry, honor it. */
+ if (acpi_int_src_ovr[gsi])
+ return true;
+
+ /*
+ * IRQ override isn't needed on modern AMD Zen systems and
+ * this override breaks active low IRQs on AMD Ryzen 6000 and
+ * newer systems. Skip it.
+ */
+ if (boot_cpu_has(X86_FEATURE_ZEN))
+ return false;
+#endif
+
return true;
}
{"BSG1160", },
{"BSG2150", },
{"CSC3551", },
+ {"CSC3556", },
{"INT33FE", },
{"INT3515", },
/* Non-conforming _HID for Cirrus Logic already released */
err_alloc_device_names_failed:
debugfs_remove_recursive(binder_debugfs_dir_entry_root);
+ binder_alloc_shrinker_exit();
return ret;
}
return ret;
}
+void binder_alloc_shrinker_exit(void)
+{
+ unregister_shrinker(&binder_shrinker);
+ list_lru_destroy(&binder_alloc_lru);
+}
+
/**
* check_buffer() - verify that buffer/offset is safe to access
* @alloc: binder_alloc for this proc
int pid);
extern void binder_alloc_init(struct binder_alloc *alloc);
extern int binder_alloc_shrinker_init(void);
+extern void binder_alloc_shrinker_exit(void);
extern void binder_alloc_vma_close(struct binder_alloc *alloc);
extern struct binder_buffer *
binder_alloc_prepare_to_free(struct binder_alloc *alloc,
CPU_SHOW_VULN_FALLBACK(mmio_stale_data);
CPU_SHOW_VULN_FALLBACK(retbleed);
CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
-CPU_SHOW_VULN_FALLBACK(gather_data_sampling);
+CPU_SHOW_VULN_FALLBACK(gds);
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL);
-static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gather_data_sampling, NULL);
+static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
static void zram_bio_read(struct zram *zram, struct bio *bio)
{
- struct bvec_iter iter;
- struct bio_vec bv;
- unsigned long start_time;
+ unsigned long start_time = bio_start_io_acct(bio);
+ struct bvec_iter iter = bio->bi_iter;
- start_time = bio_start_io_acct(bio);
- bio_for_each_segment(bv, bio, iter) {
+ do {
u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) <<
SECTOR_SHIFT;
+ struct bio_vec bv = bio_iter_iovec(bio, iter);
+
+ bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset);
if (zram_bvec_read(zram, &bv, index, offset, bio) < 0) {
atomic64_inc(&zram->stats.failed_reads);
zram_slot_lock(zram, index);
zram_accessed(zram, index);
zram_slot_unlock(zram, index);
- }
+
+ bio_advance_iter_single(bio, &iter, bv.bv_len);
+ } while (iter.bi_size);
+
bio_end_io_acct(bio, start_time);
bio_endio(bio);
}
static void zram_bio_write(struct zram *zram, struct bio *bio)
{
- struct bvec_iter iter;
- struct bio_vec bv;
- unsigned long start_time;
+ unsigned long start_time = bio_start_io_acct(bio);
+ struct bvec_iter iter = bio->bi_iter;
- start_time = bio_start_io_acct(bio);
- bio_for_each_segment(bv, bio, iter) {
+ do {
u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) <<
SECTOR_SHIFT;
+ struct bio_vec bv = bio_iter_iovec(bio, iter);
+
+ bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset);
if (zram_bvec_write(zram, &bv, index, offset, bio) < 0) {
atomic64_inc(&zram->stats.failed_writes);
zram_slot_lock(zram, index);
zram_accessed(zram, index);
zram_slot_unlock(zram, index);
- }
+
+ bio_advance_iter_single(bio, &iter, bv.bv_len);
+ } while (iter.bi_size);
+
bio_end_io_acct(bio, start_time);
bio_endio(bio);
}
tpm_tis_flush(iobase);
}
-static int interrupts = -1;
+static int interrupts;
module_param(interrupts, int, 0444);
MODULE_PARM_DESC(interrupts, "Enable interrupts");
.ident = "UPX-TGL",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "AAEON"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "UPX-TGL"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "UPX-TGL01"),
},
},
{}
# Counter devices
#
-menuconfig COUNTER
- tristate "Counter support"
- help
- This enables counter device support through the Generic Counter
- interface. You only need to enable this, if you also want to enable
- one or more of the counter device drivers below.
-
config I8254
tristate
select COUNTER
If built as a module its name will be i8254.
+menuconfig COUNTER
+ tristate "Counter support"
+ help
+ This enables counter device support through the Generic Counter
+ interface. You only need to enable this, if you also want to enable
+ one or more of the counter device drivers below.
+
if COUNTER
config 104_QUAD_8
return 0;
}
-static ssize_t show_status(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
+static ssize_t status_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
ssize_t ret;
return ret;
}
-static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
+static ssize_t status_store(struct device *a, struct device_attribute *b,
const char *buf, size_t count)
{
char *p = memchr(buf, '\n', count);
cpufreq_freq_attr_ro(amd_pstate_highest_perf);
cpufreq_freq_attr_rw(energy_performance_preference);
cpufreq_freq_attr_ro(energy_performance_available_preferences);
-define_one_global_rw(status);
+static DEVICE_ATTR_RW(status);
static struct freq_attr *amd_pstate_attr[] = {
&amd_pstate_max_freq,
};
static struct attribute *pstate_global_attributes[] = {
- &status.attr,
+ &dev_attr_status.attr,
NULL
};
}
}
-static bool psci_pd_try_set_osi_mode(void)
-{
- int ret;
-
- if (!psci_has_osi_support())
- return false;
-
- ret = psci_set_osi_mode(true);
- if (ret)
- return false;
-
- return true;
-}
-
static void psci_cpuidle_domain_sync_state(struct device *dev)
{
/*
{
struct device_node *np = pdev->dev.of_node;
struct device_node *node;
- bool use_osi;
+ bool use_osi = psci_has_osi_support();
int ret = 0, pd_count = 0;
if (!np)
return -ENODEV;
- /* If OSI mode is supported, let's try to enable it. */
- use_osi = psci_pd_try_set_osi_mode();
-
/*
* Parse child nodes for the "#power-domain-cells" property and
* initialize a genpd/genpd-of-provider pair when it's found.
continue;
ret = psci_pd_init(node, use_osi);
- if (ret)
- goto put_node;
+ if (ret) {
+ of_node_put(node);
+ goto exit;
+ }
pd_count++;
}
/* Bail out if not using the hierarchical CPU topology. */
if (!pd_count)
- goto no_pd;
+ return 0;
/* Link genpd masters/subdomains to model the CPU topology. */
ret = dt_idle_pd_init_topology(np);
if (ret)
goto remove_pd;
+ /* let's try to enable OSI. */
+ ret = psci_set_osi_mode(use_osi);
+ if (ret)
+ goto remove_pd;
+
pr_info("Initialized CPU PM domain topology using %s mode\n",
use_osi ? "OSI" : "PC");
return 0;
-put_node:
- of_node_put(node);
remove_pd:
+ dt_idle_pd_remove_topology(np);
psci_pd_remove();
+exit:
pr_err("failed to create CPU PM domains ret=%d\n", ret);
-no_pd:
- if (use_osi)
- psci_set_osi_mode(false);
return ret;
}
return 0;
}
+int dt_idle_pd_remove_topology(struct device_node *np)
+{
+ struct device_node *node;
+ struct of_phandle_args child, parent;
+ int ret;
+
+ for_each_child_of_node(np, node) {
+ if (of_parse_phandle_with_args(node, "power-domains",
+ "#power-domain-cells", 0, &parent))
+ continue;
+
+ child.np = node;
+ child.args_count = 0;
+ ret = of_genpd_remove_subdomain(&parent, &child);
+ of_node_put(parent.np);
+ if (ret) {
+ of_node_put(node);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
struct device *dt_idle_attach_cpu(int cpu, const char *name)
{
struct device *dev;
int dt_idle_pd_init_topology(struct device_node *np);
+int dt_idle_pd_remove_topology(struct device_node *np);
+
struct device *dt_idle_attach_cpu(int cpu, const char *name);
void dt_idle_detach_cpu(struct device *dev);
return 0;
}
+static inline int dt_idle_pd_remove_topology(struct device_node *np)
+{
+ return 0;
+}
+
static inline struct device *dt_idle_attach_cpu(int cpu, const char *name)
{
return NULL;
gc->set_config = gpio_sim_set_config;
gc->to_irq = gpio_sim_to_irq;
gc->free = gpio_sim_free;
+ gc->can_sleep = true;
ret = devm_gpiochip_add_data(dev, gc, chip);
if (ret)
#include <linux/spinlock.h>
#include <linux/types.h>
-#define WS16C48_EXTENT 10
+#define WS16C48_EXTENT 11
#define MAX_NUM_WS16C48 max_num_isa_dev(WS16C48_EXTENT)
static unsigned int base[MAX_NUM_WS16C48];
void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
int amdgpu_device_pci_reset(struct amdgpu_device *adev);
bool amdgpu_device_need_post(struct amdgpu_device *adev);
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev);
bool amdgpu_device_pcie_dynamic_switching_supported(void);
bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
bool amdgpu_device_aspm_support_quirk(void);
if (!p->gang_size) {
ret = -EINVAL;
- goto free_partial_kdata;
+ goto free_all_kdata;
}
for (i = 0; i < p->gang_size; ++i) {
}
/*
+ * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
+ * Disable S/G on such systems until we have a proper fix.
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
+ */
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
+{
+ switch (amdgpu_sg_display) {
+ case -1:
+ break;
+ case 0:
+ return false;
+ case 1:
+ return true;
+ default:
+ return false;
+ }
+ if ((totalram_pages() << (PAGE_SHIFT - 10)) +
+ (adev->gmc.real_vram_size / 1024) >= 64000000) {
+ DRM_WARN("Disabling S/G due to >=64GB RAM\n");
+ return false;
+ }
+ return true;
+}
+
+/*
* Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
* speed switching. Until we have confirmation from Intel that a specific host
* supports it, it's safer that we keep it disabled for all.
{
if (amdgpu_mcbp == 1)
adev->gfx.mcbp = true;
-
- if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
- (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
- adev->gfx.num_gfx_rings)
+ else if (amdgpu_mcbp == 0)
+ adev->gfx.mcbp = false;
+ else if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
+ (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
+ adev->gfx.num_gfx_rings)
adev->gfx.mcbp = true;
if (amdgpu_sriov_vf(adev))
drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
cancel_delayed_work_sync(&adev->delayed_init_work);
+ flush_delayed_work(&adev->gfx.gfx_off_delay_work);
amdgpu_ras_suspend(adev);
}
/**
+ * amdgpu_fence_need_ring_interrupt_restore - helper function to check whether
+ * fence driver interrupts need to be restored.
+ *
+ * @ring: ring that to be checked
+ *
+ * Interrupts for rings that belong to GFX IP don't need to be restored
+ * when the target power state is s0ix.
+ *
+ * Return true if need to restore interrupts, false otherwise.
+ */
+static bool amdgpu_fence_need_ring_interrupt_restore(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+ bool is_gfx_power_domain = false;
+
+ switch (ring->funcs->type) {
+ case AMDGPU_RING_TYPE_SDMA:
+ /* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */
+ if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0))
+ is_gfx_power_domain = true;
+ break;
+ case AMDGPU_RING_TYPE_GFX:
+ case AMDGPU_RING_TYPE_COMPUTE:
+ case AMDGPU_RING_TYPE_KIQ:
+ case AMDGPU_RING_TYPE_MES:
+ is_gfx_power_domain = true;
+ break;
+ default:
+ break;
+ }
+
+ return !(adev->in_s0ix && is_gfx_power_domain);
+}
+
+/**
* amdgpu_fence_driver_hw_fini - tear down the fence driver
* for all possible rings.
*
amdgpu_fence_driver_force_completion(ring);
if (!drm_dev_is_unplugged(adev_to_drm(adev)) &&
- ring->fence_drv.irq_src)
+ ring->fence_drv.irq_src &&
+ amdgpu_fence_need_ring_interrupt_restore(ring))
amdgpu_irq_put(adev, ring->fence_drv.irq_src,
ring->fence_drv.irq_type);
continue;
/* enable the interrupt */
- if (ring->fence_drv.irq_src)
+ if (ring->fence_drv.irq_src &&
+ amdgpu_fence_need_ring_interrupt_restore(ring))
amdgpu_irq_get(adev, ring->fence_drv.irq_src,
ring->fence_drv.irq_type);
}
if (adev->gfx.gfx_off_req_count == 0 &&
!adev->gfx.gfx_off_state) {
- /* If going to s2idle, no need to wait */
- if (adev->in_s0ix) {
- if (!amdgpu_dpm_set_powergating_by_smu(adev,
- AMD_IP_BLOCK_TYPE_GFX, true))
- adev->gfx.gfx_off_state = true;
- } else {
- schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+ schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
delay);
- }
}
} else {
if (adev->gfx.gfx_off_req_count == 0) {
struct amdgpu_ring_mux *mux = &adev->gfx.muxer;
WARN_ON(!ring->is_sw_ring);
- if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) {
+ if (adev->gfx.mcbp && ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) {
if (amdgpu_mcbp_scan(mux) > 0)
amdgpu_mcbp_trigger_preempt(mux);
return;
for (i = 1; i < MAX_XCP; i++) {
ret = amdgpu_xcp_drm_dev_alloc(&p_ddev);
- if (ret)
+ if (ret == -ENOSPC) {
+ dev_warn(adev->dev,
+ "Skip xcp node #%d when out of drm node resource.", i);
+ return 0;
+ } else if (ret) {
return ret;
+ }
/* Redirect all IOCTLs to the primary device */
adev->xcp_mgr->xcp[i].rdev = p_ddev->render->dev;
return 0;
for (i = 1; i < MAX_XCP; i++) {
+ if (!adev->xcp_mgr->xcp[i].ddev)
+ break;
+
ret = drm_dev_register(adev->xcp_mgr->xcp[i].ddev, ent->driver_data);
if (ret)
return ret;
return;
for (i = 1; i < MAX_XCP; i++) {
+ if (!adev->xcp_mgr->xcp[i].ddev)
+ break;
+
p_ddev = adev->xcp_mgr->xcp[i].ddev;
drm_dev_unplug(p_ddev);
p_ddev->render->dev = adev->xcp_mgr->xcp[i].rdev;
case IP_VERSION(11, 0, 3):
if ((adev->gfx.me_fw_version >= 1505) &&
(adev->gfx.pfp_fw_version >= 1600) &&
- (adev->gfx.mec_fw_version >= 512))
- adev->gfx.cp_gfx_shadow = true;
+ (adev->gfx.mec_fw_version >= 512)) {
+ if (amdgpu_sriov_vf(adev))
+ adev->gfx.cp_gfx_shadow = true;
+ else
+ adev->gfx.cp_gfx_shadow = false;
+ }
break;
default:
adev->gfx.cp_gfx_shadow = false;
int ret;
int retry_loop;
+ /* Wait for bootloader to signify that it is ready having bit 31 of
+ * C2PMSG_35 set to 1. All other bits are expected to be cleared.
+ * If there is an error in processing command, bits[7:0] will be set.
+ * This is applicable for PSP v13.0.6 and newer.
+ */
for (retry_loop = 0; retry_loop < 10; retry_loop++) {
- /* Wait for bootloader to signify that is
- ready having bit 31 of C2PMSG_35 set to 1 */
- ret = psp_wait_for(psp,
- SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
- 0x80000000,
- 0x80000000,
- false);
+ ret = psp_wait_for(
+ psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
+ 0x80000000, 0xffffffff, false);
if (ret == 0)
return 0;
if (ignore_crat)
return true;
-#ifndef KFD_SUPPORT_IOMMU_V2
ret = true;
-#else
- ret = false;
-#endif
return ret;
}
kfd_device_info_set_event_interrupt_class(kfd);
- /* Raven */
- if (gc_version == IP_VERSION(9, 1, 0) ||
- gc_version == IP_VERSION(9, 2, 2))
- kfd->device_info.needs_iommu_device = true;
-
if (gc_version < IP_VERSION(11, 0, 0)) {
/* Navi2x+, Navi1x+ */
if (gc_version == IP_VERSION(10, 3, 6))
asic_type != CHIP_TONGA)
kfd->device_info.supports_cwsr = true;
- if (asic_type == CHIP_KAVERI ||
- asic_type == CHIP_CARRIZO)
- kfd->device_info.needs_iommu_device = true;
-
if (asic_type != CHIP_HAWAII && !vf)
kfd->device_info.needs_pci_atomics = true;
}
uint32_t gfx_target_version = 0;
switch (adev->asic_type) {
-#ifdef KFD_SUPPORT_IOMMU_V2
#ifdef CONFIG_DRM_AMDGPU_CIK
case CHIP_KAVERI:
gfx_target_version = 70000;
if (!vf)
f2g = &gfx_v8_kfd2kgd;
break;
-#endif
#ifdef CONFIG_DRM_AMDGPU_CIK
case CHIP_HAWAII:
gfx_target_version = 70001;
gfx_target_version = 90000;
f2g = &gfx_v9_kfd2kgd;
break;
-#ifdef KFD_SUPPORT_IOMMU_V2
/* Raven */
case IP_VERSION(9, 1, 0):
case IP_VERSION(9, 2, 2):
if (!vf)
f2g = &gfx_v9_kfd2kgd;
break;
-#endif
/* Vega12 */
case IP_VERSION(9, 2, 1):
gfx_target_version = 90004;
}
switch (dev->adev->asic_type) {
- case CHIP_CARRIZO:
- device_queue_manager_init_vi(&dqm->asic_ops);
- break;
-
case CHIP_KAVERI:
- device_queue_manager_init_cik(&dqm->asic_ops);
- break;
-
case CHIP_HAWAII:
device_queue_manager_init_cik_hawaii(&dqm->asic_ops);
break;
+ case CHIP_CARRIZO:
case CHIP_TONGA:
case CHIP_FIJI:
case CHIP_POLARIS10:
const char *asic_name = amdgpu_asic_name[gpu->adev->asic_type];
gpu_id = kfd_generate_gpu_id(gpu);
- pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
+ if (gpu->xcp && !gpu->xcp->ddev) {
+ dev_warn(gpu->adev->dev,
+ "Won't add GPU (ID: 0x%x) to topology since it has no drm node assigned.",
+ gpu_id);
+ return 0;
+ } else {
+ pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
+ }
/* Check to see if this gpu device exists in the topology_device_list.
* If so, assign the gpu to that device,
}
break;
}
- if (init_data.flags.gpu_vm_support &&
- (amdgpu_sg_display == 0))
- init_data.flags.gpu_vm_support = false;
+ if (init_data.flags.gpu_vm_support)
+ init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev);
if (init_data.flags.gpu_vm_support)
adev->mode_info.gpu_vm_support = true;
if (computed_streams[i])
continue;
- if (!res_pool->funcs->remove_stream_from_ctx ||
+ if (res_pool->funcs->remove_stream_from_ctx &&
res_pool->funcs->remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK)
return -EINVAL;
dal_gpio_destroy_irq(&hpd);
/* ensure that the panel is detected */
- ASSERT(edp_hpd_high);
+ if (!edp_hpd_high)
+ DC_LOG_DC("%s: wait timed out!\n", __func__);
}
void dce110_edp_power_control(
.timing_trace = false,
.clock_trace = true,
.disable_pplib_clock_request = true,
- .pipe_split_policy = MPC_SPLIT_DYNAMIC,
+ .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
.force_single_disp_pipe_split = false,
.disable_dcc = DCC_ENABLE,
.vsr_support = true,
int cur_rom_en = 0;
if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
- color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA)
- cur_rom_en = 1;
+ color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
+ if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
+ cur_rom_en = 1;
+ }
+ }
REG_UPDATE_3(CURSOR0_CONTROL,
CUR0_MODE, color_format,
/*
* For SMU 13.0.4/11, PMFW will handle the features disablement properly
- * for gpu reset case. Driver involvement is unnecessary.
+ * for gpu reset and S0i3 cases. Driver involvement is unnecessary.
*/
- if (amdgpu_in_reset(adev)) {
+ if (amdgpu_in_reset(adev) || adev->in_s0ix) {
switch (adev->ip_versions[MP1_HWIP][0]) {
case IP_VERSION(13, 0, 4):
case IP_VERSION(13, 0, 11):
return -ENOMEM;
}
-static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu)
+static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu,
+ bool use_metrics_v3,
+ bool use_metrics_v2)
{
struct smu_table_context *smu_table= &smu->smu_table;
SmuMetricsExternal_t *metrics_ext =
uint32_t throttler_status = 0;
int i;
- if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) &&
- (smu->smc_fw_version >= 0x3A4900)) {
+ if (use_metrics_v3) {
for (i = 0; i < THROTTLER_COUNT; i++)
throttler_status |=
(metrics_ext->SmuMetrics_V3.ThrottlingPercentage[i] ? 1U << i : 0);
- } else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) &&
- (smu->smc_fw_version >= 0x3A4300)) {
+ } else if (use_metrics_v2) {
for (i = 0; i < THROTTLER_COUNT; i++)
throttler_status |=
(metrics_ext->SmuMetrics_V2.ThrottlingPercentage[i] ? 1U << i : 0);
metrics->TemperatureVrSoc) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
break;
case METRICS_THROTTLER_STATUS:
- *value = sienna_cichlid_get_throttler_status_locked(smu);
+ *value = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2);
break;
case METRICS_CURR_FANSPEED:
*value = use_metrics_v3 ? metrics_v3->CurrFanSpeed :
gpu_metrics->current_dclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] :
use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1];
- gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu);
+ gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2);
gpu_metrics->indep_throttle_status =
smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status,
sienna_cichlid_throttler_map);
table_context->power_play_table;
struct smu_baco_context *smu_baco = &smu->smu_baco;
PPTable_t *pptable = smu->smu_table.driver_pptable;
+#if 0
+ PPTable_t *pptable = smu->smu_table.driver_pptable;
const OverDriveLimits_t * const overdrive_upperlimits =
&pptable->SkuTable.OverDriveLimitsBasicMax;
const OverDriveLimits_t * const overdrive_lowerlimits =
&pptable->SkuTable.OverDriveLimitsMin;
+#endif
if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC)
smu->dc_controlled_by_gpio = true;
if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO)
smu_baco->maco_support = true;
+ /*
+ * We are in the transition to a new OD mechanism.
+ * Disable the OD feature support for SMU13 temporarily.
+ * TODO: get this reverted when new OD mechanism online
+ */
+#if 0
if (!overdrive_lowerlimits->FeatureCtrlMask ||
!overdrive_upperlimits->FeatureCtrlMask)
smu->od_enabled = false;
- table_context->thermal_controller_type =
- powerplay_table->thermal_controller_type;
-
/*
* Instead of having its own buffer space and get overdrive_table copied,
* smu->od_settings just points to the actual overdrive_table
*/
smu->od_settings = &powerplay_table->overdrive_table;
+#else
+ smu->od_enabled = false;
+#endif
+
+ table_context->thermal_controller_type =
+ powerplay_table->thermal_controller_type;
+
+ smu->adev->pm.no_fan =
+ !(pptable->SkuTable.FeaturesToRun[0] & (1 << FEATURE_FAN_CONTROL_BIT));
return 0;
}
(OverDriveTableExternal_t *)smu->smu_table.overdrive_table;
struct smu_13_0_dpm_table *single_dpm_table;
struct smu_13_0_pcie_table *pcie_table;
- const int link_width[] = {0, 1, 2, 4, 8, 12, 16};
uint32_t gen_speed, lane_width;
int i, curr_freq, size = 0;
int32_t min_value, max_value;
(pcie_table->pcie_lane[i] == 6) ? "x16" : "",
pcie_table->clk_freq[i],
(gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) &&
- (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ?
+ (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ?
"*" : "");
break;
#define EPSILON 1
#define smnPCIE_ESM_CTRL 0x193D0
-#define smnPCIE_LC_LINK_WIDTH_CNTL 0x1ab40288
+#define smnPCIE_LC_LINK_WIDTH_CNTL 0x1a340288
#define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L
#define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4
+#define MAX_LINK_WIDTH 6
static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COUNT] = {
MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0),
*value = SMUQ10_TO_UINT(metrics->SocketPower) << 8;
break;
case METRICS_TEMPERATURE_HOTSPOT:
- *value = SMUQ10_TO_UINT(metrics->MaxSocketTemperature);
+ *value = SMUQ10_TO_UINT(metrics->MaxSocketTemperature) *
+ SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
break;
case METRICS_TEMPERATURE_MEM:
- *value = SMUQ10_TO_UINT(metrics->MaxHbmTemperature);
+ *value = SMUQ10_TO_UINT(metrics->MaxHbmTemperature) *
+ SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
break;
/* This is the max of all VRs and not just SOC VR.
* No need to define another data type for the same.
*/
case METRICS_TEMPERATURE_VRSOC:
- *value = SMUQ10_TO_UINT(metrics->MaxVrTemperature);
+ *value = SMUQ10_TO_UINT(metrics->MaxVrTemperature) *
+ SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
break;
default:
*value = UINT_MAX;
struct amdgpu_device *adev = smu->adev;
int ret = 0, inst0, xcc0;
MetricsTable_t *metrics;
+ u16 link_width_level;
inst0 = adev->sdma.instance[0].aid_id;
xcc0 = GET_INST(GC, 0);
gpu_metrics->average_socket_power =
SMUQ10_TO_UINT(metrics->SocketPower);
- /* Energy is reported in 15.625mJ units */
- gpu_metrics->energy_accumulator =
- SMUQ10_TO_UINT(metrics->SocketEnergyAcc);
+ /* Energy counter reported in 15.259uJ (2^-16) units */
+ gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc;
gpu_metrics->current_gfxclk =
SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]);
gpu_metrics->throttle_status = 0;
if (!(adev->flags & AMD_IS_APU)) {
+ link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu);
+ if (link_width_level > MAX_LINK_WIDTH)
+ link_width_level = 0;
+
gpu_metrics->pcie_link_width =
- smu_v13_0_6_get_current_pcie_link_width_level(smu);
+ DECODE_LANE_WIDTH(link_width_level);
gpu_metrics->pcie_link_speed =
smu_v13_0_6_get_current_pcie_link_speed(smu);
}
struct smu_baco_context *smu_baco = &smu->smu_baco;
PPTable_t *smc_pptable = table_context->driver_pptable;
BoardTable_t *BoardTable = &smc_pptable->BoardTable;
+#if 0
const OverDriveLimits_t * const overdrive_upperlimits =
&smc_pptable->SkuTable.OverDriveLimitsBasicMax;
const OverDriveLimits_t * const overdrive_lowerlimits =
&smc_pptable->SkuTable.OverDriveLimitsMin;
+#endif
if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC)
smu->dc_controlled_by_gpio = true;
if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled))
smu_baco->maco_support = true;
+#if 0
if (!overdrive_lowerlimits->FeatureCtrlMask ||
!overdrive_upperlimits->FeatureCtrlMask)
smu->od_enabled = false;
- table_context->thermal_controller_type =
- powerplay_table->thermal_controller_type;
-
/*
* Instead of having its own buffer space and get overdrive_table copied,
* smu->od_settings just points to the actual overdrive_table
*/
smu->od_settings = &powerplay_table->overdrive_table;
+#else
+ smu->od_enabled = false;
+#endif
+
+ table_context->thermal_controller_type =
+ powerplay_table->thermal_controller_type;
return 0;
}
};
int int_status[3], i;
- if (it6505->enable_drv_hold || pm_runtime_get_if_in_use(dev) <= 0)
+ if (it6505->enable_drv_hold || !it6505->powered)
return IRQ_HANDLED;
+ pm_runtime_get_sync(dev);
+
int_status[0] = it6505_read(it6505, INT_STATUS_01);
int_status[1] = it6505_read(it6505, INT_STATUS_02);
int_status[2] = it6505_read(it6505, INT_STATUS_03);
dsi->lanes = 4;
dsi->format = MIPI_DSI_FMT_RGB888;
dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
- MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_MODE_VIDEO_NO_HSA |
- MIPI_DSI_MODE_VIDEO_NO_HFP | MIPI_DSI_MODE_VIDEO_NO_HBP |
- MIPI_DSI_MODE_NO_EOT_PACKET;
+ MIPI_DSI_MODE_VIDEO_HSE;
ret = devm_mipi_dsi_attach(dev, dsi);
if (ret < 0) {
connector->base.id, connector->name);
return NULL;
}
+ if (!(pt->misc & DRM_EDID_PT_SEPARATE_SYNC)) {
+ drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Composite sync not supported\n",
+ connector->base.id, connector->name);
+ }
/* it is incorrect if hsync/vsync width is zero */
if (!hsync_pulse_width || !vsync_pulse_width) {
if (info->quirks & EDID_QUIRK_DETAILED_SYNC_PP) {
mode->flags |= DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC;
} else {
- switch (pt->misc & DRM_EDID_PT_SYNC_MASK) {
- case DRM_EDID_PT_ANALOG_CSYNC:
- case DRM_EDID_PT_BIPOLAR_ANALOG_CSYNC:
- drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Analog composite sync!\n",
- connector->base.id, connector->name);
- mode->flags |= DRM_MODE_FLAG_CSYNC | DRM_MODE_FLAG_NCSYNC;
- break;
- case DRM_EDID_PT_DIGITAL_CSYNC:
- drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Digital composite sync!\n",
- connector->base.id, connector->name);
- mode->flags |= DRM_MODE_FLAG_CSYNC;
- mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
- DRM_MODE_FLAG_PCSYNC : DRM_MODE_FLAG_NCSYNC;
- break;
- case DRM_EDID_PT_DIGITAL_SEPARATE_SYNC:
- mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
- DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC;
- mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ?
- DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC;
- break;
- }
+ mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
+ DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC;
+ mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ?
+ DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC;
}
set_size:
int ret;
if (obj->import_attach) {
+ /* Reset both vm_ops and vm_private_data, so we don't end up with
+ * vm_ops pointing to our implementation if the dma-buf backend
+ * doesn't set those fields.
+ */
vma->vm_private_data = NULL;
+ vma->vm_ops = NULL;
+
ret = dma_buf_mmap(obj->dma_buf, vma, 0);
/* Drop the reference drm_gem_mmap_obj() acquired.*/
BIT(TRANSCODER_C) | BIT(TRANSCODER_D),
};
+/*
+ * Separate detection for no display cases to keep the display id array simple.
+ *
+ * IVB Q requires subvendor and subdevice matching to differentiate from IVB D
+ * GT2 server.
+ */
+static bool has_no_display(struct pci_dev *pdev)
+{
+ static const struct pci_device_id ids[] = {
+ INTEL_IVB_Q_IDS(0),
+ {}
+ };
+
+ return pci_match_id(ids, pdev);
+}
+
#undef INTEL_VGA_DEVICE
-#undef INTEL_QUANTA_VGA_DEVICE
#define INTEL_VGA_DEVICE(id, info) { id, info }
-#define INTEL_QUANTA_VGA_DEVICE(info) { 0x16a, info }
static const struct {
u32 devid;
INTEL_IRONLAKE_M_IDS(&ilk_m_display),
INTEL_SNB_D_IDS(&snb_display),
INTEL_SNB_M_IDS(&snb_display),
- INTEL_IVB_Q_IDS(NULL), /* must be first IVB in list */
INTEL_IVB_M_IDS(&ivb_display),
INTEL_IVB_D_IDS(&ivb_display),
INTEL_HSW_IDS(&hsw_display),
if (has_gmdid)
return probe_gmdid_display(i915, gmdid_ver, gmdid_rel, gmdid_step);
+ if (has_no_display(pdev)) {
+ drm_dbg_kms(&i915->drm, "Device doesn't have display\n");
+ return &no_display;
+ }
+
for (i = 0; i < ARRAY_SIZE(intel_display_ids); i++) {
if (intel_display_ids[i].devid == pdev->device)
return intel_display_ids[i].info;
__drm_atomic_helper_connector_reset(&sdvo_connector->base.base,
&conn_state->base.base);
- INIT_LIST_HEAD(&sdvo_connector->base.panel.fixed_modes);
+ intel_panel_init_alloc(&sdvo_connector->base);
return sdvo_connector;
}
ret = slpc_set_param(slpc,
SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY,
val);
- if (ret)
+ if (ret) {
guc_probe_error(slpc_to_guc(slpc), "Failed to set efficient freq(%d): %pe\n",
val, ERR_PTR(ret));
- else
+ } else {
slpc->ignore_eff_freq = val;
+ /* Set min to RPn when we disable efficient freq */
+ if (val)
+ ret = slpc_set_param(slpc,
+ SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
+ slpc->min_freq);
+ }
+
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
mutex_unlock(&slpc->lock);
return ret;
return ret;
if (!slpc->min_freq_softlimit) {
- ret = intel_guc_slpc_get_min_freq(slpc, &slpc->min_freq_softlimit);
- if (unlikely(ret))
- return ret;
+ /* Min softlimit is initialized to RPn */
+ slpc->min_freq_softlimit = slpc->min_freq;
slpc_to_gt(slpc)->defaults.min_freq = slpc->min_freq_softlimit;
} else {
return intel_guc_slpc_set_min_freq(slpc,
return ret;
}
+ /* Set cached value of ignore efficient freq */
+ intel_guc_slpc_set_ignore_eff_freq(slpc, slpc->ignore_eff_freq);
+
/* Revert SLPC min/max to softlimits if necessary */
ret = slpc_set_softlimits(slpc);
if (unlikely(ret)) {
/* Set cached media freq ratio mode */
intel_guc_slpc_set_media_ratio_mode(slpc, slpc->media_ratio_mode);
- /* Set cached value of ignore efficient freq */
- intel_guc_slpc_set_ignore_eff_freq(slpc, slpc->ignore_eff_freq);
-
return 0;
}
/* Determine display colour depth for everything except LVDS now,
* DP requires this before mode_valid() is called.
*/
- if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode)
+ if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
nouveau_connector_detect_depth(connector);
/* Find the native mode if this is a digital panel, if we didn't
ret = nvif_conn_ctor(&disp->disp, nv_connector->base.name, nv_connector->index,
&nv_connector->conn);
if (ret) {
- kfree(nv_connector);
- return ERR_PTR(ret);
+ goto drm_conn_err;
}
ret = nvif_conn_event_ctor(&nv_connector->conn, "kmsHotplug",
if (ret) {
nvif_event_dtor(&nv_connector->hpd);
nvif_conn_dtor(&nv_connector->conn);
- kfree(nv_connector);
- return ERR_PTR(ret);
+ goto drm_conn_err;
}
}
}
drm_connector_register(connector);
return connector;
+
+drm_conn_err:
+ drm_connector_cleanup(connector);
+ kfree(nv_connector);
+ return ERR_PTR(ret);
}
#include "head.h"
#include "ior.h"
+#include <drm/display/drm_dp.h>
+
#include <subdev/bios.h>
#include <subdev/bios/init.h>
#include <subdev/gpio.h>
return outp->dp.rates != 0;
}
+/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps()
+ * converted to work inside nvkm. This is a temporary holdover until we start
+ * passing the drm_dp_aux device through NVKM
+ */
+static int
+nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp)
+{
+ struct nvkm_i2c_aux *aux = outp->dp.aux;
+ u8 dpcd_ext[DP_RECEIVER_CAP_SIZE];
+ int ret;
+
+ ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Prior to DP1.3 the bit represented by
+ * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
+ * If it is set DP_DPCD_REV at 0000h could be at a value less than
+ * the true capability of the panel. The only way to check is to
+ * then compare 0000h and 2200h.
+ */
+ if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+ DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
+ return 0;
+
+ ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext));
+ if (ret < 0)
+ return ret;
+
+ if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
+ OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n",
+ outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]);
+ return 0;
+ }
+
+ if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)))
+ return 0;
+
+ memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext));
+
+ return 0;
+}
+
void
nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr)
{
memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr));
}
- if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) {
+ if (!nvkm_dp_read_dpcd_caps(outp)) {
const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 };
const u8 *rate;
int rate_max;
extern const struct gf100_grctx_func gk110_grctx;
void gk110_grctx_generate_r419eb0(struct gf100_gr *);
+void gk110_grctx_generate_r419f78(struct gf100_gr *);
extern const struct gf100_grctx_func gk110b_grctx;
extern const struct gf100_grctx_func gk208_grctx;
gk104_grctx_generate_r419f78(struct gf100_gr *gr)
{
struct nvkm_device *device = gr->base.engine.subdev.device;
- nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);
+
+ /* bit 3 set disables loads in fp helper invocations, we need it enabled */
+ nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000);
}
void
nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000);
}
+void
+gk110_grctx_generate_r419f78(struct gf100_gr *gr)
+{
+ struct nvkm_device *device = gr->base.engine.subdev.device;
+
+ /* bit 3 set disables loads in fp helper invocations, we need it enabled */
+ nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000);
+}
+
const struct gf100_grctx_func
gk110_grctx = {
.main = gf100_grctx_generate_main,
.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
.r418800 = gk104_grctx_generate_r418800,
.r419eb0 = gk110_grctx_generate_r419eb0,
+ .r419f78 = gk110_grctx_generate_r419f78,
};
.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
.r418800 = gk104_grctx_generate_r418800,
.r419eb0 = gk110_grctx_generate_r419eb0,
+ .r419f78 = gk110_grctx_generate_r419f78,
};
.dist_skip_table = gf117_grctx_generate_dist_skip_table,
.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
.r418800 = gk104_grctx_generate_r418800,
+ .r419f78 = gk110_grctx_generate_r419f78,
};
.r406500 = gm107_grctx_generate_r406500,
.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
.r419e00 = gm107_grctx_generate_r419e00,
+ .r419f78 = gk110_grctx_generate_r419f78,
};
return gk20a_gr_av_to_init_(blob, 64, 0x00100000, ppack);
}
-int
-tu102_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
-{
- int ret;
-
- ret = gm200_gr_load(gr, ver, fwif);
- if (ret)
- return ret;
-
- return gk20a_gr_load_net(gr, "gr/", "sw_veid_bundle_init", ver, tu102_gr_av_to_init_veid,
- &gr->bundle_veid);
-}
-
static const struct gf100_gr_fwif
tu102_gr_fwif[] = {
{ 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(jdi->supplies),
jdi->supplies);
- if (ret < 0) {
- dev_err(dev, "failed to init regulator, ret=%d\n", ret);
- return ret;
- }
+ if (ret < 0)
+ return dev_err_probe(dev, ret,
+ "failed to init regulator, ret=%d\n", ret);
jdi->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
if (IS_ERR(jdi->enable_gpio)) {
- ret = PTR_ERR(jdi->enable_gpio);
- dev_err(dev, "cannot get enable-gpio %d\n", ret);
- return ret;
+ return dev_err_probe(dev, PTR_ERR(jdi->enable_gpio),
+ "cannot get enable-gpio %d\n", ret);
}
jdi->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
- if (IS_ERR(jdi->reset_gpio)) {
- ret = PTR_ERR(jdi->reset_gpio);
- dev_err(dev, "cannot get reset-gpios %d\n", ret);
- return ret;
- }
+ if (IS_ERR(jdi->reset_gpio))
+ return dev_err_probe(dev, PTR_ERR(jdi->reset_gpio),
+ "cannot get reset-gpios %d\n", ret);
jdi->dcdc_en_gpio = devm_gpiod_get(dev, "dcdc-en", GPIOD_OUT_LOW);
- if (IS_ERR(jdi->dcdc_en_gpio)) {
- ret = PTR_ERR(jdi->dcdc_en_gpio);
- dev_err(dev, "cannot get dcdc-en-gpio %d\n", ret);
- return ret;
- }
+ if (IS_ERR(jdi->dcdc_en_gpio))
+ return dev_err_probe(dev, PTR_ERR(jdi->dcdc_en_gpio),
+ "cannot get dcdc-en-gpio %d\n", ret);
jdi->backlight = drm_panel_create_dsi_backlight(jdi->dsi);
- if (IS_ERR(jdi->backlight)) {
- ret = PTR_ERR(jdi->backlight);
- dev_err(dev, "failed to register backlight %d\n", ret);
- return ret;
- }
+ if (IS_ERR(jdi->backlight))
+ return dev_err_probe(dev, PTR_ERR(jdi->backlight),
+ "failed to register backlight %d\n", ret);
drm_panel_init(&jdi->base, &jdi->dsi->dev, &jdi_panel_funcs,
DRM_MODE_CONNECTOR_DSI);
.connector_type = DRM_MODE_CONNECTOR_LVDS,
};
-static const struct drm_display_mode auo_g121ean01_mode = {
- .clock = 66700,
- .hdisplay = 1280,
- .hsync_start = 1280 + 58,
- .hsync_end = 1280 + 58 + 8,
- .htotal = 1280 + 58 + 8 + 70,
- .vdisplay = 800,
- .vsync_start = 800 + 6,
- .vsync_end = 800 + 6 + 4,
- .vtotal = 800 + 6 + 4 + 10,
+static const struct display_timing auo_g121ean01_timing = {
+ .pixelclock = { 60000000, 74400000, 90000000 },
+ .hactive = { 1280, 1280, 1280 },
+ .hfront_porch = { 20, 50, 100 },
+ .hback_porch = { 20, 50, 100 },
+ .hsync_len = { 30, 100, 200 },
+ .vactive = { 800, 800, 800 },
+ .vfront_porch = { 2, 10, 25 },
+ .vback_porch = { 2, 10, 25 },
+ .vsync_len = { 4, 18, 50 },
};
static const struct panel_desc auo_g121ean01 = {
- .modes = &auo_g121ean01_mode,
- .num_modes = 1,
+ .timings = &auo_g121ean01_timing,
+ .num_timings = 1,
.bpc = 8,
.size = {
.width = 261,
u32 domain,
size_t size,
struct qxl_surface *surf,
- struct qxl_bo **qobj,
+ struct drm_gem_object **gobj,
uint32_t *handle);
void qxl_gem_object_free(struct drm_gem_object *gobj);
int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv);
{
struct qxl_device *qdev = to_qxl(dev);
struct qxl_bo *qobj;
+ struct drm_gem_object *gobj;
uint32_t handle;
int r;
struct qxl_surface surf;
r = qxl_gem_object_create_with_handle(qdev, file_priv,
QXL_GEM_DOMAIN_CPU,
- args->size, &surf, &qobj,
+ args->size, &surf, &gobj,
&handle);
if (r)
return r;
+ qobj = gem_to_qxl_bo(gobj);
qobj->is_dumb = true;
+ drm_gem_object_put(gobj);
args->pitch = pitch;
args->handle = handle;
return 0;
return 0;
}
+/*
+ * If the caller passed a valid gobj pointer, it is responsible to call
+ * drm_gem_object_put() when it no longer needs to acess the object.
+ *
+ * If gobj is NULL, it is handled internally.
+ */
int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
struct drm_file *file_priv,
u32 domain,
size_t size,
struct qxl_surface *surf,
- struct qxl_bo **qobj,
+ struct drm_gem_object **gobj,
uint32_t *handle)
{
- struct drm_gem_object *gobj;
int r;
+ struct drm_gem_object *local_gobj;
- BUG_ON(!qobj);
BUG_ON(!handle);
r = qxl_gem_object_create(qdev, size, 0,
domain,
false, false, surf,
- &gobj);
+ &local_gobj);
if (r)
return -ENOMEM;
- r = drm_gem_handle_create(file_priv, gobj, handle);
+ r = drm_gem_handle_create(file_priv, local_gobj, handle);
if (r)
return r;
- /* drop reference from allocate - handle holds it now */
- *qobj = gem_to_qxl_bo(gobj);
- drm_gem_object_put(gobj);
+
+ if (gobj)
+ *gobj = local_gobj;
+ else
+ /* drop reference from allocate - handle holds it now */
+ drm_gem_object_put(local_gobj);
+
return 0;
}
struct qxl_device *qdev = to_qxl(dev);
struct drm_qxl_alloc *qxl_alloc = data;
int ret;
- struct qxl_bo *qobj;
uint32_t handle;
u32 domain = QXL_GEM_DOMAIN_VRAM;
domain,
qxl_alloc->size,
NULL,
- &qobj, &handle);
+ NULL, &handle);
if (ret) {
DRM_ERROR("%s: failed to create gem ret=%d\n",
__func__, ret);
{
struct qxl_device *qdev = to_qxl(dev);
struct drm_qxl_alloc_surf *param = data;
- struct qxl_bo *qobj;
int handle;
int ret;
int size, actual_stride;
QXL_GEM_DOMAIN_SURFACE,
size,
&surf,
- &qobj, &handle);
+ NULL, &handle);
if (ret) {
DRM_ERROR("%s: failed to create gem ret=%d\n",
__func__, ret);
* need align with 2 pixel.
*/
if (fb->format->is_yuv && ((new_plane_state->src.x1 >> 16) % 2)) {
- DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n");
+ DRM_DEBUG_KMS("Invalid Source: Yuv format not support odd xpos\n");
return -EINVAL;
}
if (fb->format->is_yuv && new_plane_state->rotation & DRM_MODE_REFLECT_Y) {
- DRM_ERROR("Invalid Source: Yuv format does not support this rotation\n");
+ DRM_DEBUG_KMS("Invalid Source: Yuv format does not support this rotation\n");
return -EINVAL;
}
struct vop *vop = to_vop(crtc);
if (!vop->data->afbc) {
- DRM_ERROR("vop does not support AFBC\n");
+ DRM_DEBUG_KMS("vop does not support AFBC\n");
return -EINVAL;
}
return ret;
if (new_plane_state->src.x1 || new_plane_state->src.y1) {
- DRM_ERROR("AFBC does not support offset display, xpos=%d, ypos=%d, offset=%d\n",
- new_plane_state->src.x1,
- new_plane_state->src.y1, fb->offsets[0]);
+ DRM_DEBUG_KMS("AFBC does not support offset display, " \
+ "xpos=%d, ypos=%d, offset=%d\n",
+ new_plane_state->src.x1, new_plane_state->src.y1,
+ fb->offsets[0]);
return -EINVAL;
}
if (new_plane_state->rotation && new_plane_state->rotation != DRM_MODE_ROTATE_0) {
- DRM_ERROR("No rotation support in AFBC, rotation=%d\n",
- new_plane_state->rotation);
+ DRM_DEBUG_KMS("No rotation support in AFBC, rotation=%d\n",
+ new_plane_state->rotation);
return -EINVAL;
}
}
#include <linux/crc16.h>
#include <linux/debugfs.h>
+#include <linux/delay.h>
#include <linux/hid.h>
#include <linux/hwmon.h>
#include <linux/jiffies.h>
+#include <linux/ktime.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/seq_file.h>
#define CTRL_REPORT_ID 0x03
#define AQUAERO_CTRL_REPORT_ID 0x0b
+#define CTRL_REPORT_DELAY 200 /* ms */
+
/* The HID report that the official software always sends
* after writing values, currently same for all devices
*/
int secondary_ctrl_report_size;
u8 *secondary_ctrl_report;
+ ktime_t last_ctrl_report_op;
+ int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */
+
int buffer_size;
u8 *buffer;
int checksum_start;
return 0;
}
+static void aqc_delay_ctrl_report(struct aqc_data *priv)
+{
+ /*
+ * If previous read or write is too close to this one, delay the current operation
+ * to give the device enough time to process the previous one.
+ */
+ if (priv->ctrl_report_delay) {
+ s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op);
+
+ if (delta < priv->ctrl_report_delay)
+ msleep(priv->ctrl_report_delay - delta);
+ }
+}
+
/* Expects the mutex to be locked */
static int aqc_get_ctrl_data(struct aqc_data *priv)
{
int ret;
+ aqc_delay_ctrl_report(priv);
+
memset(priv->buffer, 0x00, priv->buffer_size);
ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size,
HID_FEATURE_REPORT, HID_REQ_GET_REPORT);
if (ret < 0)
ret = -ENODATA;
+ priv->last_ctrl_report_op = ktime_get();
+
return ret;
}
int ret;
u16 checksum;
+ aqc_delay_ctrl_report(priv);
+
/* Checksum is not needed for Aquaero */
if (priv->kind != aquaero) {
/* Init and xorout value for CRC-16/USB is 0xffff */
ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size,
HID_FEATURE_REPORT, HID_REQ_SET_REPORT);
if (ret < 0)
- return ret;
+ goto record_access_and_ret;
/* The official software sends this report after every change, so do it here as well */
ret = hid_hw_raw_request(priv->hdev, priv->secondary_ctrl_report_id,
priv->secondary_ctrl_report, priv->secondary_ctrl_report_size,
HID_FEATURE_REPORT, HID_REQ_SET_REPORT);
+
+record_access_and_ret:
+ priv->last_ctrl_report_op = ktime_get();
+
return ret;
}
priv->buffer_size = AQUAERO_CTRL_REPORT_SIZE;
priv->temp_ctrl_offset = AQUAERO_TEMP_CTRL_OFFSET;
+ priv->ctrl_report_delay = CTRL_REPORT_DELAY;
priv->temp_label = label_temp_sensors;
priv->virtual_temp_label = label_virtual_temp_sensors;
priv->temp_ctrl_offset = D5NEXT_TEMP_CTRL_OFFSET;
priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE;
+ priv->ctrl_report_delay = CTRL_REPORT_DELAY;
priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES;
priv->temp_ctrl_offset = OCTO_TEMP_CTRL_OFFSET;
priv->buffer_size = OCTO_CTRL_REPORT_SIZE;
+ priv->ctrl_report_delay = CTRL_REPORT_DELAY;
priv->power_cycle_count_offset = OCTO_POWER_CYCLES;
priv->temp_ctrl_offset = QUADRO_TEMP_CTRL_OFFSET;
priv->buffer_size = QUADRO_CTRL_REPORT_SIZE;
+ priv->ctrl_report_delay = CTRL_REPORT_DELAY;
priv->flow_pulses_ctrl_offset = QUADRO_FLOW_PULSES_CTRL_OFFSET;
priv->power_cycle_count_offset = QUADRO_POWER_CYCLES;
enum chips {pfe1100, pfe3000};
/*
- * Disable status check for pfe3000 devices, because some devices report
- * communication error (invalid command) for VOUT_MODE command (0x20)
- * although correct VOUT_MODE (0x16) is returned: it leads to incorrect
- * exponent in linear mode.
+ * Disable status check because some devices report communication error
+ * (invalid command) for VOUT_MODE command (0x20) although the correct
+ * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear
+ * mode.
+ * This affects both pfe3000 and pfe1100.
*/
-static struct pmbus_platform_data pfe3000_plat_data = {
+static struct pmbus_platform_data pfe_plat_data = {
.flags = PMBUS_SKIP_STATUS_CHECK,
};
int model;
model = (int)i2c_match_id(pfe_device_id, client)->driver_data;
+ client->dev.platform_data = &pfe_plat_data;
/*
* PFE3000-12-069RA devices may not stay in page 0 during device
* probe which leads to probe failure (read status word failed).
* So let's set the device to page 0 at the beginning.
*/
- if (model == pfe3000) {
- client->dev.platform_data = &pfe3000_plat_data;
+ if (model == pfe3000)
i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0);
- }
return pmbus_do_probe(client, &pfe_driver_info[model]);
}
#define AD7192_MODE_STA_MASK BIT(20) /* Status Register transmission Mask */
#define AD7192_MODE_CLKSRC(x) (((x) & 0x3) << 18) /* Clock Source Select */
#define AD7192_MODE_SINC3 BIT(15) /* SINC3 Filter Select */
-#define AD7192_MODE_ACX BIT(14) /* AC excitation enable(AD7195 only)*/
#define AD7192_MODE_ENPAR BIT(13) /* Parity Enable */
#define AD7192_MODE_CLKDIV BIT(12) /* Clock divide by 2 (AD7190/2 only)*/
#define AD7192_MODE_SCYCLE BIT(11) /* Single cycle conversion */
/* Configuration Register Bit Designations (AD7192_REG_CONF) */
#define AD7192_CONF_CHOP BIT(23) /* CHOP enable */
+#define AD7192_CONF_ACX BIT(22) /* AC excitation enable(AD7195 only) */
#define AD7192_CONF_REFSEL BIT(20) /* REFIN1/REFIN2 Reference Select */
#define AD7192_CONF_CHAN(x) ((x) << 8) /* Channel select */
#define AD7192_CONF_CHAN_MASK (0x7FF << 8) /* Channel select mask */
struct iio_dev *indio_dev = dev_to_iio_dev(dev);
struct ad7192_state *st = iio_priv(indio_dev);
- return sysfs_emit(buf, "%d\n", !!(st->mode & AD7192_MODE_ACX));
+ return sysfs_emit(buf, "%d\n", !!(st->conf & AD7192_CONF_ACX));
}
static ssize_t ad7192_show_bridge_switch(struct device *dev,
ad_sd_write_reg(&st->sd, AD7192_REG_GPOCON, 1, st->gpocon);
break;
- case AD7192_REG_MODE:
+ case AD7192_REG_CONF:
if (val)
- st->mode |= AD7192_MODE_ACX;
+ st->conf |= AD7192_CONF_ACX;
else
- st->mode &= ~AD7192_MODE_ACX;
+ st->conf &= ~AD7192_CONF_ACX;
- ad_sd_write_reg(&st->sd, AD7192_REG_MODE, 3, st->mode);
+ ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, st->conf);
break;
default:
ret = -EINVAL;
static IIO_DEVICE_ATTR(ac_excitation_en, 0644,
ad7192_show_ac_excitation, ad7192_set,
- AD7192_REG_MODE);
+ AD7192_REG_CONF);
static struct attribute *ad7192_attributes[] = {
&iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr,
&iio_dev_attr_bridge_switch_en.dev_attr.attr,
- &iio_dev_attr_ac_excitation_en.dev_attr.attr,
NULL
};
static struct attribute *ad7195_attributes[] = {
&iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr,
&iio_dev_attr_bridge_switch_en.dev_attr.attr,
+ &iio_dev_attr_ac_excitation_en.dev_attr.attr,
NULL
};
enum ina2xx_ids { ina219, ina226 };
struct ina2xx_config {
+ const char *name;
u16 config_default;
int calibration_value;
int shunt_voltage_lsb; /* nV */
static const struct ina2xx_config ina2xx_config[] = {
[ina219] = {
+ .name = "ina219",
.config_default = INA219_CONFIG_DEFAULT,
.calibration_value = 4096,
.shunt_voltage_lsb = 10000,
.chip_id = ina219,
},
[ina226] = {
+ .name = "ina226",
.config_default = INA226_CONFIG_DEFAULT,
.calibration_value = 2048,
.shunt_voltage_lsb = 2500,
/* Patch the current config register with default. */
val = chip->config->config_default;
- if (id->driver_data == ina226) {
+ if (type == ina226) {
ina226_set_average(chip, INA226_DEFAULT_AVG, &val);
ina226_set_int_time_vbus(chip, INA226_DEFAULT_IT, &val);
ina226_set_int_time_vshunt(chip, INA226_DEFAULT_IT, &val);
}
indio_dev->modes = INDIO_DIRECT_MODE;
- if (id->driver_data == ina226) {
+ if (type == ina226) {
indio_dev->channels = ina226_channels;
indio_dev->num_channels = ARRAY_SIZE(ina226_channels);
indio_dev->info = &ina226_info;
indio_dev->num_channels = ARRAY_SIZE(ina219_channels);
indio_dev->info = &ina219_info;
}
- indio_dev->name = id->name;
+ indio_dev->name = id ? id->name : chip->config->name;
ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
&ina2xx_setup_ops);
goto err_vref;
}
- ret = clk_prepare_enable(priv->core_clk);
- if (ret) {
- dev_err(dev, "failed to enable core clk\n");
- goto err_core_clk;
- }
-
regval = FIELD_PREP(MESON_SAR_ADC_REG0_FIFO_CNT_IRQ_MASK, 1);
regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG0,
MESON_SAR_ADC_REG0_FIFO_CNT_IRQ_MASK, regval);
regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG3,
MESON_SAR_ADC_REG3_ADC_EN, 0);
meson_sar_adc_set_bandgap(indio_dev, false);
- clk_disable_unprepare(priv->core_clk);
-err_core_clk:
regulator_disable(priv->vref);
err_vref:
meson_sar_adc_unlock(indio_dev);
meson_sar_adc_set_bandgap(indio_dev, false);
- clk_disable_unprepare(priv->core_clk);
-
regulator_disable(priv->vref);
if (!ret)
if (IS_ERR(priv->clkin))
return dev_err_probe(dev, PTR_ERR(priv->clkin), "failed to get clkin\n");
- priv->core_clk = devm_clk_get(dev, "core");
+ priv->core_clk = devm_clk_get_enabled(dev, "core");
if (IS_ERR(priv->core_clk))
return dev_err_probe(dev, PTR_ERR(priv->core_clk), "failed to get core clk\n");
static int meson_sar_adc_suspend(struct device *dev)
{
struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct meson_sar_adc_priv *priv = iio_priv(indio_dev);
meson_sar_adc_hw_disable(indio_dev);
+ clk_disable_unprepare(priv->core_clk);
+
return 0;
}
static int meson_sar_adc_resume(struct device *dev)
{
struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct meson_sar_adc_priv *priv = iio_priv(indio_dev);
+ int ret;
+
+ ret = clk_prepare_enable(priv->core_clk);
+ if (ret) {
+ dev_err(dev, "failed to enable core clk\n");
+ return ret;
+ }
return meson_sar_adc_hw_enable(indio_dev);
}
platform_set_drvdata(pdev, indio_dev);
state->ec = ec->ec_dev;
- state->msg = devm_kzalloc(&pdev->dev,
+ state->msg = devm_kzalloc(&pdev->dev, sizeof(*state->msg) +
max((u16)sizeof(struct ec_params_motion_sense),
state->ec->max_response), GFP_KERNEL);
if (!state->msg)
static int admv1013_update_mixer_vgate(struct admv1013_state *st)
{
- unsigned int vcm, mixer_vgate;
+ unsigned int mixer_vgate;
+ int vcm;
vcm = regulator_get_voltage(st->reg);
+ if (vcm < 0)
+ return vcm;
if (vcm < 1800000)
mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100;
static int lsm6dsx_get_acpi_mount_matrix(struct device *dev,
struct iio_mount_matrix *orientation)
{
- return false;
+ return -EOPNOTSUPP;
}
#endif
int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod)
{
struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
- struct fwnode_handle *fwnode;
+ struct fwnode_handle *fwnode = NULL;
int ret;
if (!indio_dev->info)
/* If the calling driver did not initialize firmware node, do it here */
if (dev_fwnode(&indio_dev->dev))
fwnode = dev_fwnode(&indio_dev->dev);
- else
+ /* The default dummy IIO device has no parent */
+ else if (indio_dev->dev.parent)
fwnode = dev_fwnode(indio_dev->dev.parent);
device_set_node(&indio_dev->dev, fwnode);
.address = BU27008_REG_##data##_LO, \
.scan_index = BU27008_##color, \
.scan_type = { \
- .sign = 's', \
+ .sign = 'u', \
.realbits = 16, \
.storagebits = 16, \
.endianness = IIO_LE, \
for (i = 0; i < data->gts.num_itime; i++) {
new_time_sel = data->gts.itime_table[i].sel;
ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts,
- new_time_sel, val, val2 * 1000, gain_sel);
+ new_time_sel, val, val2, gain_sel);
if (!ret)
break;
}
goto unlock_out;
ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel,
- val, val2 * 1000, &gain_sel);
+ val, val2, &gain_sel);
if (ret) {
ret = bu27008_try_find_new_time_gain(data, val, val2, &gain_sel);
if (ret)
return ret;
}
+static int bu27008_write_raw_get_fmt(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ long mask)
+{
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE:
+ return IIO_VAL_INT_PLUS_NANO;
+ case IIO_CHAN_INFO_INT_TIME:
+ return IIO_VAL_INT_PLUS_MICRO;
+ default:
+ return -EINVAL;
+ }
+}
+
static int bu27008_write_raw(struct iio_dev *idev,
struct iio_chan_spec const *chan,
int val, int val2, long mask)
static const struct iio_info bu27008_info = {
.read_raw = &bu27008_read_raw,
.write_raw = &bu27008_write_raw,
+ .write_raw_get_fmt = &bu27008_write_raw_get_fmt,
.read_avail = &bu27008_read_avail,
.update_scan_mode = bu27008_update_scan_mode,
.validate_trigger = iio_validate_own_trigger,
return -EINVAL;
if (chan == BU27034_CHAN_ALS) {
- if (val == 0 && val2 == 1000)
+ if (val == 0 && val2 == 1000000)
return 0;
return -EINVAL;
goto unlock_out;
ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel,
- val, val2 * 1000, &gain_sel);
+ val, val2, &gain_sel);
if (ret) {
/*
* Could not support scale with given time. Need to change time.
/* Can we provide requested scale with this time? */
ret = iio_gts_find_gain_sel_for_scale_using_time(
- &data->gts, new_time_sel, val, val2 * 1000,
+ &data->gts, new_time_sel, val, val2,
&gain_sel);
if (ret)
continue;
}
}
+static int bu27034_write_raw_get_fmt(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ long mask)
+{
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE:
+ return IIO_VAL_INT_PLUS_NANO;
+ case IIO_CHAN_INFO_INT_TIME:
+ return IIO_VAL_INT_PLUS_MICRO;
+ default:
+ return -EINVAL;
+ }
+}
+
static int bu27034_write_raw(struct iio_dev *idev,
struct iio_chan_spec const *chan,
int val, int val2, long mask)
static const struct iio_info bu27034_info = {
.read_raw = &bu27034_read_raw,
.write_raw = &bu27034_write_raw,
+ .write_raw_get_fmt = &bu27034_write_raw_get_fmt,
.read_avail = &bu27034_read_avail,
};
dma_addr_t mask;
int i;
+ umem->iova = va = virt;
+
if (umem->is_odp) {
unsigned int page_size = BIT(to_ib_umem_odp(umem)->page_shift);
*/
pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT);
- umem->iova = va = virt;
/* The best result is the smallest page size that results in the minimum
* number of required pages. Compute the largest page size that could
* work based on VA address bits that don't change.
rc = bnxt_re_setup_chip_ctx(rdev, wqe_mode);
if (rc) {
+ bnxt_unregister_dev(rdev->en_dev);
+ clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
ibdev_err(&rdev->ibdev, "Failed to get chip context\n");
return -EINVAL;
}
}
bnxt_re_setup_cc(rdev, false);
ib_unregister_device(&rdev->ibdev);
- ib_dealloc_device(&rdev->ibdev);
bnxt_re_dev_uninit(rdev);
+ ib_dealloc_device(&rdev->ibdev);
skip_remove:
mutex_unlock(&bnxt_re_mutex);
}
}
memset((u8 *)dpit->tbl, 0xFF, bytes);
+ mutex_init(&res->dpi_tbl_lock);
dpit->priv_db = dpit->ucreg.bar_reg + dpit->ucreg.offset;
return 0;
if (dd->synth_stats_timer.function)
del_timer_sync(&dd->synth_stats_timer);
+ cancel_work_sync(&dd->update_cntr_work);
ppd = (struct hfi1_pportdata *)(dd + 1);
for (i = 0; i < dd->num_pports; i++, ppd++) {
kfree(ppd->cntrs);
temp = agg_peak[bucket] * bcm->vote_scale;
bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit);
+
+ if (bcm->enable_mask && (bcm->vote_x[bucket] || bcm->vote_y[bucket])) {
+ bcm->vote_x[bucket] = 0;
+ bcm->vote_y[bucket] = bcm->enable_mask;
+ }
}
if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 &&
* @vote_x: aggregated threshold values, represents sum_bw when @type is bw bcm
* @vote_y: aggregated threshold values, represents peak_bw when @type is bw bcm
* @vote_scale: scaling factor for vote_x and vote_y
+ * @enable_mask: optional mask to send as vote instead of vote_x/vote_y
* @dirty: flag used to indicate whether the bcm needs to be committed
* @keepalive: flag used to indicate whether a keepalive is required
* @aux_data: auxiliary data used when calculating threshold values and
u64 vote_x[QCOM_ICC_NUM_BUCKETS];
u64 vote_y[QCOM_ICC_NUM_BUCKETS];
u64 vote_scale;
+ u32 enable_mask;
bool dirty;
bool keepalive;
struct bcm_db aux_data;
static struct qcom_icc_bcm bcm_acv = {
.name = "ACV",
+ .enable_mask = 0x8,
.num_nodes = 1,
.nodes = { &ebi },
};
static struct qcom_icc_bcm bcm_acv = {
.name = "ACV",
+ .enable_mask = 0x8,
.num_nodes = 1,
.nodes = { &ebi },
};
static struct qcom_icc_bcm bcm_cn0 = {
.name = "CN0",
+ .enable_mask = 0x1,
.keepalive = true,
.num_nodes = 55,
.nodes = { &qnm_gemnoc_cnoc, &qnm_gemnoc_pcie,
static struct qcom_icc_bcm bcm_co0 = {
.name = "CO0",
+ .enable_mask = 0x1,
.num_nodes = 2,
.nodes = { &qxm_nsp, &qns_nsp_gemnoc },
};
static struct qcom_icc_bcm bcm_mm1 = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 12,
.nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp,
&qnm_camnoc_sf, &qnm_mdp,
static struct qcom_icc_bcm bcm_sh1 = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 7,
.nodes = { &alm_gpu_tcu, &alm_sys_tcu,
&qnm_nsp_gemnoc, &qnm_pcie,
static struct qcom_icc_bcm bcm_sn1 = {
.name = "SN1",
+ .enable_mask = 0x1,
.num_nodes = 4,
.nodes = { &qhm_gic, &qxm_pimem,
&xm_gic, &qns_gemnoc_gc },
static struct qcom_icc_bcm bcm_acv_disp = {
.name = "ACV",
+ .enable_mask = 0x1,
.num_nodes = 1,
.nodes = { &ebi_disp },
};
static struct qcom_icc_bcm bcm_mm1_disp = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 3,
.nodes = { &qnm_mdp_disp, &qnm_rot_disp,
&qns_mem_noc_sf_disp },
static struct qcom_icc_bcm bcm_sh1_disp = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 1,
.nodes = { &qnm_pcie_disp },
};
static struct qcom_icc_bcm bcm_acv = {
.name = "ACV",
+ .enable_mask = 0x8,
.num_nodes = 1,
.nodes = { &ebi },
};
static struct qcom_icc_bcm bcm_cn0 = {
.name = "CN0",
+ .enable_mask = 0x1,
.keepalive = true,
.num_nodes = 54,
.nodes = { &qsm_cfg, &qhs_ahb2phy0,
static struct qcom_icc_bcm bcm_co0 = {
.name = "CO0",
+ .enable_mask = 0x1,
.num_nodes = 2,
.nodes = { &qxm_nsp, &qns_nsp_gemnoc },
};
static struct qcom_icc_bcm bcm_mm1 = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 8,
.nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp,
&qnm_camnoc_sf, &qnm_vapss_hcp,
static struct qcom_icc_bcm bcm_sh1 = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 13,
.nodes = { &alm_gpu_tcu, &alm_sys_tcu,
&chm_apps, &qnm_gpu,
static struct qcom_icc_bcm bcm_sn1 = {
.name = "SN1",
+ .enable_mask = 0x1,
.num_nodes = 3,
.nodes = { &qhm_gic, &xm_gic,
&qns_gemnoc_gc },
static struct qcom_icc_bcm bcm_acv_disp = {
.name = "ACV",
+ .enable_mask = 0x1,
.num_nodes = 1,
.nodes = { &ebi_disp },
};
static struct qcom_icc_bcm bcm_sh1_disp = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 2,
.nodes = { &qnm_mnoc_hf_disp, &qnm_pcie_disp },
};
static struct qcom_icc_bcm bcm_acv_cam_ife_0 = {
.name = "ACV",
+ .enable_mask = 0x0,
.num_nodes = 1,
.nodes = { &ebi_cam_ife_0 },
};
static struct qcom_icc_bcm bcm_mm1_cam_ife_0 = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 4,
.nodes = { &qnm_camnoc_hf_cam_ife_0, &qnm_camnoc_icp_cam_ife_0,
&qnm_camnoc_sf_cam_ife_0, &qns_mem_noc_sf_cam_ife_0 },
static struct qcom_icc_bcm bcm_sh1_cam_ife_0 = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 3,
.nodes = { &qnm_mnoc_hf_cam_ife_0, &qnm_mnoc_sf_cam_ife_0,
&qnm_pcie_cam_ife_0 },
static struct qcom_icc_bcm bcm_acv_cam_ife_1 = {
.name = "ACV",
+ .enable_mask = 0x0,
.num_nodes = 1,
.nodes = { &ebi_cam_ife_1 },
};
static struct qcom_icc_bcm bcm_mm1_cam_ife_1 = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 4,
.nodes = { &qnm_camnoc_hf_cam_ife_1, &qnm_camnoc_icp_cam_ife_1,
&qnm_camnoc_sf_cam_ife_1, &qns_mem_noc_sf_cam_ife_1 },
static struct qcom_icc_bcm bcm_sh1_cam_ife_1 = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 3,
.nodes = { &qnm_mnoc_hf_cam_ife_1, &qnm_mnoc_sf_cam_ife_1,
&qnm_pcie_cam_ife_1 },
static struct qcom_icc_bcm bcm_acv_cam_ife_2 = {
.name = "ACV",
+ .enable_mask = 0x0,
.num_nodes = 1,
.nodes = { &ebi_cam_ife_2 },
};
static struct qcom_icc_bcm bcm_mm1_cam_ife_2 = {
.name = "MM1",
+ .enable_mask = 0x1,
.num_nodes = 4,
.nodes = { &qnm_camnoc_hf_cam_ife_2, &qnm_camnoc_icp_cam_ife_2,
&qnm_camnoc_sf_cam_ife_2, &qns_mem_noc_sf_cam_ife_2 },
static struct qcom_icc_bcm bcm_sh1_cam_ife_2 = {
.name = "SH1",
+ .enable_mask = 0x1,
.num_nodes = 3,
.nodes = { &qnm_mnoc_hf_cam_ife_2, &qnm_mnoc_sf_cam_ife_2,
&qnm_pcie_cam_ife_2 },
}
}
- if (option->force_clkreq_0)
+ if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG)
rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG,
FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
else
option->ltr_enabled = false;
}
}
-
- if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
- | PM_L1_1_EN | PM_L1_2_EN))
- option->force_clkreq_0 = false;
- else
- option->force_clkreq_0 = true;
}
static int rts5228_extra_init_hw(struct rtsx_pcr *pcr)
{
- struct rtsx_cr_option *option = &pcr->option;
rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1,
CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
else
rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
- /*
- * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
- * to drive low, and we forcibly request clock.
- */
- if (option->force_clkreq_0)
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
- else
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
-
rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB);
if (pcr->rtd3_en) {
}
}
-
/*
* If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
* to drive low, and we forcibly request clock.
*/
- if (option->force_clkreq_0)
+ if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG)
rtsx_pci_write_register(pcr, PETXCFG,
FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
else
option->ltr_enabled = false;
}
}
-
- if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
- | PM_L1_1_EN | PM_L1_2_EN))
- option->force_clkreq_0 = false;
- else
- option->force_clkreq_0 = true;
}
static int rts5260_extra_init_hw(struct rtsx_pcr *pcr)
{
- struct rtsx_cr_option *option = &pcr->option;
/* Set mcu_cnt to 7 to ensure data can be sampled properly */
rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07);
rts5260_init_hw(pcr);
- /*
- * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
- * to drive low, and we forcibly request clock.
- */
- if (option->force_clkreq_0)
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
- else
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
-
rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00);
return 0;
option->ltr_enabled = false;
}
}
-
- if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
- | PM_L1_1_EN | PM_L1_2_EN))
- option->force_clkreq_0 = false;
- else
- option->force_clkreq_0 = true;
}
static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
{
- struct rtsx_cr_option *option = &pcr->option;
u32 val;
rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1,
else
rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
- /*
- * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
- * to drive low, and we forcibly request clock.
- */
- if (option->force_clkreq_0)
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
- else
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
-
rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB);
if (pcr->rtd3_en) {
return err;
}
- if (pcr->aspm_mode == ASPM_MODE_REG)
+ if (pcr->aspm_mode == ASPM_MODE_REG) {
rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30);
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+ }
/* No CD interrupt if probing driver with card inserted.
* So we need to initialize pcr->card_exist here.
#include <linux/mfd/tps6594.h>
+#define TPS6594_DEV_REV_1 0x08
+
static irqreturn_t tps6594_esm_isr(int irq, void *dev_id)
{
struct platform_device *pdev = dev_id;
{
struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent);
struct device *dev = &pdev->dev;
+ unsigned int rev;
int irq;
int ret;
int i;
- for (i = 0 ; i < pdev->num_resources ; i++) {
+ /*
+ * Due to a bug in revision 1 of the PMIC, the GPIO3 used for the
+ * SoC ESM function is used to power the load switch instead.
+ * As a consequence, ESM can not be used on those PMIC.
+ * Check the version and return an error in case of revision 1.
+ */
+ ret = regmap_read(tps->regmap, TPS6594_REG_DEV_REV, &rev);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "Failed to read PMIC revision\n");
+ if (rev == TPS6594_DEV_REV_1)
+ return dev_err_probe(dev, -ENODEV,
+ "ESM not supported for revision 1 PMIC\n");
+
+ for (i = 0; i < pdev->num_resources; i++) {
irq = platform_get_irq_byname(pdev, pdev->resource[i].name);
if (irq < 0)
return dev_err_probe(dev, irq, "Failed to get %s irq\n",
at runtime through a userspace interface exported using configfs.
See <file:Documentation/networking/netconsole.rst> for details.
+config NETCONSOLE_EXTENDED_LOG
+ bool "Set kernel extended message by default"
+ depends on NETCONSOLE
+ default n
+ help
+ Set extended log support for netconsole message. If this option is
+ set, log messages are transmitted with extended metadata header in a
+ format similar to /dev/kmsg. See
+ <file:Documentation/networking/netconsole.rst> for details.
+
+config NETCONSOLE_PREPEND_RELEASE
+ bool "Prepend kernel release version in the message by default"
+ depends on NETCONSOLE_EXTENDED_LOG
+ default n
+ help
+ Set kernel release to be prepended to each netconsole message by
+ default. If this option is set, the kernel release is prepended into
+ the first field of every netconsole message, so, the netconsole
+ server/peer can easily identify what kernel release is logging each
+ message. See <file:Documentation/networking/netconsole.rst> for
+ details.
+
config NETPOLL
def_bool NETCONSOLE
/* If there is a GPIO connected to the reset pin, toggle it */
if (gpiod) {
+ /* If the switch has just been reset and not yet completed
+ * loading EEPROM, the reset may interrupt the I2C transaction
+ * mid-byte, causing the first EEPROM read after the reset
+ * from the wrong location resulting in the switch booting
+ * to wrong mode and inoperable.
+ */
+ mv88e6xxx_g1_wait_eeprom_done(chip);
+
gpiod_set_value_cansleep(gpiod, 1);
usleep_range(10000, 20000);
gpiod_set_value_cansleep(gpiod, 0);
host_info = ena_dev->host_attr.host_info;
- host_info->bdf = (pdev->bus->number << 8) | pdev->devfn;
+ host_info->bdf = pci_dev_id(pdev);
host_info->os_type = ENA_ADMIN_OS_LINUX;
host_info->kernel_ver = LINUX_VERSION_CODE;
strscpy(host_info->kernel_ver_str, utsname()->version,
b44_readphy(bp, MII_BMCR, &bmcr);
b44_readphy(bp, MII_BMCR, &bmcr);
r = -EINVAL;
- if (bmcr & BMCR_ANENABLE) {
- b44_writephy(bp, MII_BMCR,
- bmcr | BMCR_ANRESTART);
- r = 0;
- }
+ if (bmcr & BMCR_ANENABLE)
+ r = b44_writephy(bp, MII_BMCR,
+ bmcr | BMCR_ANRESTART);
spin_unlock_irq(&bp->lock);
return r;
unsigned int q;
int err;
+ if (!device_may_wakeup(&bp->dev->dev))
+ phy_exit(bp->sgmii_phy);
+
if (!netif_running(netdev))
return 0;
if (!(bp->wol & MACB_WOL_ENABLED)) {
rtnl_lock();
phylink_stop(bp->phylink);
- phy_exit(bp->sgmii_phy);
rtnl_unlock();
spin_lock_irqsave(&bp->lock, flags);
macb_reset_hw(bp);
unsigned int q;
int err;
+ if (!device_may_wakeup(&bp->dev->dev))
+ phy_init(bp->sgmii_phy);
+
if (!netif_running(netdev))
return 0;
macb_set_rx_mode(netdev);
macb_restore_features(bp);
rtnl_lock();
- if (!device_may_wakeup(&bp->dev->dev))
- phy_init(bp->sgmii_phy);
phylink_start(bp->phylink);
rtnl_unlock();
}
/* Free the sk buffer associated with this last transmit */
- dev_kfree_skb_any(skb);
+ napi_consume_skb(skb, budget);
} else if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
xdp_return_frame_rx_napi(xdpf);
} else { /* recycle pages of XDP_TX frames */
* @hw: pointer to the HW structure.
* @module_pointer: module pointer location in words from the NVM beginning
* @offset: offset in words from module start
- * @words: number of words to write
- * @data: buffer with words to write to the Shadow RAM
+ * @words: number of words to read
+ * @data: buffer with words to read to the Shadow RAM
* @last_command: tells the AdminQ that this is the last command
*
- * Writes a 16 bit words buffer to the Shadow RAM using the admin command.
+ * Reads a 16 bit words buffer to the Shadow RAM using the admin command.
**/
static int i40e_read_nvm_aq(struct i40e_hw *hw,
u8 module_pointer, u32 offset,
*/
if ((offset + words) > hw->nvm.sr_size)
i40e_debug(hw, I40E_DEBUG_NVM,
- "NVM write error: offset %d beyond Shadow RAM limit %d\n",
+ "NVM read error: offset %d beyond Shadow RAM limit %d\n",
(offset + words), hw->nvm.sr_size);
else if (words > I40E_SR_SECTOR_SIZE_IN_WORDS)
- /* We can write only up to 4KB (one sector), in one AQ write */
+ /* We can read only up to 4KB (one sector), in one AQ write */
i40e_debug(hw, I40E_DEBUG_NVM,
- "NVM write fail error: tried to write %d words, limit is %d.\n",
+ "NVM read fail error: tried to read %d words, limit is %d.\n",
words, I40E_SR_SECTOR_SIZE_IN_WORDS);
else if (((offset + (words - 1)) / I40E_SR_SECTOR_SIZE_IN_WORDS)
!= (offset / I40E_SR_SECTOR_SIZE_IN_WORDS))
- /* A single write cannot spread over two sectors */
+ /* A single read cannot spread over two sectors */
i40e_debug(hw, I40E_DEBUG_NVM,
- "NVM write error: cannot spread over two sectors in a single write offset=%d words=%d\n",
+ "NVM read error: cannot spread over two sectors in a single read offset=%d words=%d\n",
offset, words);
else
ret_code = i40e_aq_read_nvm(hw, module_pointer,
fltr->ip_mask.src_port = fsp->m_u.tcp_ip4_spec.psrc;
fltr->ip_mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst;
fltr->ip_mask.tos = fsp->m_u.tcp_ip4_spec.tos;
+ fltr->ip_ver = 4;
break;
case AH_V4_FLOW:
case ESP_V4_FLOW:
fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.ah_ip4_spec.ip4dst;
fltr->ip_mask.spi = fsp->m_u.ah_ip4_spec.spi;
fltr->ip_mask.tos = fsp->m_u.ah_ip4_spec.tos;
+ fltr->ip_ver = 4;
break;
case IPV4_USER_FLOW:
fltr->ip_data.v4_addrs.src_ip = fsp->h_u.usr_ip4_spec.ip4src;
fltr->ip_mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes;
fltr->ip_mask.tos = fsp->m_u.usr_ip4_spec.tos;
fltr->ip_mask.proto = fsp->m_u.usr_ip4_spec.proto;
+ fltr->ip_ver = 4;
break;
case TCP_V6_FLOW:
case UDP_V6_FLOW:
fltr->ip_mask.src_port = fsp->m_u.tcp_ip6_spec.psrc;
fltr->ip_mask.dst_port = fsp->m_u.tcp_ip6_spec.pdst;
fltr->ip_mask.tclass = fsp->m_u.tcp_ip6_spec.tclass;
+ fltr->ip_ver = 6;
break;
case AH_V6_FLOW:
case ESP_V6_FLOW:
sizeof(struct in6_addr));
fltr->ip_mask.spi = fsp->m_u.ah_ip6_spec.spi;
fltr->ip_mask.tclass = fsp->m_u.ah_ip6_spec.tclass;
+ fltr->ip_ver = 6;
break;
case IPV6_USER_FLOW:
memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.usr_ip6_spec.ip6src,
fltr->ip_mask.l4_header = fsp->m_u.usr_ip6_spec.l4_4_bytes;
fltr->ip_mask.tclass = fsp->m_u.usr_ip6_spec.tclass;
fltr->ip_mask.proto = fsp->m_u.usr_ip6_spec.l4_proto;
+ fltr->ip_ver = 6;
break;
case ETHER_FLOW:
fltr->eth_data.etype = fsp->h_u.ether_spec.h_proto;
return -EINVAL;
}
+ err = iavf_validate_fdir_fltr_masks(adapter, fltr);
+ if (err)
+ return err;
+
if (iavf_fdir_is_dup_fltr(adapter, fltr))
return -EEXIST;
}
};
+static const struct in6_addr ipv6_addr_zero_mask = {
+ .in6_u = {
+ .u6_addr8 = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ }
+ }
+};
+
+/**
+ * iavf_validate_fdir_fltr_masks - validate Flow Director filter fields masks
+ * @adapter: pointer to the VF adapter structure
+ * @fltr: Flow Director filter data structure
+ *
+ * Returns 0 if all masks of packet fields are either full or empty. Returns
+ * error on at least one partial mask.
+ */
+int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter,
+ struct iavf_fdir_fltr *fltr)
+{
+ if (fltr->eth_mask.etype && fltr->eth_mask.etype != htons(U16_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_ver == 4) {
+ if (fltr->ip_mask.v4_addrs.src_ip &&
+ fltr->ip_mask.v4_addrs.src_ip != htonl(U32_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_mask.v4_addrs.dst_ip &&
+ fltr->ip_mask.v4_addrs.dst_ip != htonl(U32_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_mask.tos && fltr->ip_mask.tos != U8_MAX)
+ goto partial_mask;
+ } else if (fltr->ip_ver == 6) {
+ if (memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_zero_mask,
+ sizeof(struct in6_addr)) &&
+ memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_full_mask,
+ sizeof(struct in6_addr)))
+ goto partial_mask;
+
+ if (memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_zero_mask,
+ sizeof(struct in6_addr)) &&
+ memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_full_mask,
+ sizeof(struct in6_addr)))
+ goto partial_mask;
+
+ if (fltr->ip_mask.tclass && fltr->ip_mask.tclass != U8_MAX)
+ goto partial_mask;
+ }
+
+ if (fltr->ip_mask.proto && fltr->ip_mask.proto != U8_MAX)
+ goto partial_mask;
+
+ if (fltr->ip_mask.src_port && fltr->ip_mask.src_port != htons(U16_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_mask.dst_port && fltr->ip_mask.dst_port != htons(U16_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_mask.spi && fltr->ip_mask.spi != htonl(U32_MAX))
+ goto partial_mask;
+
+ if (fltr->ip_mask.l4_header &&
+ fltr->ip_mask.l4_header != htonl(U32_MAX))
+ goto partial_mask;
+
+ return 0;
+
+partial_mask:
+ dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, partial masks are not supported\n");
+ return -EOPNOTSUPP;
+}
+
/**
* iavf_pkt_udp_no_pay_len - the length of UDP packet without payload
* @fltr: Flow Director filter data structure
VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DST);
}
- fltr->ip_ver = 4;
-
return 0;
}
VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, DST);
}
- fltr->ip_ver = 6;
-
return 0;
}
struct virtchnl_fdir_add vc_add_msg;
};
+int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter,
+ struct iavf_fdir_fltr *fltr);
int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
{
+ if (ice_is_adq_active(pf)) {
+ dev_err(ice_pf_to_dev(pf), "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root");
+ NL_SET_ERR_MSG_MOD(extack, "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root");
+ return -EOPNOTSUPP;
+ }
+
dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev",
pf->hw.pf_id);
NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev");
ice_setup_tc_block_cb,
np, np, true);
case TC_SETUP_QDISC_MQPRIO:
+ if (ice_is_eswitch_mode_switchdev(pf)) {
+ netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n");
+ return -EOPNOTSUPP;
+ }
+
if (pf->adev) {
mutex_lock(&pf->adev_mutex);
device_lock(&pf->adev->dev);
list_add_tail(&d->list, &oct->ctrl_req_wait_list);
ret = wait_event_interruptible_timeout(oct->ctrl_req_wait_q,
(d->done != 0),
- jiffies + msecs_to_jiffies(500));
+ msecs_to_jiffies(500));
list_del(&d->list);
if (ret == 0 || ret == 1)
return -EAGAIN;
{
int i;
+ oct->poll_non_ioq_intr = false;
+ cancel_delayed_work_sync(&oct->intr_poll_task);
+ cancel_work_sync(&oct->ctrl_mbox_task);
+
dev_info(&oct->pdev->dev, "Cleaning up Octeon Device ...\n");
for (i = 0; i < OCTEP_MAX_VF; i++) {
if (!oct)
return;
- cancel_work_sync(&oct->tx_timeout_task);
- cancel_work_sync(&oct->ctrl_mbox_task);
netdev = oct->netdev;
if (netdev->reg_state == NETREG_REGISTERED)
unregister_netdev(netdev);
- oct->poll_non_ioq_intr = false;
- cancel_delayed_work_sync(&oct->intr_poll_task);
+ cancel_work_sync(&oct->tx_timeout_task);
octep_device_cleanup(oct);
pci_release_mem_regions(pdev);
free_netdev(netdev);
* MLX5E_XDP_XMIT_MODE_XSK:
* none.
*/
+#define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4
+
union mlx5e_xdp_info {
enum mlx5e_xdp_xmit_mode mode;
union {
{
struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- int entries = wq_sz * MLX5_SEND_WQEBB_NUM_DS * 2; /* upper bound for maximum num of
- * entries of all xmit_modes.
- */
+ int entries;
size_t size;
+ /* upper bound for maximum num of entries of all xmit_modes. */
+ entries = roundup_pow_of_two(wq_sz * MLX5_SEND_WQEBB_NUM_DS *
+ MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO);
+
size = array_size(sizeof(*xdpi_fifo->xi), entries);
xdpi_fifo->xi = kvzalloc_node(size, GFP_KERNEL, numa);
if (!xdpi_fifo->xi)
mlx5_lag_is_shared_fdb(dev) &&
mlx5_lag_is_master(dev)) {
struct mlx5_core_dev *peer_dev;
- int i;
+ int i, j;
mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
err = mlx5_cmd_set_slave_root_fdb(dev, peer_dev, !disconnect,
(!disconnect) ? ft->id : 0);
if (err && !disconnect) {
+ mlx5_lag_for_each_peer_mdev(dev, peer_dev, j) {
+ if (j < i)
+ mlx5_cmd_set_slave_root_fdb(dev, peer_dev, 1,
+ ns->root_ft->id);
+ else
+ break;
+ }
+
MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
MLX5_SET(set_flow_table_root_in, in, table_id,
ns->root_ft->id);
}
#endif
+static int __maybe_unused qede_suspend(struct device *dev)
+{
+ dev_info(dev, "Device does not support suspend operation\n");
+
+ return -EOPNOTSUPP;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(qede_pm_ops, qede_suspend, NULL);
+
static const struct pci_error_handlers qede_err_handler = {
.error_detected = qede_io_error_detected,
};
.sriov_configure = qede_sriov_configure,
#endif
.err_handler = &qede_err_handler,
+ .driver.pm = &qede_pm_ops,
};
static struct qed_eth_cb_ops qede_ll_ops = {
net_dev->features |= NETIF_F_HW_TC;
efx->fixed_features |= NETIF_F_HW_TC;
}
- return rc;
+ return 0;
}
int ef100_probe_vf(struct efx_nic *efx)
rc = efx_mae_get_tables(efx);
if (rc)
return rc;
- efx->tc->up = true;
rc = flow_indr_dev_register(efx_tc_indr_setup_cb, efx);
if (rc)
goto out_free;
+ efx->tc->up = true;
return 0;
out_free:
efx_mae_free_tables(efx);
return efx_tc_ct_stats(ct_zone, tcb);
default:
break;
- };
+ }
return -EOPNOTSUPP;
}
/* restore vlan configurations */
vlan_for_each(ndev, cpsw_restore_vlans, port);
- /* Initialize QoS */
- am65_cpsw_qos_mqprio_init(port);
-
phylink_start(port->slave.phylink);
return 0;
#define AM65_CPSW_REG_CTL 0x004
#define AM65_CPSW_PN_REG_CTL 0x004
-#define AM65_CPSW_PN_REG_TX_PRI_MAP 0x018
-#define AM65_CPSW_PN_REG_RX_PRI_MAP 0x020
#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050
#define AM65_CPSW_PN_REG_EST_CTL 0x060
#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri))
-#define AM65_CPSW_PN_REG_PRI_EIR(pri) (0x160 + 4 * (pri))
/* AM65_CPSW_REG_CTL register fields */
#define AM65_CPSW_CTL_EST_EN BIT(18)
TACT_SKIP_PROG, /* just buffer can be updated */
};
-/* number of traffic classes (FIFOs) per port */
-#define AM65_CPSW_PN_TC_NUM 8
-#define AM65_CPSW_PN_TX_PRI_MAP_DEFAULT 0x76543210
-
-static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data);
-
static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port)
{
return port->qos.est_oper || port->qos.est_admin;
ktime_t cur_time;
s64 delta;
+ port->qos.link_speed = link_speed;
if (!am65_cpsw_port_est_enabled(port))
return;
return am65_cpsw_tc_query_caps(ndev, type_data);
case TC_SETUP_QDISC_TAPRIO:
return am65_cpsw_setup_taprio(ndev, type_data);
- case TC_SETUP_QDISC_MQPRIO:
- return am65_cpsw_setup_mqprio(ndev, type_data);
case TC_SETUP_BLOCK:
return am65_cpsw_qos_setup_tc_block(ndev, type_data);
default:
}
}
-static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port);
-
void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
{
struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
- port->qos.link_speed = link_speed;
- am65_cpsw_tx_pn_shaper_link_up(port);
-
if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
return;
host->port_base + AM65_CPSW_PN_REG_PRI_CIR(tx_ch));
}
}
-
-static void am65_cpsw_tx_pn_shaper_apply(struct am65_cpsw_port *port)
-{
- struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
- struct am65_cpsw_common *common = port->common;
- struct tc_mqprio_qopt_offload *mqprio;
- bool shaper_en;
- u32 rate_mbps;
- int i;
-
- mqprio = &p_mqprio->mqprio_hw;
- shaper_en = p_mqprio->shaper_en && !p_mqprio->shaper_susp;
-
- for (i = 0; i < mqprio->qopt.num_tc; i++) {
- rate_mbps = 0;
- if (shaper_en) {
- rate_mbps = mqprio->min_rate[i] * 8 / 1000000;
- rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
- common->bus_freq);
- }
-
- writel(rate_mbps,
- port->port_base + AM65_CPSW_PN_REG_PRI_CIR(i));
- }
-
- for (i = 0; i < mqprio->qopt.num_tc; i++) {
- rate_mbps = 0;
- if (shaper_en && mqprio->max_rate[i]) {
- rate_mbps = mqprio->max_rate[i] - mqprio->min_rate[i];
- rate_mbps = rate_mbps * 8 / 1000000;
- rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
- common->bus_freq);
- }
-
- writel(rate_mbps,
- port->port_base + AM65_CPSW_PN_REG_PRI_EIR(i));
- }
-}
-
-static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port)
-{
- struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
- struct am65_cpsw_common *common = port->common;
- bool shaper_susp = false;
-
- if (!p_mqprio->enable || !p_mqprio->shaper_en)
- return;
-
- if (p_mqprio->max_rate_total > port->qos.link_speed)
- shaper_susp = true;
-
- if (p_mqprio->shaper_susp == shaper_susp)
- return;
-
- if (shaper_susp)
- dev_info(common->dev,
- "Port%u: total shaper tx rate > link speed - suspend shaper\n",
- port->port_id);
- else
- dev_info(common->dev,
- "Port%u: link recover - resume shaper\n",
- port->port_id);
-
- p_mqprio->shaper_susp = shaper_susp;
- am65_cpsw_tx_pn_shaper_apply(port);
-}
-
-void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port)
-{
- struct am65_cpsw_host *host = am65_common_get_host(port->common);
- struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
- struct tc_mqprio_qopt_offload *mqprio;
- u32 tx_prio_map = 0, rx_prio_map;
- int i, fifo;
-
- mqprio = &p_mqprio->mqprio_hw;
- rx_prio_map = readl(host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
-
- if (p_mqprio->enable) {
- for (i = 0; i < AM65_CPSW_PN_TC_NUM; i++) {
- fifo = mqprio->qopt.prio_tc_map[i];
- tx_prio_map |= fifo << (4 * i);
- }
-
- netdev_set_num_tc(port->ndev, mqprio->qopt.num_tc);
- for (i = 0; i < mqprio->qopt.num_tc; i++) {
- netdev_set_tc_queue(port->ndev, i,
- mqprio->qopt.count[i],
- mqprio->qopt.offset[i]);
- if (!i) {
- p_mqprio->tc0_q = mqprio->qopt.offset[i];
- rx_prio_map &= ~(0x7 << (4 * p_mqprio->tc0_q));
- }
- }
- } else {
- /* restore default configuration */
- netdev_reset_tc(port->ndev);
- tx_prio_map = AM65_CPSW_PN_TX_PRI_MAP_DEFAULT;
- rx_prio_map |= p_mqprio->tc0_q << (4 * p_mqprio->tc0_q);
- p_mqprio->tc0_q = 0;
- }
-
- writel(tx_prio_map,
- port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
- writel(rx_prio_map,
- host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
-
- am65_cpsw_tx_pn_shaper_apply(port);
-}
-
-static int am65_cpsw_mqprio_verify(struct am65_cpsw_port *port,
- struct tc_mqprio_qopt_offload *mqprio)
-{
- int i;
-
- for (i = 0; i < mqprio->qopt.num_tc; i++) {
- unsigned int last = mqprio->qopt.offset[i] +
- mqprio->qopt.count[i];
-
- if (mqprio->qopt.offset[i] >= port->ndev->real_num_tx_queues ||
- !mqprio->qopt.count[i] ||
- last > port->ndev->real_num_tx_queues)
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int am65_cpsw_mqprio_verify_shaper(struct am65_cpsw_port *port,
- struct tc_mqprio_qopt_offload *mqprio,
- u64 *max_rate)
-{
- struct am65_cpsw_common *common = port->common;
- u64 min_rate_total = 0, max_rate_total = 0;
- u32 min_rate_msk = 0, max_rate_msk = 0;
- bool has_min_rate, has_max_rate;
- int num_tc, i;
-
- has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
- has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
-
- if (!has_min_rate && has_max_rate)
- return -EOPNOTSUPP;
-
- if (!has_min_rate)
- return 0;
-
- num_tc = mqprio->qopt.num_tc;
-
- for (i = num_tc - 1; i >= 0; i--) {
- u32 ch_msk;
-
- if (mqprio->min_rate[i])
- min_rate_msk |= BIT(i);
- min_rate_total += mqprio->min_rate[i];
-
- if (has_max_rate) {
- if (mqprio->max_rate[i])
- max_rate_msk |= BIT(i);
- max_rate_total += mqprio->max_rate[i];
-
- if (!mqprio->min_rate[i] && mqprio->max_rate[i]) {
- dev_err(common->dev, "TX tc%d rate max>0 but min=0\n",
- i);
- return -EINVAL;
- }
-
- if (mqprio->max_rate[i] &&
- mqprio->max_rate[i] < mqprio->min_rate[i]) {
- dev_err(common->dev, "TX tc%d rate min(%llu)>max(%llu)\n",
- i, mqprio->min_rate[i],
- mqprio->max_rate[i]);
- return -EINVAL;
- }
- }
-
- ch_msk = GENMASK(num_tc - 1, i);
- if ((min_rate_msk & BIT(i)) && (min_rate_msk ^ ch_msk)) {
- dev_err(common->dev, "TX Min rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
- min_rate_msk);
- return -EINVAL;
- }
-
- if ((max_rate_msk & BIT(i)) && (max_rate_msk ^ ch_msk)) {
- dev_err(common->dev, "TX max rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
- max_rate_msk);
- return -EINVAL;
- }
- }
- min_rate_total *= 8;
- min_rate_total /= 1000 * 1000;
- max_rate_total *= 8;
- max_rate_total /= 1000 * 1000;
-
- if (port->qos.link_speed != SPEED_UNKNOWN) {
- if (min_rate_total > port->qos.link_speed) {
- dev_err(common->dev, "TX rate min exceed %llu link speed %d\n",
- min_rate_total, port->qos.link_speed);
- return -EINVAL;
- }
-
- if (max_rate_total > port->qos.link_speed) {
- dev_err(common->dev, "TX rate max exceed %llu link speed %d\n",
- max_rate_total, port->qos.link_speed);
- return -EINVAL;
- }
- }
-
- *max_rate = max_t(u64, min_rate_total, max_rate_total);
-
- return 0;
-}
-
-static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data)
-{
- struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
- struct tc_mqprio_qopt_offload *mqprio = type_data;
- struct am65_cpsw_common *common = port->common;
- struct am65_cpsw_mqprio *p_mqprio;
- bool has_min_rate;
- int num_tc, ret;
- u64 max_rate;
-
- p_mqprio = &port->qos.mqprio;
-
- if (!mqprio->qopt.hw)
- goto skip_check;
-
- if (mqprio->mode != TC_MQPRIO_MODE_CHANNEL)
- return -EOPNOTSUPP;
-
- num_tc = mqprio->qopt.num_tc;
- if (num_tc > AM65_CPSW_PN_TC_NUM)
- return -ERANGE;
-
- if ((mqprio->flags & TC_MQPRIO_F_SHAPER) &&
- mqprio->shaper != TC_MQPRIO_SHAPER_BW_RATE)
- return -EOPNOTSUPP;
-
- ret = am65_cpsw_mqprio_verify(port, mqprio);
- if (ret)
- return ret;
-
- ret = am65_cpsw_mqprio_verify_shaper(port, mqprio, &max_rate);
- if (ret)
- return ret;
-
-skip_check:
- ret = pm_runtime_get_sync(common->dev);
- if (ret < 0) {
- pm_runtime_put_noidle(common->dev);
- return ret;
- }
-
- if (mqprio->qopt.hw) {
- memcpy(&p_mqprio->mqprio_hw, mqprio, sizeof(*mqprio));
- has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
- p_mqprio->enable = 1;
- p_mqprio->shaper_en = has_min_rate;
- p_mqprio->shaper_susp = !has_min_rate;
- p_mqprio->max_rate_total = max_rate;
- } else {
- unsigned int tc0_q = p_mqprio->tc0_q;
-
- memset(p_mqprio, 0, sizeof(*p_mqprio));
- p_mqprio->mqprio_hw.qopt.num_tc = AM65_CPSW_PN_TC_NUM;
- p_mqprio->tc0_q = tc0_q;
- }
-
- if (!netif_running(ndev))
- goto exit_put;
-
- am65_cpsw_qos_mqprio_init(port);
-
-exit_put:
- pm_runtime_put(common->dev);
- return 0;
-}
#include <linux/netdevice.h>
#include <net/pkt_sched.h>
-#include <net/pkt_cls.h>
struct am65_cpsw_common;
-struct am65_cpsw_port;
struct am65_cpsw_est {
int buf;
struct tc_taprio_qopt_offload taprio;
};
-struct am65_cpsw_mqprio {
- struct tc_mqprio_qopt_offload mqprio_hw;
- u64 max_rate_total;
-
- unsigned enable:1;
- unsigned shaper_en:1;
- unsigned shaper_susp:1;
- unsigned tc0_q:3;
-};
-
struct am65_cpsw_ale_ratelimit {
unsigned long cookie;
u64 rate_packet_ps;
struct am65_cpsw_est *est_oper;
ktime_t link_down_time;
int link_speed;
- struct am65_cpsw_mqprio mqprio;
struct am65_cpsw_ale_ratelimit ale_bc_ratelimit;
struct am65_cpsw_ale_ratelimit ale_mc_ratelimit;
void *type_data);
void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
void am65_cpsw_qos_link_down(struct net_device *ndev);
-void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port);
int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps);
void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common);
of_id = of_match_device(xgene_mdio_of_match, &pdev->dev);
if (of_id) {
- mdio_id = (enum xgene_mdio_id)of_id->data;
+ mdio_id = (uintptr_t)of_id->data;
} else {
#ifdef CONFIG_ACPI
const struct acpi_device_id *acpi_id;
#endif /* CONFIG_NETCONSOLE_DYNAMIC */
-/* Allocate new target (from boot/module param) and setup netpoll for it */
-static struct netconsole_target *alloc_param_target(char *target_config)
+/* Allocate and initialize with defaults.
+ * Note that these targets get their config_item fields zeroed-out.
+ */
+static struct netconsole_target *alloc_and_init(void)
{
- int err = -ENOMEM;
struct netconsole_target *nt;
- /*
- * Allocate and initialize with defaults.
- * Note that these targets get their config_item fields zeroed-out.
- */
nt = kzalloc(sizeof(*nt), GFP_KERNEL);
if (!nt)
- goto fail;
+ return nt;
+
+ if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG))
+ nt->extended = true;
+ if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE))
+ nt->release = true;
nt->np.name = "netconsole";
strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
nt->np.remote_port = 6666;
eth_broadcast_addr(nt->np.remote_mac);
+ return nt;
+}
+
+/* Allocate new target (from boot/module param) and setup netpoll for it */
+static struct netconsole_target *alloc_param_target(char *target_config)
+{
+ struct netconsole_target *nt;
+ int err;
+
+ nt = alloc_and_init();
+ if (!nt) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
if (*target_config == '+') {
nt->extended = true;
target_config++;
if (*target_config == 'r') {
if (!nt->extended) {
pr_err("Netconsole configuration error. Release feature requires extended log message");
+ err = -EINVAL;
goto fail;
}
nt->release = true;
static struct config_item *make_netconsole_target(struct config_group *group,
const char *name)
{
- unsigned long flags;
struct netconsole_target *nt;
+ unsigned long flags;
- /*
- * Allocate and initialize with defaults.
- * Target is disabled at creation (!enabled).
- */
- nt = kzalloc(sizeof(*nt), GFP_KERNEL);
+ nt = alloc_and_init();
if (!nt)
return ERR_PTR(-ENOMEM);
- nt->np.name = "netconsole";
- strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
- nt->np.local_port = 6665;
- nt->np.remote_port = 6666;
- eth_broadcast_addr(nt->np.remote_mac);
-
/* Initialize the config_item member */
config_item_init_type_name(&nt->item, name, &netconsole_target_type);
pdev = of_find_device_by_node(pcs_np);
of_node_put(pcs_np);
- if (!pdev || !platform_get_drvdata(pdev))
+ if (!pdev || !platform_get_drvdata(pdev)) {
+ if (pdev)
+ put_device(&pdev->dev);
return ERR_PTR(-EPROBE_DEFER);
+ }
miic_port = kzalloc(sizeof(*miic_port), GFP_KERNEL);
- if (!miic_port)
+ if (!miic_port) {
+ put_device(&pdev->dev);
return ERR_PTR(-ENOMEM);
+ }
miic = platform_get_drvdata(pdev);
device_link_add(dev, miic->dev, DL_FLAG_AUTOREMOVE_CONSUMER);
+ put_device(&pdev->dev);
miic_port->miic = miic;
miic_port->port = port - 1;
return bcm54xx_config_init(phydev);
}
+static int bcm54810_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
+{
+ return -EOPNOTSUPP;
+}
+
+static int bcm54810_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
+ u16 val)
+{
+ return -EOPNOTSUPP;
+}
+
static int bcm54811_config_init(struct phy_device *phydev)
{
int err, reg;
.get_strings = bcm_phy_get_strings,
.get_stats = bcm54xx_get_stats,
.probe = bcm54xx_phy_probe,
+ .read_mmd = bcm54810_read_mmd,
+ .write_mmd = bcm54810_write_mmd,
.config_init = bcm54xx_config_init,
.config_aneg = bcm5481_config_aneg,
.config_intr = bcm_phy_config_intr,
goto out;
}
+ phy_disable_interrupts(phydev);
+
/* Start out supporting everything. Eventually,
* a controller will attach, and may modify one
* or both of these values
return 0;
}
-static void phy_shutdown(struct device *dev)
-{
- struct phy_device *phydev = to_phy_device(dev);
-
- if (phydev->state == PHY_READY || !phydev->attached_dev)
- return;
-
- phy_disable_interrupts(phydev);
-}
-
/**
* phy_driver_register - register a phy_driver with the PHY layer
* @new_driver: new phy_driver to register
new_driver->mdiodrv.driver.bus = &mdio_bus_type;
new_driver->mdiodrv.driver.probe = phy_probe;
new_driver->mdiodrv.driver.remove = phy_remove;
- new_driver->mdiodrv.driver.shutdown = phy_shutdown;
new_driver->mdiodrv.driver.owner = owner;
new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
dev->hw_features = TEAM_VLAN_FEATURES |
NETIF_F_HW_VLAN_CTAG_RX |
- NETIF_F_HW_VLAN_CTAG_FILTER;
+ NETIF_F_HW_VLAN_CTAG_FILTER |
+ NETIF_F_HW_VLAN_STAG_RX |
+ NETIF_F_HW_VLAN_STAG_FILTER;
dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
dev->features |= dev->hw_features;
return ret;
}
-static void tun_cleanup(void)
+static void __exit tun_cleanup(void)
{
misc_deregister(&tun_miscdev);
rtnl_link_unregister(&tun_link_ops);
err_xdp_ring:
for (i--; i >= start; i--)
ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
+ i = end;
err_page_pool:
- for (i = start; i < end; i++) {
+ for (i--; i >= start; i--) {
page_pool_destroy(priv->rq[i].page_pool);
priv->rq[i].page_pool = NULL;
}
vi->ctrl->rss.indirection_table[i] = indir_val;
}
- vi->ctrl->rss.max_tx_vq = vi->curr_queue_pairs;
+ vi->ctrl->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0;
vi->ctrl->rss.hash_key_length = vi->rss_key_size;
netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size);
if (vi->has_rss || vi->has_rss_hash_report)
virtnet_init_default_rss(vi);
- _virtnet_set_queues(vi, vi->curr_queue_pairs);
-
/* serialize netdev register + virtio_device_ready() with ndo_open() */
rtnl_lock();
virtio_device_ready(vdev);
+ _virtnet_set_queues(vi, vi->curr_queue_pairs);
+
/* a random MAC address has been assigned, notify the device.
* We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there
* because many devices work fine without getting MAC explicitly
*/
nvme_mpath_clear_ctrl_paths(ctrl);
+ /*
+ * Unquiesce io queues so any pending IO won't hang, especially
+ * those submitted from scan work
+ */
+ nvme_unquiesce_io_queues(ctrl);
+
/* prevent racing with ns scanning */
flush_work(&ctrl->scan_work);
* removing the namespaces' disks; fail all the queues now to avoid
* potentially having to clean up the failed sync later.
*/
- if (ctrl->state == NVME_CTRL_DEAD) {
+ if (ctrl->state == NVME_CTRL_DEAD)
nvme_mark_namespaces_dead(ctrl);
- nvme_unquiesce_io_queues(ctrl);
- }
/* this is a no-op when called from the controller reset handler */
nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
return 0;
- rcu_read_lock();
req = READ_ONCE(ioucmd->cookie);
if (req && blk_rq_is_poll(req))
ret = blk_rq_poll(req, iob, poll_flags);
- rcu_read_unlock();
return ret;
}
#ifdef CONFIG_NVME_MULTIPATH
{ PCI_DEVICE(0x1d97, 0x2263), /* SPCC */
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x144d, 0xa80b), /* Samsung PM9B1 256G and 512G */
- .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES |
+ NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x144d, 0xa802), /* Samsung SM953 */
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_unquiesce_io_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
if (ctrl->queue_count <= 1)
return;
nvme_quiesce_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
MODULE_PARM_DESC(sba_reserve_agpgart, "Reserve half of IO pdir as AGPGART");
#endif
+struct proc_dir_entry *proc_runway_root __ro_after_init;
+struct proc_dir_entry *proc_mckinley_root __ro_after_init;
/************************************
** SBA register read and write support
#ifdef CONFIG_PROC_FS
switch (dev->id.hversion) {
case PLUTO_MCKINLEY_PORT:
+ if (!proc_mckinley_root)
+ proc_mckinley_root = proc_mkdir("bus/mckinley", NULL);
root = proc_mckinley_root;
break;
case ASTRO_RUNWAY_PORT:
case IKE_MERCED_PORT:
default:
+ if (!proc_runway_root)
+ proc_runway_root = proc_mkdir("bus/runway", NULL);
root = proc_runway_root;
break;
}
depends on MVEBU_MBUS
depends on ARM
depends on OF
- depends on BROKEN
select PCI_BRIDGE_EMUL
help
Add support for Marvell EBU PCIe controller. This PCIe controller
if (ret)
goto err_remove_edma;
- if (dw_pcie_link_up(pci)) {
- dw_pcie_print_link_status(pci);
- } else {
+ if (!dw_pcie_link_up(pci)) {
ret = dw_pcie_start_link(pci);
if (ret)
goto err_remove_edma;
-
- if (pci->ops && pci->ops->start_link) {
- ret = dw_pcie_wait_for_link(pci);
- if (ret)
- goto err_stop_link;
- }
}
+ /* Ignore errors, the link may come up later */
+ dw_pcie_wait_for_link(pci);
+
bridge->sysdata = pp;
ret = pci_host_probe(bridge);
dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0);
}
-void dw_pcie_print_link_status(struct dw_pcie *pci)
-{
- u32 offset, val;
-
- offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
- val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
-
- dev_info(pci->dev, "PCIe Gen.%u x%u link up\n",
- FIELD_GET(PCI_EXP_LNKSTA_CLS, val),
- FIELD_GET(PCI_EXP_LNKSTA_NLW, val));
-}
-
int dw_pcie_wait_for_link(struct dw_pcie *pci)
{
+ u32 offset, val;
int retries;
/* Check if the link is up or not */
return -ETIMEDOUT;
}
- dw_pcie_print_link_status(pci);
+ offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+ val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
+
+ dev_info(pci->dev, "PCIe Gen.%u x%u link up\n",
+ FIELD_GET(PCI_EXP_LNKSTA_CLS, val),
+ FIELD_GET(PCI_EXP_LNKSTA_NLW, val));
return 0;
}
void dw_pcie_iatu_detect(struct dw_pcie *pci);
int dw_pcie_edma_detect(struct dw_pcie *pci);
void dw_pcie_edma_remove(struct dw_pcie *pci);
-void dw_pcie_print_link_status(struct dw_pcie *pci);
static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val)
{
acpiphp_native_scan_bridge(dev);
}
} else {
+ LIST_HEAD(add_list);
int max, pass;
acpiphp_rescan_slot(slot);
if (pass && dev->subordinate) {
check_hotplug_bridge(slot, dev);
pcibios_resource_survey_bus(dev->subordinate);
+ if (pci_is_root_bus(bus))
+ __pci_bus_size_bridges(dev->subordinate, &add_list);
}
}
}
- pci_assign_unassigned_bridge_resources(bus->self);
+ if (pci_is_root_bus(bus))
+ __pci_bus_assign_resources(bus, &add_list, NULL);
+ else
+ pci_assign_unassigned_bridge_resources(bus->self);
}
acpiphp_sanitize_bus(bus);
int amd_pmf_power_slider_update_event(struct amd_pmf_dev *dev)
{
- u8 mode, flag = 0;
+ u8 flag = 0;
+ int mode;
int src;
mode = amd_pmf_get_pprof_modes(dev);
node = dev_to_node(&_pci_dev->dev);
if (node == NUMA_NO_NODE) {
- pr_info("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n",
- cpu, bus_no, dev, fn);
+ pr_info_once("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n",
+ cpu, bus_no, dev, fn);
continue;
}
module_param(ec_trigger, bool, 0444);
MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events");
+static bool force;
+module_param(force, bool, 0444);
+MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type");
+
static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = {
{
/* Lenovo Yoga 7 14ARB7 */
{ }
};
+static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */),
+ },
+ },
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */),
+ },
+ },
+ { }
+};
+
struct lenovo_ymc_private {
struct input_dev *input_dev;
struct acpi_device *ec_acpi_dev;
struct input_dev *input_dev;
int err;
+ if (!dmi_check_system(allowed_chasis_types_dmi_table)) {
+ if (force)
+ dev_info(&wdev->dev, "Force loading Lenovo YMC support\n");
+ else
+ return -ENODEV;
+ }
+
ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table);
priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL);
#define MLXPLAT_CPLD_LPC_REG_PWM_CONTROL_OFFSET 0x37
#define MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET 0x3a
#define MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET 0x3b
-#define MLXPLAT_CPLD_LPC_REG_DBG1_OFFSET 0x3c
-#define MLXPLAT_CPLD_LPC_REG_DBG2_OFFSET 0x3d
-#define MLXPLAT_CPLD_LPC_REG_DBG3_OFFSET 0x3e
-#define MLXPLAT_CPLD_LPC_REG_DBG4_OFFSET 0x3f
#define MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET 0x40
#define MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET 0x41
#define MLXPLAT_CPLD_LPC_REG_AGGRCO_OFFSET 0x42
#define MLXPLAT_CPLD_LPC_REG_LC_SD_EVENT_OFFSET 0xaa
#define MLXPLAT_CPLD_LPC_REG_LC_SD_MASK_OFFSET 0xab
#define MLXPLAT_CPLD_LPC_REG_LC_PWR_ON 0xb2
+#define MLXPLAT_CPLD_LPC_REG_DBG1_OFFSET 0xb6
+#define MLXPLAT_CPLD_LPC_REG_DBG2_OFFSET 0xb7
+#define MLXPLAT_CPLD_LPC_REG_DBG3_OFFSET 0xb8
+#define MLXPLAT_CPLD_LPC_REG_DBG4_OFFSET 0xb9
#define MLXPLAT_CPLD_LPC_REG_GP4_RO_OFFSET 0xc2
#define MLXPLAT_CPLD_LPC_REG_SPI_CHNL_SELECT 0xc3
#define MLXPLAT_CPLD_LPC_REG_WD_CLEAR_OFFSET 0xc7
MLXPLAT_CPLD_AGGR_MASK_LC_SDWN)
#define MLXPLAT_CPLD_LOW_AGGR_MASK_LOW 0xc1
#define MLXPLAT_CPLD_LOW_AGGR_MASK_ASIC2 BIT(2)
-#define MLXPLAT_CPLD_LOW_AGGR_MASK_PWR_BUT BIT(4)
+#define MLXPLAT_CPLD_LOW_AGGR_MASK_PWR_BUT GENMASK(5, 4)
#define MLXPLAT_CPLD_LOW_AGGR_MASK_I2C BIT(6)
#define MLXPLAT_CPLD_PSU_MASK GENMASK(1, 0)
#define MLXPLAT_CPLD_PWR_MASK GENMASK(1, 0)
#define MLXPLAT_CPLD_GWP_MASK GENMASK(0, 0)
#define MLXPLAT_CPLD_EROT_MASK GENMASK(1, 0)
#define MLXPLAT_CPLD_PWR_BUTTON_MASK BIT(0)
-#define MLXPLAT_CPLD_LATCH_RST_MASK BIT(5)
+#define MLXPLAT_CPLD_LATCH_RST_MASK BIT(6)
#define MLXPLAT_CPLD_THERMAL1_PDB_MASK BIT(3)
#define MLXPLAT_CPLD_THERMAL2_PDB_MASK BIT(4)
#define MLXPLAT_CPLD_INTRUSION_MASK BIT(6)
u8 action)
{
dev_info(&mlxplat_dev->dev, "System shutdown due to short press of power button");
- kernel_halt();
+ kernel_power_off();
return 0;
}
.reg = MLXPLAT_CPLD_LPC_REG_PWRB_OFFSET,
.mask = MLXPLAT_CPLD_PWR_BUTTON_MASK,
.count = ARRAY_SIZE(mlxplat_mlxcpld_l1_switch_pwr_events_items_data),
- .inversed = 0,
+ .inversed = 1,
.health = false,
},
{
.reg = MLXPLAT_CPLD_LPC_REG_BRD_OFFSET,
.mask = MLXPLAT_CPLD_L1_CHA_HEALTH_MASK,
.count = ARRAY_SIZE(mlxplat_mlxcpld_l1_switch_health_events_items_data),
- .inversed = 0,
+ .inversed = 1,
.health = false,
.ind = 8,
},
{
.label = "latch_reset",
.reg = MLXPLAT_CPLD_LPC_REG_GP1_OFFSET,
- .mask = GENMASK(7, 0) & ~BIT(5),
+ .mask = GENMASK(7, 0) & ~BIT(6),
.mode = 0200,
},
{
if (priv->pdev_mux[i])
platform_device_unregister(priv->pdev_mux[i]);
}
-
- mlxplat_post_exit();
}
static int mlxplat_i2c_main_complition_notify(void *handle, int id)
pm_power_off = NULL;
mlxplat_pre_exit(priv);
mlxplat_i2c_main_exit(priv);
+ mlxplat_post_exit();
}
module_exit(mlxplat_exit);
#include <linux/seq_file.h>
#include <linux/string.h>
-static const char *const SM_ECO_NAME = "eco";
-static const char *const SM_COMFORT_NAME = "comfort";
-static const char *const SM_SPORT_NAME = "sport";
-static const char *const SM_TURBO_NAME = "turbo";
-
-static const char *const FM_AUTO_NAME = "auto";
-static const char *const FM_SILENT_NAME = "silent";
-static const char *const FM_BASIC_NAME = "basic";
-static const char *const FM_ADVANCED_NAME = "advanced";
+#define SM_ECO_NAME "eco"
+#define SM_COMFORT_NAME "comfort"
+#define SM_SPORT_NAME "sport"
+#define SM_TURBO_NAME "turbo"
+
+#define FM_AUTO_NAME "auto"
+#define FM_SILENT_NAME "silent"
+#define FM_BASIC_NAME "basic"
+#define FM_ADVANCED_NAME "advanced"
static const char * const ALLOWED_FW_0[] __initconst = {
"14C1EMS1.012",
.bus_type = SMI_AUTO_DETECT,
};
+static const struct smi_node cs35l56_hda = {
+ .instances = {
+ { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 },
+ { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 },
+ { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 },
+ { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 },
+ /* a 5th entry is an alias address, not a real device */
+ { "cs35l56-hda_dummy_dev" },
+ {}
+ },
+ .bus_type = SMI_AUTO_DETECT,
+};
+
/*
* Note new device-ids must also be added to ignore_serial_bus_ids in
* drivers/acpi/scan.c: acpi_device_enumeration_by_parent().
{ "BSG1160", (unsigned long)&bsg1160_data },
{ "BSG2150", (unsigned long)&bsg2150_data },
{ "CSC3551", (unsigned long)&cs35l41_hda },
+ { "CSC3556", (unsigned long)&cs35l56_hda },
{ "INT3515", (unsigned long)&int3515_data },
/* Non-conforming _HID for Cirrus Logic already released */
{ "CLSA0100", (unsigned long)&cs35l41_hda },
const struct notification_limit *uv_l = &constr->under_voltage_limits;
const struct notification_limit *ov_l = &constr->over_voltage_limits;
- if (!config->init_data) /* No config in DT, pointers will be invalid */
- return 0;
-
/* make sure that only one severity is used to clarify if unchanged, enabled or disabled */
if ((!!uv_l->prot + !!uv_l->err + !!uv_l->warn) > 1) {
dev_err(config->dev, "%s: at most one voltage monitoring severity allowed!\n",
config.of_node = da9063_reg_matches[id].of_node;
config.regmap = da9063->regmap;
- ret = da9063_check_xvp_constraints(&config);
- if (ret)
- return ret;
+ /* Checking constraints requires init_data from DT. */
+ if (config.init_data) {
+ ret = da9063_check_xvp_constraints(&config);
+ if (ret)
+ return ret;
+ }
regl->rdev = devm_regulator_register(&pdev->dev, ®l->desc,
&config);
RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"),
RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo515, "vdd-l1-l4-l10"),
RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo515, "vdd-l11"),
- RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"),
+ RPMH_VREG("ldo12", "ldo%s12", &pmic5_nldo515, "vdd-l12"),
RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"),
RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"),
RPMH_VREG("ldo15", "ldo%s15", &pmic5_nldo515, "vdd-l15"),
printk("scsi%d (%d:%d) PHASE MISMATCH IN SEND MESSAGE %d remain, return %p[%04x], phase %s\n", host->host_no, pun, lun, count, (void *)temp, temp - hostdata->pScript, sbcl_to_string(NCR_700_readb(host, SBCL_REG)));
#endif
resume_offset = hostdata->pScript + Ent_SendMessagePhaseMismatch;
- } else if(dsp >= to32bit(&slot->pSG[0].ins) &&
+ } else if (slot && dsp >= to32bit(&slot->pSG[0].ins) &&
dsp <= to32bit(&slot->pSG[NCR_700_SG_SEGMENTS].ins)) {
int data_transfer = NCR_700_readl(host, DBC_REG) & 0xffffff;
int SGcount = (dsp - to32bit(&slot->pSG[0].ins))/sizeof(struct NCR_700_SG_List);
#define DRV_NAME "fnic"
#define DRV_DESCRIPTION "Cisco FCoE HBA Driver"
-#define DRV_VERSION "1.6.0.54"
+#define DRV_VERSION "1.6.0.55"
#define PFX DRV_NAME ": "
#define DFX DRV_NAME "%d: "
bool new_sc)
{
- int ret = SUCCESS;
+ int ret = 0;
struct fnic_pending_aborts_iter_data iter_data = {
.fnic = fnic,
.lun_dev = lr_sc->device,
/* walk again to check, if IOs are still pending in fw */
if (fnic_is_abts_pending(fnic, lr_sc))
- ret = FAILED;
+ ret = 1;
clean_pending_aborts_end:
+ FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
+ "%s: exit status: %d\n", __func__, ret);
return ret;
}
}
}
-#define LPFC_INVALID_REFTAG ((u32)-1)
-
/**
* lpfc_rampdown_queue_depth - Post RAMP_DOWN_QUEUE event to worker thread
* @phba: The Hba for which this call is being executed.
sgpe = scsi_prot_sglist(sc);
lba = scsi_prot_ref_tag(sc);
- if (lba == LPFC_INVALID_REFTAG)
- return 0;
/* First check if we need to match the LBA */
if (phba->lpfc_injerr_lba != LPFC_INJERR_LBA_OFF) {
/* extract some info from the scsi command for pde*/
reftag = scsi_prot_ref_tag(sc);
- if (reftag == LPFC_INVALID_REFTAG)
- goto out;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
/* extract some info from the scsi command */
blksize = scsi_prot_interval(sc);
reftag = scsi_prot_ref_tag(sc);
- if (reftag == LPFC_INVALID_REFTAG)
- goto out;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
/* extract some info from the scsi command for pde*/
reftag = scsi_prot_ref_tag(sc);
- if (reftag == LPFC_INVALID_REFTAG)
- goto out;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
/* extract some info from the scsi command */
blksize = scsi_prot_interval(sc);
reftag = scsi_prot_ref_tag(sc);
- if (reftag == LPFC_INVALID_REFTAG)
- goto out;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
src = (struct scsi_dif_tuple *)sg_virt(sgpe);
start_ref_tag = scsi_prot_ref_tag(cmd);
- if (start_ref_tag == LPFC_INVALID_REFTAG)
- goto out;
start_app_tag = src->app_tag;
len = sgpe->length;
while (src && protsegcnt) {
scsi_cmnd->sc_data_direction);
lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
- "9084 Cannot setup S/G List for HBA"
- "IO segs %d/%d SGL %d SCSI %d: %d %d\n",
+ "9084 Cannot setup S/G List for HBA "
+ "IO segs %d/%d SGL %d SCSI %d: %d %d %d\n",
lpfc_cmd->seg_cnt, lpfc_cmd->prot_seg_cnt,
phba->cfg_total_seg_cnt, phba->cfg_sg_seg_cnt,
- prot_group_type, num_sge);
+ prot_group_type, num_sge, ret);
lpfc_cmd->seg_cnt = 0;
lpfc_cmd->prot_seg_cnt = 0;
static void qedf_shutdown(struct pci_dev *pdev);
static void qedf_schedule_recovery_handler(void *dev);
static void qedf_recovery_handler(struct work_struct *work);
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state);
/*
* Driver module parameters.
.probe = qedf_probe,
.remove = qedf_remove,
.shutdown = qedf_shutdown,
+ .suspend = qedf_suspend,
};
static int __qedf_probe(struct pci_dev *pdev, int mode)
__qedf_remove(pdev, QEDF_MODE_NORMAL);
}
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedf_ctx *qedf;
+
+ if (!pdev) {
+ QEDF_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedf = pci_get_drvdata(pdev);
+
+ QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
/*
* Recovery handler code
*/
static void qedi_recovery_handler(struct work_struct *work);
static void qedi_schedule_hw_err_handler(void *dev,
enum qed_hw_err_type err_type);
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state);
static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
{
struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
struct qedi_work *work, *tmp;
struct task_struct *thread;
+ unsigned long flags;
- spin_lock_bh(&p->p_work_lock);
+ spin_lock_irqsave(&p->p_work_lock, flags);
thread = p->iothread;
p->iothread = NULL;
kfree(work);
}
- spin_unlock_bh(&p->p_work_lock);
+ spin_unlock_irqrestore(&p->p_work_lock, flags);
if (thread)
kthread_stop(thread);
return 0;
__qedi_remove(pdev, QEDI_MODE_SHUTDOWN);
}
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct qedi_ctx *qedi;
+
+ if (!pdev) {
+ QEDI_ERR(NULL, "pdev is NULL.\n");
+ return -ENODEV;
+ }
+
+ qedi = pci_get_drvdata(pdev);
+
+ QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+ return -EPERM;
+}
+
static int __qedi_probe(struct pci_dev *pdev, int mode)
{
struct qedi_ctx *qedi;
.remove = qedi_remove,
.shutdown = qedi_shutdown,
.err_handler = &qedi_err_handler,
+ .suspend = qedi_suspend,
};
static int __init qedi_init(void)
return 0;
err_out:
+ put_device(&rc->dev);
list_del(&rc->node);
rd->component_count--;
put_device(component_dev);
size_t length, loff_t *ppos)
{
int host, channel, id, lun;
- char *buffer, *p;
+ char *buffer, *end, *p;
int err;
if (!buf || length > PAGE_SIZE)
goto out;
err = -EINVAL;
- if (length < PAGE_SIZE)
- buffer[length] = '\0';
- else if (buffer[PAGE_SIZE-1])
- goto out;
+ if (length < PAGE_SIZE) {
+ end = buffer + length;
+ *end = '\0';
+ } else {
+ end = buffer + PAGE_SIZE - 1;
+ if (*end)
+ goto out;
+ }
/*
* Usage: echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi
if (!strncmp("scsi add-single-device", buffer, 22)) {
p = buffer + 23;
- host = simple_strtoul(p, &p, 0);
- channel = simple_strtoul(p + 1, &p, 0);
- id = simple_strtoul(p + 1, &p, 0);
- lun = simple_strtoul(p + 1, &p, 0);
+ host = (p < end) ? simple_strtoul(p, &p, 0) : 0;
+ channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
+ id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
+ lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
err = scsi_add_single_device(host, channel, id, lun);
} else if (!strncmp("scsi remove-single-device", buffer, 25)) {
p = buffer + 26;
- host = simple_strtoul(p, &p, 0);
- channel = simple_strtoul(p + 1, &p, 0);
- id = simple_strtoul(p + 1, &p, 0);
- lun = simple_strtoul(p + 1, &p, 0);
+ host = (p < end) ? simple_strtoul(p, &p, 0) : 0;
+ channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
+ id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
+ lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
err = scsi_remove_single_device(host, channel, id, lun);
}
"Snic Tgt: device_add, with err = %d\n",
ret);
+ put_device(&tgt->dev);
put_device(&snic->shost->shost_gendev);
spin_lock_irqsave(snic->shost->host_lock, flags);
list_del(&tgt->list);
*/
static enum scsi_timeout_action storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
{
-#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
- if (scmnd->device->host->transportt == fc_transport_template)
- return fc_eh_timed_out(scmnd);
-#endif
return SCSI_EH_RESET_TIMER;
}
pm_runtime_mark_last_busy(&tb->dev);
pm_runtime_put_autosuspend(&tb->dev);
+
+ kfree(ev);
}
static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port)
* uni-directional mode and we don't want to change it's TMU
* mode.
*/
- tb_switch_tmu_rate_write(sw, tmu_rates[TB_SWITCH_TMU_MODE_OFF]);
+ ret = tb_switch_tmu_rate_write(sw, tmu_rates[TB_SWITCH_TMU_MODE_OFF]);
+ if (ret)
+ return ret;
tb_port_tmu_time_sync_disable(up);
ret = tb_port_tmu_time_sync_disable(down);
{
struct ufs_renesas_priv *priv;
- priv = devm_kmalloc(hba->dev, sizeof(*priv), GFP_KERNEL);
+ priv = devm_kzalloc(hba->dev, sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
ufshcd_set_variant(hba, priv);
struct power_supply_desc desc;
struct power_supply *charger;
+ bool initial_detection;
};
/*
dev_dbg(info->dev, "role %s -> %s, gpios: id %d, vbus %d\n",
usb_role_string(info->last_role), usb_role_string(role), id, vbus);
- if (info->last_role == role) {
+ if (!info->initial_detection && info->last_role == role) {
dev_warn(info->dev, "repeated role: %s\n", usb_role_string(role));
return;
}
+ info->initial_detection = false;
+
if (info->last_role == USB_ROLE_HOST && info->vbus)
regulator_disable(info->vbus);
device_set_wakeup_capable(&pdev->dev, true);
/* Perform initial detection */
+ info->initial_detection = true;
usb_conn_queue_dwork(info, 0);
return 0;
u32 count;
if (pm_runtime_suspended(dwc->dev)) {
+ dwc->pending_events = true;
+ /*
+ * Trigger runtime resume. The get() function will be balanced
+ * after processing the pending events in dwc3_process_pending
+ * events().
+ */
pm_runtime_get(dwc->dev);
disable_irq_nosync(dwc->irq_gadget);
- dwc->pending_events = true;
return IRQ_HANDLED;
}
{
if (dwc->pending_events) {
dwc3_interrupt(dwc->irq_gadget, dwc->ev_buf);
+ dwc3_thread_interrupt(dwc->irq_gadget, dwc->ev_buf);
+ pm_runtime_put(dwc->dev);
dwc->pending_events = false;
enable_irq(dwc->irq_gadget);
}
* usb_gadget_activate() is called. For example, user mode components may
* need to be activated before the system can talk to hosts.
*
+ * This routine may sleep; it must not be called in interrupt context
+ * (such as from within a gadget driver's disconnect() callback).
+ *
* Returns zero on success, else negative errno.
*/
int usb_gadget_deactivate(struct usb_gadget *gadget)
* This routine activates gadget which was previously deactivated with
* usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed.
*
+ * This routine may sleep; it must not be called in interrupt context.
+ *
* Returns zero on success, else negative errno.
*/
int usb_gadget_activate(struct usb_gadget *gadget)
usb_gadget_disable_async_callbacks(udc);
if (gadget->irq)
synchronize_irq(gadget->irq);
+ mutex_unlock(&udc->connect_lock);
+
udc->driver->unbind(gadget);
+
+ mutex_lock(&udc->connect_lock);
usb_gadget_udc_stop_locked(udc);
mutex_unlock(&udc->connect_lock);
rc = usb_stor_ctrl_transfer(us, us->recv_ctrl_pipe,
command, 0xc0, 0, 1, data, 2);
- usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]);
+ if (rc == USB_STOR_XFER_GOOD)
+ usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]);
return rc;
}
static int alauda_check_media(struct us_data *us)
{
struct alauda_info *info = (struct alauda_info *) us->extra;
- unsigned char status[2];
+ unsigned char *status = us->iobuf;
+ int rc;
- alauda_get_media_status(us, status);
+ rc = alauda_get_media_status(us, status);
+ if (rc != USB_STOR_XFER_GOOD) {
+ status[0] = 0xF0; /* Pretend there's no media */
+ status[1] = 0;
+ }
/* Check for no media or door open */
if ((status[0] & 0x80) || ((status[0] & 0x1F) == 0x10)
enum dp_state state;
bool hpd;
+ bool pending_hpd;
struct mutex lock; /* device lock */
struct work_struct work;
dp->state = DP_STATE_EXIT;
} else if (!(con & DP_CONF_CURRENTLY(dp->data.conf))) {
ret = dp_altmode_configure(dp, con);
- if (!ret)
+ if (!ret) {
dp->state = DP_STATE_CONFIGURE;
+ if (dp->hpd != hpd) {
+ dp->hpd = hpd;
+ dp->pending_hpd = true;
+ }
+ }
} else {
if (dp->hpd != hpd) {
drm_connector_oob_hotplug_event(dp->connector_fwnode);
{
sysfs_notify(&dp->alt->dev.kobj, "displayport", "configuration");
sysfs_notify(&dp->alt->dev.kobj, "displayport", "pin_assignment");
+ /*
+ * If the DFP_D/UFP_D sends a change in HPD when first notifying the
+ * DisplayPort driver that it is connected, then we wait until
+ * configuration is complete to signal HPD.
+ */
+ if (dp->pending_hpd) {
+ drm_connector_oob_hotplug_event(dp->connector_fwnode);
+ sysfs_notify(&dp->alt->dev.kobj, "displayport", "hpd");
+ dp->pending_hpd = false;
+ }
return dp_altmode_notify(dp);
}
tristate "Intel PMC mux control"
depends on ACPI
depends on INTEL_SCU_IPC
+ select USB_COMMON
select USB_ROLE_SWITCH
help
Driver for USB muxes controlled by Intel PMC FW. Intel PMC FW can
ret = nb7vpq904m_register_bridge(nb7);
if (ret)
- return ret;
+ goto err_disable_gpio;
sw_desc.drvdata = nb7;
sw_desc.fwnode = dev->fwnode;
sw_desc.set = nb7vpq904m_sw_set;
nb7->sw = typec_switch_register(dev, &sw_desc);
- if (IS_ERR(nb7->sw))
- return dev_err_probe(dev, PTR_ERR(nb7->sw),
- "Error registering typec switch\n");
+ if (IS_ERR(nb7->sw)) {
+ ret = dev_err_probe(dev, PTR_ERR(nb7->sw),
+ "Error registering typec switch\n");
+ goto err_disable_gpio;
+ }
retimer_desc.drvdata = nb7;
retimer_desc.fwnode = dev->fwnode;
nb7->retimer = typec_retimer_register(dev, &retimer_desc);
if (IS_ERR(nb7->retimer)) {
- typec_switch_unregister(nb7->sw);
- return dev_err_probe(dev, PTR_ERR(nb7->retimer),
- "Error registering typec retimer\n");
+ ret = dev_err_probe(dev, PTR_ERR(nb7->retimer),
+ "Error registering typec retimer\n");
+ goto err_switch_unregister;
}
return 0;
+
+err_switch_unregister:
+ typec_switch_unregister(nb7->sw);
+
+err_disable_gpio:
+ gpiod_set_value(nb7->enable_gpio, 0);
+ regulator_disable(nb7->vcc_supply);
+
+ return ret;
}
static void nb7vpq904m_remove(struct i2c_client *client)
/* Do nothing, vbus drop expected */
break;
+ case SNK_HARD_RESET_WAIT_VBUS:
+ /* Do nothing, its OK to receive vbus off events */
+ break;
+
default:
if (port->pwr_role == TYPEC_SINK && port->attached)
tcpm_set_state(port, SNK_UNATTACHED, tcpm_wait_for_discharge(port));
case SNK_DEBOUNCED:
/*Do nothing, still waiting for VSAFE5V for connect */
break;
+ case SNK_HARD_RESET_WAIT_VBUS:
+ /* Do nothing, its OK to receive vbus off events */
+ break;
default:
if (port->pwr_role == TYPEC_SINK && port->auto_vbus_discharge_enabled)
tcpm_set_state(port, SNK_UNATTACHED, 0);
struct list_head head;
unsigned long num_directs;
unsigned long num_klms;
+ /* state of dvq mr */
bool initialized;
/* serialize mkey creation and destruction */
int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
unsigned int asid);
void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
+void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
#define mlx5_vdpa_warn(__dev, format, ...) \
dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \
}
}
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
+static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+ if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
+ return;
+
+ prune_iotlb(mvdev);
+}
+
+static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
- mutex_lock(&mr->mkey_mtx);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
+ return;
+
if (!mr->initialized)
- goto out;
+ return;
- prune_iotlb(mvdev);
if (mr->user_mr)
destroy_user_mr(mvdev, mr);
else
destroy_dma_mr(mvdev, mr);
mr->initialized = false;
-out:
+}
+
+void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+
+ mutex_lock(&mr->mkey_mtx);
+
+ _mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
+ _mlx5_vdpa_destroy_cvq_mr(mvdev, asid);
+
mutex_unlock(&mr->mkey_mtx);
}
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
- struct vhost_iotlb *iotlb, unsigned int asid)
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
+{
+ mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_CVQ_GROUP]);
+ mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]);
+}
+
+static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb,
+ unsigned int asid)
+{
+ if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
+ return 0;
+
+ return dup_iotlb(mvdev, iotlb);
+}
+
+static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err;
- if (mr->initialized)
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
return 0;
- if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
- if (iotlb)
- err = create_user_mr(mvdev, iotlb);
- else
- err = create_dma_mr(mvdev, mr);
+ if (mr->initialized)
+ return 0;
- if (err)
- return err;
- }
+ if (iotlb)
+ err = create_user_mr(mvdev, iotlb);
+ else
+ err = create_dma_mr(mvdev, mr);
- if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
- err = dup_iotlb(mvdev, iotlb);
- if (err)
- goto out_err;
- }
+ if (err)
+ return err;
mr->initialized = true;
+
+ return 0;
+}
+
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
+{
+ int err;
+
+ err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid);
+ if (err)
+ return err;
+
+ err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid);
+ if (err)
+ goto out_err;
+
return 0;
out_err:
- if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
- if (iotlb)
- destroy_user_mr(mvdev, mr);
- else
- destroy_dma_mr(mvdev, mr);
- }
+ _mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
return err;
}
else
ndev->rqt_size = 1;
- ndev->cur_num_vqs = 2 * ndev->rqt_size;
+ /* Device must start with 1 queue pair, as per VIRTIO v1.2 spec, section
+ * 5.1.6.5.5 "Device operation in multiqueue mode":
+ *
+ * Multiqueue is disabled by default.
+ * The driver enables multiqueue by sending a command using class
+ * VIRTIO_NET_CTRL_MQ. The command selects the mode of multiqueue
+ * operation, as follows: ...
+ */
+ ndev->cur_num_vqs = 2;
update_cvq_info(mvdev);
return err;
goto err_mr;
teardown_driver(ndev);
- mlx5_vdpa_destroy_mr(mvdev);
+ mlx5_vdpa_destroy_mr_asid(mvdev, asid);
err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
if (err)
goto err_mr;
return 0;
err_setup:
- mlx5_vdpa_destroy_mr(mvdev);
+ mlx5_vdpa_destroy_mr_asid(mvdev, asid);
err_mr:
return err;
}
kfree(mgtdev);
}
-static void mlx5v_shutdown(struct auxiliary_device *auxdev)
-{
- struct mlx5_vdpa_mgmtdev *mgtdev;
- struct mlx5_vdpa_net *ndev;
-
- mgtdev = auxiliary_get_drvdata(auxdev);
- ndev = mgtdev->ndev;
-
- free_irqs(ndev);
-}
-
static const struct auxiliary_device_id mlx5v_id_table[] = {
{ .name = MLX5_ADEV_NAME ".vnet", },
{},
.name = "vnet",
.probe = mlx5v_probe,
.remove = mlx5v_remove,
- .shutdown = mlx5v_shutdown,
.id_table = mlx5v_id_table,
};
pds_vdpa-y := aux_drv.o \
cmds.o \
+ debugfs.o \
vdpa_dev.o
-
-pds_vdpa-$(CONFIG_DEBUG_FS) += debugfs.o
{
struct pds_vdpa_aux *vdpa_aux = seq->private;
struct vdpa_mgmt_dev *mgmt;
+ u64 hw_features;
seq_printf(seq, "aux_dev: %s\n",
dev_name(&vdpa_aux->padev->aux_dev.dev));
mgmt = &vdpa_aux->vdpa_mdev;
seq_printf(seq, "max_vqs: %d\n", mgmt->max_supported_vqs);
seq_printf(seq, "config_attr_mask: %#llx\n", mgmt->config_attr_mask);
- seq_printf(seq, "supported_features: %#llx\n", mgmt->supported_features);
- print_feature_bits_all(seq, mgmt->supported_features);
+ hw_features = le64_to_cpu(vdpa_aux->ident.hw_features);
+ seq_printf(seq, "hw_features: %#llx\n", hw_features);
+ print_feature_bits_all(seq, hw_features);
return 0;
}
{
struct pds_vdpa_device *pdsv = seq->private;
struct virtio_net_config vc;
- u64 driver_features;
u8 status;
memcpy_fromio(&vc, pdsv->vdpa_aux->vd_mdev.device,
status = vp_modern_get_status(&pdsv->vdpa_aux->vd_mdev);
seq_printf(seq, "dev_status: %#x\n", status);
print_status_bits(seq, status);
-
- seq_printf(seq, "req_features: %#llx\n", pdsv->req_features);
- print_feature_bits_all(seq, pdsv->req_features);
- driver_features = vp_modern_get_driver_features(&pdsv->vdpa_aux->vd_mdev);
- seq_printf(seq, "driver_features: %#llx\n", driver_features);
- print_feature_bits_all(seq, driver_features);
+ seq_printf(seq, "negotiated_features: %#llx\n", pdsv->negotiated_features);
+ print_feature_bits_all(seq, pdsv->negotiated_features);
seq_printf(seq, "vdpa_index: %d\n", pdsv->vdpa_index);
seq_printf(seq, "num_vqs: %d\n", pdsv->num_vqs);
static void pds_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, u16 qid, bool ready)
{
struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
- struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
struct device *dev = &pdsv->vdpa_dev.dev;
u64 driver_features;
u16 invert_idx = 0;
- int irq;
int err;
dev_dbg(dev, "%s: qid %d ready %d => %d\n",
invert_idx = PDS_VDPA_PACKED_INVERT_IDX;
if (ready) {
- irq = pci_irq_vector(pdev, qid);
- snprintf(pdsv->vqs[qid].irq_name, sizeof(pdsv->vqs[qid].irq_name),
- "vdpa-%s-%d", dev_name(dev), qid);
-
- err = request_irq(irq, pds_vdpa_isr, 0,
- pdsv->vqs[qid].irq_name, &pdsv->vqs[qid]);
- if (err) {
- dev_err(dev, "%s: no irq for qid %d: %pe\n",
- __func__, qid, ERR_PTR(err));
- return;
- }
- pdsv->vqs[qid].irq = irq;
-
/* Pass vq setup info to DSC using adminq to gather up and
* send all info at once so FW can do its full set up in
* one easy operation
if (err) {
dev_err(dev, "Failed to init vq %d: %pe\n",
qid, ERR_PTR(err));
- pds_vdpa_release_irq(pdsv, qid);
ready = false;
}
} else {
if (err)
dev_err(dev, "%s: reset_vq failed qid %d: %pe\n",
__func__, qid, ERR_PTR(err));
- pds_vdpa_release_irq(pdsv, qid);
}
pdsv->vqs[qid].ready = ready;
struct device *dev = &pdsv->vdpa_dev.dev;
u64 driver_features;
u64 nego_features;
+ u64 hw_features;
u64 missing;
if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM)) && features) {
return -EOPNOTSUPP;
}
- pdsv->req_features = features;
-
/* Check for valid feature bits */
- nego_features = features & le64_to_cpu(pdsv->vdpa_aux->ident.hw_features);
- missing = pdsv->req_features & ~nego_features;
+ nego_features = features & pdsv->supported_features;
+ missing = features & ~nego_features;
if (missing) {
dev_err(dev, "Can't support all requested features in %#llx, missing %#llx features\n",
- pdsv->req_features, missing);
+ features, missing);
return -EOPNOTSUPP;
}
+ pdsv->negotiated_features = nego_features;
+
driver_features = pds_vdpa_get_driver_features(vdpa_dev);
dev_dbg(dev, "%s: %#llx => %#llx\n",
__func__, driver_features, nego_features);
+ /* if we're faking the F_MAC, strip it before writing to device */
+ hw_features = le64_to_cpu(pdsv->vdpa_aux->ident.hw_features);
+ if (!(hw_features & BIT_ULL(VIRTIO_NET_F_MAC)))
+ nego_features &= ~BIT_ULL(VIRTIO_NET_F_MAC);
+
if (driver_features == nego_features)
return 0;
{
struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
- return vp_modern_get_driver_features(&pdsv->vdpa_aux->vd_mdev);
+ return pdsv->negotiated_features;
}
static void pds_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
return vp_modern_get_status(&pdsv->vdpa_aux->vd_mdev);
}
+static int pds_vdpa_request_irqs(struct pds_vdpa_device *pdsv)
+{
+ struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
+ struct pds_vdpa_aux *vdpa_aux = pdsv->vdpa_aux;
+ struct device *dev = &pdsv->vdpa_dev.dev;
+ int max_vq, nintrs, qid, err;
+
+ max_vq = vdpa_aux->vdpa_mdev.max_supported_vqs;
+
+ nintrs = pci_alloc_irq_vectors(pdev, max_vq, max_vq, PCI_IRQ_MSIX);
+ if (nintrs < 0) {
+ dev_err(dev, "Couldn't get %d msix vectors: %pe\n",
+ max_vq, ERR_PTR(nintrs));
+ return nintrs;
+ }
+
+ for (qid = 0; qid < pdsv->num_vqs; ++qid) {
+ int irq = pci_irq_vector(pdev, qid);
+
+ snprintf(pdsv->vqs[qid].irq_name, sizeof(pdsv->vqs[qid].irq_name),
+ "vdpa-%s-%d", dev_name(dev), qid);
+
+ err = request_irq(irq, pds_vdpa_isr, 0,
+ pdsv->vqs[qid].irq_name,
+ &pdsv->vqs[qid]);
+ if (err) {
+ dev_err(dev, "%s: no irq for qid %d: %pe\n",
+ __func__, qid, ERR_PTR(err));
+ goto err_release;
+ }
+
+ pdsv->vqs[qid].irq = irq;
+ }
+
+ vdpa_aux->nintrs = nintrs;
+
+ return 0;
+
+err_release:
+ while (qid--)
+ pds_vdpa_release_irq(pdsv, qid);
+
+ pci_free_irq_vectors(pdev);
+
+ vdpa_aux->nintrs = 0;
+
+ return err;
+}
+
+static void pds_vdpa_release_irqs(struct pds_vdpa_device *pdsv)
+{
+ struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
+ struct pds_vdpa_aux *vdpa_aux = pdsv->vdpa_aux;
+ int qid;
+
+ if (!vdpa_aux->nintrs)
+ return;
+
+ for (qid = 0; qid < pdsv->num_vqs; qid++)
+ pds_vdpa_release_irq(pdsv, qid);
+
+ pci_free_irq_vectors(pdev);
+
+ vdpa_aux->nintrs = 0;
+}
+
static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
{
struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
old_status = pds_vdpa_get_status(vdpa_dev);
dev_dbg(dev, "%s: old %#x new %#x\n", __func__, old_status, status);
+ if (status & ~old_status & VIRTIO_CONFIG_S_DRIVER_OK) {
+ if (pds_vdpa_request_irqs(pdsv))
+ status = old_status | VIRTIO_CONFIG_S_FAILED;
+ }
+
pds_vdpa_cmd_set_status(pdsv, status);
/* Note: still working with FW on the need for this reset cmd */
pdsv->vqs[i].avail_idx = 0;
pdsv->vqs[i].used_idx = 0;
}
+
+ pds_vdpa_cmd_set_mac(pdsv, pdsv->mac);
}
if (status & ~old_status & VIRTIO_CONFIG_S_FEATURES_OK) {
i, &pdsv->vqs[i].notify_pa);
}
}
+
+ if (old_status & ~status & VIRTIO_CONFIG_S_DRIVER_OK)
+ pds_vdpa_release_irqs(pdsv);
+}
+
+static void pds_vdpa_init_vqs_entry(struct pds_vdpa_device *pdsv, int qid,
+ void __iomem *notify)
+{
+ memset(&pdsv->vqs[qid], 0, sizeof(pdsv->vqs[0]));
+ pdsv->vqs[qid].qid = qid;
+ pdsv->vqs[qid].pdsv = pdsv;
+ pdsv->vqs[qid].ready = false;
+ pdsv->vqs[qid].irq = VIRTIO_MSI_NO_VECTOR;
+ pdsv->vqs[qid].notify = notify;
}
static int pds_vdpa_reset(struct vdpa_device *vdpa_dev)
if (err)
dev_err(dev, "%s: reset_vq failed qid %d: %pe\n",
__func__, i, ERR_PTR(err));
- pds_vdpa_release_irq(pdsv, i);
- memset(&pdsv->vqs[i], 0, sizeof(pdsv->vqs[0]));
- pdsv->vqs[i].ready = false;
}
}
pds_vdpa_set_status(vdpa_dev, 0);
+ if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
+ /* Reset the vq info */
+ for (i = 0; i < pdsv->num_vqs && !err; i++)
+ pds_vdpa_init_vqs_entry(pdsv, i, pdsv->vqs[i].notify);
+ }
+
return 0;
}
struct device *dma_dev;
struct pci_dev *pdev;
struct device *dev;
- u8 mac[ETH_ALEN];
int err;
int i;
if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
u64 unsupp_features =
- add_config->device_features & ~mgmt->supported_features;
+ add_config->device_features & ~pdsv->supported_features;
if (unsupp_features) {
dev_err(dev, "Unsupported features: %#llx\n", unsupp_features);
}
/* Set a mac, either from the user config if provided
- * or set a random mac if default is 00:..:00
+ * or use the device's mac if not 00:..:00
+ * or set a random mac
*/
if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR)) {
- ether_addr_copy(mac, add_config->net.mac);
- pds_vdpa_cmd_set_mac(pdsv, mac);
+ ether_addr_copy(pdsv->mac, add_config->net.mac);
} else {
struct virtio_net_config __iomem *vc;
vc = pdsv->vdpa_aux->vd_mdev.device;
- memcpy_fromio(mac, vc->mac, sizeof(mac));
- if (is_zero_ether_addr(mac)) {
- eth_random_addr(mac);
- dev_info(dev, "setting random mac %pM\n", mac);
- pds_vdpa_cmd_set_mac(pdsv, mac);
+ memcpy_fromio(pdsv->mac, vc->mac, sizeof(pdsv->mac));
+ if (is_zero_ether_addr(pdsv->mac) &&
+ (pdsv->supported_features & BIT_ULL(VIRTIO_NET_F_MAC))) {
+ eth_random_addr(pdsv->mac);
+ dev_info(dev, "setting random mac %pM\n", pdsv->mac);
}
}
+ pds_vdpa_cmd_set_mac(pdsv, pdsv->mac);
for (i = 0; i < pdsv->num_vqs; i++) {
- pdsv->vqs[i].qid = i;
- pdsv->vqs[i].pdsv = pdsv;
- pdsv->vqs[i].irq = VIRTIO_MSI_NO_VECTOR;
- pdsv->vqs[i].notify = vp_modern_map_vq_notify(&pdsv->vdpa_aux->vd_mdev,
- i, &pdsv->vqs[i].notify_pa);
+ void __iomem *notify;
+
+ notify = vp_modern_map_vq_notify(&pdsv->vdpa_aux->vd_mdev,
+ i, &pdsv->vqs[i].notify_pa);
+ pds_vdpa_init_vqs_entry(pdsv, i, notify);
}
pdsv->vdpa_dev.mdev = &vdpa_aux->vdpa_mdev;
max_vqs = min_t(u16, dev_intrs, max_vqs);
mgmt->max_supported_vqs = min_t(u16, PDS_VDPA_MAX_QUEUES, max_vqs);
- vdpa_aux->nintrs = mgmt->max_supported_vqs;
+ vdpa_aux->nintrs = 0;
mgmt->ops = &pds_vdpa_mgmt_dev_ops;
mgmt->id_table = pds_vdpa_id_table;
mgmt->device = dev;
mgmt->supported_features = le64_to_cpu(vdpa_aux->ident.hw_features);
+
+ /* advertise F_MAC even if the device doesn't */
+ mgmt->supported_features |= BIT_ULL(VIRTIO_NET_F_MAC);
+
mgmt->config_attr_mask = BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR);
mgmt->config_attr_mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
mgmt->config_attr_mask |= BIT_ULL(VDPA_ATTR_DEV_FEATURES);
- err = pci_alloc_irq_vectors(pdev, vdpa_aux->nintrs, vdpa_aux->nintrs,
- PCI_IRQ_MSIX);
- if (err < 0) {
- dev_err(dev, "Couldn't get %d msix vectors: %pe\n",
- vdpa_aux->nintrs, ERR_PTR(err));
- return err;
- }
- vdpa_aux->nintrs = err;
-
return 0;
}
struct pds_vdpa_aux *vdpa_aux;
struct pds_vdpa_vq_info vqs[PDS_VDPA_MAX_QUEUES];
- u64 supported_features; /* specified device features */
- u64 req_features; /* features requested by vdpa */
+ u64 supported_features; /* supported device features */
+ u64 negotiated_features; /* negotiated features */
u8 vdpa_index; /* rsvd for future subdevice use */
u8 num_vqs; /* num vqs in use */
+ u8 mac[ETH_ALEN]; /* mac selected when the device was added */
struct vdpa_callback config_cb;
struct notifier_block nb;
};
[VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING },
[VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING },
[VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR,
+ [VDPA_ATTR_DEV_NET_CFG_MAX_VQP] = { .type = NLA_U16 },
/* virtio spec 1.1 section 5.1.4.1 for valid MTU range */
[VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68),
+ [VDPA_ATTR_DEV_QUEUE_INDEX] = { .type = NLA_U32 },
+ [VDPA_ATTR_DEV_FEATURES] = { .type = NLA_U64 },
};
static const struct genl_ops vdpa_nl_ops[] = {
{
.cmd = VDPA_CMD_MGMTDEV_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_mgmtdev_get_doit,
.dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit,
},
{
.cmd = VDPA_CMD_DEV_NEW,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_dev_add_set_doit,
.flags = GENL_ADMIN_PERM,
},
{
.cmd = VDPA_CMD_DEV_DEL,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_dev_del_set_doit,
.flags = GENL_ADMIN_PERM,
},
{
.cmd = VDPA_CMD_DEV_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_dev_get_doit,
.dumpit = vdpa_nl_cmd_dev_get_dumpit,
},
{
.cmd = VDPA_CMD_DEV_CONFIG_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_dev_config_get_doit,
.dumpit = vdpa_nl_cmd_dev_config_get_dumpit,
},
{
.cmd = VDPA_CMD_DEV_VSTATS_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = vdpa_nl_cmd_dev_stats_get_doit,
.flags = GENL_ADMIN_PERM,
},
{
struct vduse_dev *dev = container_of(work, struct vduse_dev, inject);
- spin_lock_irq(&dev->irq_lock);
+ spin_lock_bh(&dev->irq_lock);
if (dev->config_cb.callback)
dev->config_cb.callback(dev->config_cb.private);
- spin_unlock_irq(&dev->irq_lock);
+ spin_unlock_bh(&dev->irq_lock);
}
static void vduse_vq_irq_inject(struct work_struct *work)
struct vduse_virtqueue *vq = container_of(work,
struct vduse_virtqueue, inject);
- spin_lock_irq(&vq->irq_lock);
+ spin_lock_bh(&vq->irq_lock);
if (vq->ready && vq->cb.callback)
vq->cb.callback(vq->cb.private);
- spin_unlock_irq(&vq->irq_lock);
+ spin_unlock_bh(&vq->irq_lock);
}
static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq)
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/miscdevice.h>
+#include <linux/blk_types.h>
+#include <linux/bio.h>
#include <asm/unaligned.h>
#include <scsi/scsi_common.h>
#include <scsi/scsi_proto.h>
u32 tvc_prot_sgl_count;
/* Saved unpacked SCSI LUN for vhost_scsi_target_queue_cmd() */
u32 tvc_lun;
+ u32 copied_iov:1;
+ const void *saved_iter_addr;
+ struct iov_iter saved_iter;
/* Pointer to the SGL formatted memory from virtio-scsi */
struct scatterlist *tvc_sgl;
struct scatterlist *tvc_prot_sgl;
int i;
if (tv_cmd->tvc_sgl_count) {
- for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
- put_page(sg_page(&tv_cmd->tvc_sgl[i]));
+ for (i = 0; i < tv_cmd->tvc_sgl_count; i++) {
+ if (tv_cmd->copied_iov)
+ __free_page(sg_page(&tv_cmd->tvc_sgl[i]));
+ else
+ put_page(sg_page(&tv_cmd->tvc_sgl[i]));
+ }
+ kfree(tv_cmd->saved_iter_addr);
}
if (tv_cmd->tvc_prot_sgl_count) {
for (i = 0; i < tv_cmd->tvc_prot_sgl_count; i++)
mutex_unlock(&vq->mutex);
}
+static int vhost_scsi_copy_sgl_to_iov(struct vhost_scsi_cmd *cmd)
+{
+ struct iov_iter *iter = &cmd->saved_iter;
+ struct scatterlist *sg = cmd->tvc_sgl;
+ struct page *page;
+ size_t len;
+ int i;
+
+ for (i = 0; i < cmd->tvc_sgl_count; i++) {
+ page = sg_page(&sg[i]);
+ len = sg[i].length;
+
+ if (copy_page_to_iter(page, 0, len, iter) != len) {
+ pr_err("Could not copy data while handling misaligned cmd. Error %zu\n",
+ len);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
/* Fill in status and signal that we are done processing this command
*
* This is scheduled in the vhost work queue so we are called with the owner
pr_debug("%s tv_cmd %p resid %u status %#02x\n", __func__,
cmd, se_cmd->residual_count, se_cmd->scsi_status);
-
memset(&v_rsp, 0, sizeof(v_rsp));
- v_rsp.resid = cpu_to_vhost32(cmd->tvc_vq, se_cmd->residual_count);
- /* TODO is status_qualifier field needed? */
- v_rsp.status = se_cmd->scsi_status;
- v_rsp.sense_len = cpu_to_vhost32(cmd->tvc_vq,
- se_cmd->scsi_sense_length);
- memcpy(v_rsp.sense, cmd->tvc_sense_buf,
- se_cmd->scsi_sense_length);
+
+ if (cmd->saved_iter_addr && vhost_scsi_copy_sgl_to_iov(cmd)) {
+ v_rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
+ } else {
+ v_rsp.resid = cpu_to_vhost32(cmd->tvc_vq,
+ se_cmd->residual_count);
+ /* TODO is status_qualifier field needed? */
+ v_rsp.status = se_cmd->scsi_status;
+ v_rsp.sense_len = cpu_to_vhost32(cmd->tvc_vq,
+ se_cmd->scsi_sense_length);
+ memcpy(v_rsp.sense, cmd->tvc_sense_buf,
+ se_cmd->scsi_sense_length);
+ }
iov_iter_init(&iov_iter, ITER_DEST, cmd->tvc_resp_iov,
cmd->tvc_in_iovs, sizeof(v_rsp));
vhost_scsi_map_to_sgl(struct vhost_scsi_cmd *cmd,
struct iov_iter *iter,
struct scatterlist *sgl,
- bool write)
+ bool is_prot)
{
struct page **pages = cmd->tvc_upages;
struct scatterlist *sg = sgl;
- ssize_t bytes;
- size_t offset;
+ ssize_t bytes, mapped_bytes;
+ size_t offset, mapped_offset;
unsigned int npages = 0;
bytes = iov_iter_get_pages2(iter, pages, LONG_MAX,
if (bytes <= 0)
return bytes < 0 ? bytes : -EFAULT;
+ mapped_bytes = bytes;
+ mapped_offset = offset;
+
while (bytes) {
unsigned n = min_t(unsigned, PAGE_SIZE - offset, bytes);
+ /*
+ * The block layer requires bios/requests to be a multiple of
+ * 512 bytes, but Windows can send us vecs that are misaligned.
+ * This can result in bios and later requests with misaligned
+ * sizes if we have to break up a cmd/scatterlist into multiple
+ * bios.
+ *
+ * We currently only break up a command into multiple bios if
+ * we hit the vec/seg limit, so check if our sgl_count is
+ * greater than the max and if a vec in the cmd has a
+ * misaligned offset/size.
+ */
+ if (!is_prot &&
+ (offset & (SECTOR_SIZE - 1) || n & (SECTOR_SIZE - 1)) &&
+ cmd->tvc_sgl_count > BIO_MAX_VECS) {
+ WARN_ONCE(true,
+ "vhost-scsi detected misaligned IO. Performance may be degraded.");
+ goto revert_iter_get_pages;
+ }
+
sg_set_page(sg++, pages[npages++], n, offset);
bytes -= n;
offset = 0;
}
+
return npages;
+
+revert_iter_get_pages:
+ iov_iter_revert(iter, mapped_bytes);
+
+ npages = 0;
+ while (mapped_bytes) {
+ unsigned int n = min_t(unsigned int, PAGE_SIZE - mapped_offset,
+ mapped_bytes);
+
+ put_page(pages[npages++]);
+
+ mapped_bytes -= n;
+ mapped_offset = 0;
+ }
+
+ return -EINVAL;
}
static int
}
static int
-vhost_scsi_iov_to_sgl(struct vhost_scsi_cmd *cmd, bool write,
- struct iov_iter *iter,
- struct scatterlist *sg, int sg_count)
+vhost_scsi_copy_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
+ struct scatterlist *sg, int sg_count)
+{
+ size_t len = iov_iter_count(iter);
+ unsigned int nbytes = 0;
+ struct page *page;
+ int i;
+
+ if (cmd->tvc_data_direction == DMA_FROM_DEVICE) {
+ cmd->saved_iter_addr = dup_iter(&cmd->saved_iter, iter,
+ GFP_KERNEL);
+ if (!cmd->saved_iter_addr)
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < sg_count; i++) {
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ i--;
+ goto err;
+ }
+
+ nbytes = min_t(unsigned int, PAGE_SIZE, len);
+ sg_set_page(&sg[i], page, nbytes, 0);
+
+ if (cmd->tvc_data_direction == DMA_TO_DEVICE &&
+ copy_page_from_iter(page, 0, nbytes, iter) != nbytes)
+ goto err;
+
+ len -= nbytes;
+ }
+
+ cmd->copied_iov = 1;
+ return 0;
+
+err:
+ pr_err("Could not read %u bytes while handling misaligned cmd\n",
+ nbytes);
+
+ for (; i >= 0; i--)
+ __free_page(sg_page(&sg[i]));
+ kfree(cmd->saved_iter_addr);
+ return -ENOMEM;
+}
+
+static int
+vhost_scsi_map_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
+ struct scatterlist *sg, int sg_count, bool is_prot)
{
struct scatterlist *p = sg;
+ size_t revert_bytes;
int ret;
while (iov_iter_count(iter)) {
- ret = vhost_scsi_map_to_sgl(cmd, iter, sg, write);
+ ret = vhost_scsi_map_to_sgl(cmd, iter, sg, is_prot);
if (ret < 0) {
+ revert_bytes = 0;
+
while (p < sg) {
- struct page *page = sg_page(p++);
- if (page)
+ struct page *page = sg_page(p);
+
+ if (page) {
put_page(page);
+ revert_bytes += p->length;
+ }
+ p++;
}
+
+ iov_iter_revert(iter, revert_bytes);
return ret;
}
sg += ret;
}
+
return 0;
}
size_t data_bytes, struct iov_iter *data_iter)
{
int sgl_count, ret;
- bool write = (cmd->tvc_data_direction == DMA_FROM_DEVICE);
if (prot_bytes) {
sgl_count = vhost_scsi_calc_sgls(prot_iter, prot_bytes,
pr_debug("%s prot_sg %p prot_sgl_count %u\n", __func__,
cmd->tvc_prot_sgl, cmd->tvc_prot_sgl_count);
- ret = vhost_scsi_iov_to_sgl(cmd, write, prot_iter,
- cmd->tvc_prot_sgl,
- cmd->tvc_prot_sgl_count);
+ ret = vhost_scsi_map_iov_to_sgl(cmd, prot_iter,
+ cmd->tvc_prot_sgl,
+ cmd->tvc_prot_sgl_count, true);
if (ret < 0) {
cmd->tvc_prot_sgl_count = 0;
return ret;
pr_debug("%s data_sg %p data_sgl_count %u\n", __func__,
cmd->tvc_sgl, cmd->tvc_sgl_count);
- ret = vhost_scsi_iov_to_sgl(cmd, write, data_iter,
- cmd->tvc_sgl, cmd->tvc_sgl_count);
+ ret = vhost_scsi_map_iov_to_sgl(cmd, data_iter, cmd->tvc_sgl,
+ cmd->tvc_sgl_count, false);
+ if (ret == -EINVAL) {
+ sg_init_table(cmd->tvc_sgl, cmd->tvc_sgl_count);
+ ret = vhost_scsi_copy_iov_to_sgl(cmd, data_iter, cmd->tvc_sgl,
+ cmd->tvc_sgl_count);
+ }
+
if (ret < 0) {
cmd->tvc_sgl_count = 0;
return ret;
MODULE_PARM_DESC(bbm_block_size,
"Big Block size in bytes. Default is 0 (auto-detection).");
-static bool bbm_safe_unplug = true;
-module_param(bbm_safe_unplug, bool, 0444);
-MODULE_PARM_DESC(bbm_safe_unplug,
- "Use a safe unplug mechanism in BBM, avoiding long/endless loops");
-
/*
* virtio-mem currently supports the following modes of operation:
*
/* The number of subblocks per Linux memory block. */
uint32_t sbs_per_mb;
+ /*
+ * Some of the Linux memory blocks tracked as "partially
+ * plugged" are completely unplugged and can be offlined
+ * and removed -- which previously failed.
+ */
+ bool have_unplugged_mb;
+
/* Summary of all memory block states. */
unsigned long mb_count[VIRTIO_MEM_SBM_MB_COUNT];
* immediately instead of waiting.
*/
virtio_mem_retry(vm);
- } else {
- dev_dbg(&vm->vdev->dev,
- "offlining and removing memory failed: %d\n", rc);
+ return 0;
}
- return rc;
+ dev_dbg(&vm->vdev->dev, "offlining and removing memory failed: %d\n", rc);
+ /*
+ * We don't really expect this to fail, because we fake-offlined all
+ * memory already. But it could fail in corner cases.
+ */
+ WARN_ON_ONCE(rc != -ENOMEM && rc != -EBUSY);
+ return rc == -ENOMEM ? -ENOMEM : -EBUSY;
}
/*
}
/*
+ * Try (offlining and) removing memory from Linux in case all subblocks are
+ * unplugged. Can be called on online and offline memory blocks.
+ *
+ * May modify the state of memory blocks in virtio-mem.
+ */
+static int virtio_mem_sbm_try_remove_unplugged_mb(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ int rc;
+
+ /*
+ * Once all subblocks of a memory block were unplugged, offline and
+ * remove it.
+ */
+ if (!virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb))
+ return 0;
+
+ /* offline_and_remove_memory() works for online and offline memory. */
+ mutex_unlock(&vm->hotplug_mutex);
+ rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
+ mutex_lock(&vm->hotplug_mutex);
+ if (!rc)
+ virtio_mem_sbm_set_mb_state(vm, mb_id,
+ VIRTIO_MEM_SBM_MB_UNUSED);
+ return rc;
+}
+
+/*
* See virtio_mem_offline_and_remove_memory(): Try to offline and remove a
* all Linux memory blocks covered by the big block.
*/
* Try to allocate a range, marking pages fake-offline, effectively
* fake-offlining them.
*/
-static int virtio_mem_fake_offline(unsigned long pfn, unsigned long nr_pages)
+static int virtio_mem_fake_offline(struct virtio_mem *vm, unsigned long pfn,
+ unsigned long nr_pages)
{
const bool is_movable = is_zone_movable_page(pfn_to_page(pfn));
int rc, retry_count;
* some guarantees.
*/
for (retry_count = 0; retry_count < 5; retry_count++) {
+ /*
+ * If the config changed, stop immediately and go back to the
+ * main loop: avoid trying to keep unplugging if the device
+ * might have decided to not remove any more memory.
+ */
+ if (atomic_read(&vm->config_changed))
+ return -EAGAIN;
+
rc = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE,
GFP_KERNEL);
if (rc == -ENOMEM)
start_pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
sb_id * vm->sbm.sb_size);
- rc = virtio_mem_fake_offline(start_pfn, nr_pages);
+ rc = virtio_mem_fake_offline(vm, start_pfn, nr_pages);
if (rc)
return rc;
}
unplugged:
- /*
- * Once all subblocks of a memory block were unplugged, offline and
- * remove it. This will usually not fail, as no memory is in use
- * anymore - however some other notifiers might NACK the request.
- */
- if (virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
- mutex_unlock(&vm->hotplug_mutex);
- rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
- mutex_lock(&vm->hotplug_mutex);
- if (!rc)
- virtio_mem_sbm_set_mb_state(vm, mb_id,
- VIRTIO_MEM_SBM_MB_UNUSED);
- }
-
+ rc = virtio_mem_sbm_try_remove_unplugged_mb(vm, mb_id);
+ if (rc)
+ vm->sbm.have_unplugged_mb = 1;
+ /* Ignore errors, this is not critical. We'll retry later. */
return 0;
}
VIRTIO_MEM_BBM_BB_ADDED))
return -EINVAL;
- if (bbm_safe_unplug) {
- /*
- * Start by fake-offlining all memory. Once we marked the device
- * block as fake-offline, all newly onlined memory will
- * automatically be kept fake-offline. Protect from concurrent
- * onlining/offlining until we have a consistent state.
- */
- mutex_lock(&vm->hotplug_mutex);
- virtio_mem_bbm_set_bb_state(vm, bb_id,
- VIRTIO_MEM_BBM_BB_FAKE_OFFLINE);
+ /*
+ * Start by fake-offlining all memory. Once we marked the device
+ * block as fake-offline, all newly onlined memory will
+ * automatically be kept fake-offline. Protect from concurrent
+ * onlining/offlining until we have a consistent state.
+ */
+ mutex_lock(&vm->hotplug_mutex);
+ virtio_mem_bbm_set_bb_state(vm, bb_id, VIRTIO_MEM_BBM_BB_FAKE_OFFLINE);
- for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- page = pfn_to_online_page(pfn);
- if (!page)
- continue;
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ page = pfn_to_online_page(pfn);
+ if (!page)
+ continue;
- rc = virtio_mem_fake_offline(pfn, PAGES_PER_SECTION);
- if (rc) {
- end_pfn = pfn;
- goto rollback_safe_unplug;
- }
+ rc = virtio_mem_fake_offline(vm, pfn, PAGES_PER_SECTION);
+ if (rc) {
+ end_pfn = pfn;
+ goto rollback;
}
- mutex_unlock(&vm->hotplug_mutex);
}
+ mutex_unlock(&vm->hotplug_mutex);
rc = virtio_mem_bbm_offline_and_remove_bb(vm, bb_id);
if (rc) {
- if (bbm_safe_unplug) {
- mutex_lock(&vm->hotplug_mutex);
- goto rollback_safe_unplug;
- }
- return rc;
+ mutex_lock(&vm->hotplug_mutex);
+ goto rollback;
}
rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
VIRTIO_MEM_BBM_BB_UNUSED);
return rc;
-rollback_safe_unplug:
+rollback:
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
page = pfn_to_online_page(pfn);
if (!page)
/*
* Try to unplug all blocks that couldn't be unplugged before, for example,
- * because the hypervisor was busy.
+ * because the hypervisor was busy. Further, offline and remove any memory
+ * blocks where we previously failed.
*/
-static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
+static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm)
{
unsigned long id;
- int rc;
+ int rc = 0;
if (!vm->in_sbm) {
virtio_mem_bbm_for_each_bb(vm, id,
VIRTIO_MEM_SBM_MB_UNUSED);
}
+ if (!vm->sbm.have_unplugged_mb)
+ return 0;
+
+ /*
+ * Let's retry (offlining and) removing completely unplugged Linux
+ * memory blocks.
+ */
+ vm->sbm.have_unplugged_mb = false;
+
+ mutex_lock(&vm->hotplug_mutex);
+ virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_MOVABLE_PARTIAL)
+ rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+ virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_KERNEL_PARTIAL)
+ rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+ virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL)
+ rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
+ mutex_unlock(&vm->hotplug_mutex);
+
+ if (rc)
+ vm->sbm.have_unplugged_mb = true;
+ /* Ignore errors, this is not critical. We'll retry later. */
return 0;
}
virtio_mem_refresh_config(vm);
}
- /* Unplug any leftovers from previous runs */
+ /* Cleanup any leftovers from previous runs */
if (!rc)
- rc = virtio_mem_unplug_pending_mb(vm);
+ rc = virtio_mem_cleanup_pending_mb(vm);
if (!rc && vm->requested_size != vm->plugged_size) {
if (vm->requested_size > vm->plugged_size) {
}
}
+ /*
+ * Keep retrying to offline and remove completely unplugged Linux
+ * memory blocks.
+ */
+ if (!rc && vm->in_sbm && vm->sbm.have_unplugged_mb)
+ rc = -EBUSY;
+
switch (rc) {
case 0:
vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
struct virtio_device *vdev =
container_of(_d, struct virtio_device, dev);
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
- struct platform_device *pdev = vm_dev->pdev;
- devm_kfree(&pdev->dev, vm_dev);
+ kfree(vm_dev);
}
/* Platform device */
unsigned long magic;
int rc;
- vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
+ vm_dev = kzalloc(sizeof(*vm_dev), GFP_KERNEL);
if (!vm_dev)
return -ENOMEM;
pci_set_master(pci_dev);
- vp_dev->is_legacy = vp_dev->ldev.ioaddr ? true : false;
-
rc = register_virtio_device(&vp_dev->vdev);
reg_dev = vp_dev;
if (rc)
vp_dev->config_vector = vp_config_vector;
vp_dev->setup_vq = setup_vq;
vp_dev->del_vq = del_vq;
+ vp_dev->is_legacy = true;
return 0;
}
cb.callback = virtio_vdpa_config_cb;
cb.private = vd_dev;
ops->set_config_cb(vdpa, &cb);
+ kfree(masks);
return 0;
err_setup_vq:
virtio_vdpa_del_vqs(vdev);
+ kfree(masks);
return err;
}
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
+ int progress;
caching_ctl = btrfs_get_caching_control(cache);
if (!caching_ctl)
return;
+ /*
+ * We've already failed to allocate from this block group, so even if
+ * there's enough space in the block group it isn't contiguous enough to
+ * allow for an allocation, so wait for at least the next wakeup tick,
+ * or for the thing to be done.
+ */
+ progress = atomic_read(&caching_ctl->progress);
+
wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
- (cache->free_space_ctl->free_space >= num_bytes));
+ (progress != atomic_read(&caching_ctl->progress) &&
+ (cache->free_space_ctl->free_space >= num_bytes)));
btrfs_put_caching_control(caching_ctl);
}
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
- if (wakeup)
+ if (wakeup) {
+ atomic_inc(&caching_ctl->progress);
wake_up(&caching_ctl->wait);
+ }
}
}
path->slots[0]++;
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
refcount_set(&caching_ctl->count, 2);
+ atomic_set(&caching_ctl->progress, 0);
btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
spin_lock(&cache->lock);
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
+ /* Track progress of caching during allocation. */
+ atomic_t progress;
refcount_t count;
};
btrfs_drew_lock_init(&root->snapshot_lock);
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
- !btrfs_is_data_reloc_root(root)) {
+ !btrfs_is_data_reloc_root(root) &&
+ is_fstree(root->root_key.objectid)) {
set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
btrfs_check_and_init_root_item(&root->root_item);
}
root = btrfs_get_global_root(fs_info, objectid);
if (root)
return root;
+
+ /*
+ * If we're called for non-subvolume trees, and above function didn't
+ * find one, do not try to read it from disk.
+ *
+ * This is namely for free-space-tree and quota tree, which can change
+ * at runtime and should only be grabbed from fs_info.
+ */
+ if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID)
+ return ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
ret = 0;
}
- if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+ if (!cache_block_group_error)
+ cache_block_group_error = -EIO;
goto loop;
+ }
if (!find_free_extent_check_size_class(ffe_ctl, block_group))
goto loop;
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
}
/*
- * the filesystem may choose to bump up nr_to_write.
+ * The filesystem may choose to bump up nr_to_write.
* We have to make sure to honor the new nr_to_write
- * at any time
+ * at any time.
*/
- nr_to_write_done = wbc->nr_to_write <= 0;
+ nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
+ wbc->nr_to_write <= 0);
}
folio_batch_release(&fbatch);
cond_resched();
clear_bits,
page_ops);
start += cur_alloc_size;
- if (start >= end)
- return ret;
}
/*
* space_info's bytes_may_use counter, reserved in
* btrfs_check_data_free_space().
*/
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
- clear_bits | EXTENT_CLEAR_DATA_RESV,
- page_ops);
+ if (start < end) {
+ clear_bits |= EXTENT_CLEAR_DATA_RESV;
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ clear_bits, page_ops);
+ }
return ret;
}
err = PTR_ERR(root);
break;
}
- ASSERT(root->reloc_root == reloc_root);
+
+ if (unlikely(root->reloc_root != reloc_root)) {
+ if (root->reloc_root) {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ root->reloc_root->root_key.objectid,
+ root->reloc_root->root_key.type,
+ root->reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &root->reloc_root->root_item),
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ } else {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ }
+ list_add(&reloc_root->root_list, &reloc_roots);
+ btrfs_put_root(root);
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ if (!err)
+ err = -EUCLEAN;
+ break;
+ }
/*
* set reference count to 1, so btrfs_recover_relocation
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
false);
if (btrfs_root_refs(&reloc_root->root_item) > 0) {
- if (IS_ERR(root)) {
+ if (WARN_ON(IS_ERR(root))) {
/*
* For recovery we read the fs roots on mount,
* and if we didn't find the root then we marked
* memory. However there's no reason we can't
* handle the error properly here just in case.
*/
- ASSERT(0);
ret = PTR_ERR(root);
goto out;
}
- if (root->reloc_root != reloc_root) {
+ if (WARN_ON(root->reloc_root != reloc_root)) {
/*
- * This is actually impossible without something
- * going really wrong (like weird race condition
- * or cosmic rays).
+ * This can happen if on-disk metadata has some
+ * corruption, e.g. bad reloc tree key offset.
*/
- ASSERT(0);
ret = -EINVAL;
goto out;
}
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY);
+ /*
+ * Bad rootid for reloc trees.
+ *
+ * Reloc trees are only for subvolume trees, other trees only need
+ * to be COWed to be relocated.
+ */
+ if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID &&
+ !is_fstree(key->offset))) {
+ generic_err(leaf, slot,
+ "invalid reloc tree for root %lld, root id is not a subvolume tree",
+ key->offset);
+ return -EUCLEAN;
+ }
+
/* No such tree id */
if (unlikely(key->objectid == 0)) {
if (is_root_item)
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
-#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
{
struct inode *inode;
- spin_lock_prefetch(&sb->s_inode_list_lock);
-
inode = new_inode_pseudo(sb);
if (inode)
inode_sb_list_add(inode);
int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct buffer_head *ibh;
int err;
+ /*
+ * Do not dirty inodes after the log writer has been detached
+ * and its nilfs_root struct has been freed.
+ */
+ if (unlikely(nilfs_purging(nilfs)))
+ return 0;
+
err = nilfs_load_inode_block(inode, &ibh);
if (unlikely(err)) {
nilfs_warn(inode->i_sb,
nilfs_segctor_destroy(nilfs->ns_writer);
nilfs->ns_writer = NULL;
}
+ set_nilfs_purging(nilfs);
/* Force to free the list of dirty files */
spin_lock(&nilfs->ns_inode_lock);
up_write(&nilfs->ns_segctor_sem);
nilfs_dispose_list(nilfs, &garbage_list, 1);
+ clear_nilfs_purging(nilfs);
}
THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */
THE_NILFS_GC_RUNNING, /* gc process is running */
THE_NILFS_SB_DIRTY, /* super block is dirty */
+ THE_NILFS_PURGING, /* disposing dirty files for cleanup */
};
/**
THE_NILFS_FNS(DISCONTINUED, discontinued)
THE_NILFS_FNS(GC_RUNNING, gc_running)
THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
/*
* Mount option operations
static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
{
+ struct file *file = iocb->ki_filp;
+ char *buf = file->private_data;
loff_t *fpos = &iocb->ki_pos;
size_t phdrs_offset, notes_offset, data_offset;
size_t page_offline_frozen = 1;
case KCORE_VMEMMAP:
case KCORE_TEXT:
/*
- * We use _copy_to_iter() to bypass usermode hardening
- * which would otherwise prevent this operation.
+ * Sadly we must use a bounce buffer here to be able to
+ * make use of copy_from_kernel_nofault(), as these
+ * memory regions might not always be mapped on all
+ * architectures.
*/
- if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+ if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+ if (iov_iter_zero(tsz, iter) != tsz) {
+ ret = -EFAULT;
+ goto out;
+ }
+ /*
+ * We know the bounce buffer is safe to copy from, so
+ * use _copy_to_iter() directly.
+ */
+ } else if (_copy_to_iter(buf, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
if (ret)
return ret;
+ filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
return 0;
}
+static int release_kcore(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
static const struct proc_ops kcore_proc_ops = {
.proc_read_iter = read_kcore_iter,
.proc_open = open_kcore,
+ .proc_release = release_kcore,
.proc_lseek = default_llseek,
};
in_flight(server),
atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
+#ifdef CONFIG_NET_NS
+ if (server->net)
+ seq_printf(m, " Net namespace: %u ", server->net->ns.inum);
+#endif /* NET_NS */
+
}
static inline const char *smb_speed_to_str(size_t bps)
server->reconnect_instance,
server->srv_count,
server->sec_mode, in_flight(server));
+#ifdef CONFIG_NET_NS
+ if (server->net)
+ seq_printf(m, " Net namespace: %u ", server->net->ns.inum);
+#endif /* NET_NS */
seq_printf(m, "\nIn Send: %d In MaxReq Wait: %d",
atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
+
if (server->leaf_fullpath) {
seq_printf(m, "\nDFS leaf full path: %s",
server->leaf_fullpath);
io_error:
kunmap(page);
- unlock_page(page);
read_complete:
+ unlock_page(page);
return rc;
}
struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
oplock_break);
struct inode *inode = d_inode(cfile->dentry);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsInodeInfo *cinode = CIFS_I(inode);
- struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
- struct TCP_Server_Info *server = tcon->ses->server;
+ struct cifs_tcon *tcon;
+ struct TCP_Server_Info *server;
+ struct tcon_link *tlink;
int rc = 0;
bool purge_cache = false, oplock_break_cancelled;
__u64 persistent_fid, volatile_fid;
wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
TASK_UNINTERRUPTIBLE);
+ tlink = cifs_sb_tlink(cifs_sb);
+ if (IS_ERR(tlink))
+ goto out;
+ tcon = tlink_tcon(tlink);
+ server = tcon->ses->server;
+
server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
cfile->oplock_epoch, &purge_cache);
/*
* MS-SMB2 3.2.5.19.1 and 3.2.5.19.2 (and MS-CIFS 3.2.5.42) do not require
* an acknowledgment to be sent when the file has already been closed.
- * check for server null, since can race with kill_sb calling tree disconnect.
*/
spin_lock(&cinode->open_file_lock);
- if (tcon->ses && tcon->ses->server && !oplock_break_cancelled &&
- !list_empty(&cinode->openFileList)) {
+ /* check list empty since can race with kill_sb calling tree disconnect */
+ if (!oplock_break_cancelled && !list_empty(&cinode->openFileList)) {
spin_unlock(&cinode->open_file_lock);
- rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid,
- volatile_fid, net_fid, cinode);
+ rc = server->ops->oplock_response(tcon, persistent_fid,
+ volatile_fid, net_fid, cinode);
cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
} else
spin_unlock(&cinode->open_file_lock);
+ cifs_put_tlink(tlink);
+out:
cifs_done_oplock_break(cinode);
}
return generic_file_llseek_size(file, offset, whence, isize, isize);
}
-struct zonefs_zone_append_bio {
- /* The target inode of the BIO */
- struct inode *inode;
-
- /* For sync writes, the target append write offset */
- u64 append_offset;
-
- /*
- * This member must come last, bio_alloc_bioset will allocate enough
- * bytes for entire zonefs_bio but relies on bio being last.
- */
- struct bio bio;
-};
-
-static inline struct zonefs_zone_append_bio *
-zonefs_zone_append_bio(struct bio *bio)
-{
- return container_of(bio, struct zonefs_zone_append_bio, bio);
-}
-
-static void zonefs_file_zone_append_dio_bio_end_io(struct bio *bio)
-{
- struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio);
- struct zonefs_zone *z = zonefs_inode_zone(za_bio->inode);
- sector_t za_sector;
-
- if (bio->bi_status != BLK_STS_OK)
- goto bio_end;
-
- /*
- * If the file zone was written underneath the file system, the zone
- * append operation can still succedd (if the zone is not full) but
- * the write append location will not be where we expect it to be.
- * Check that we wrote where we intended to, that is, at z->z_wpoffset.
- */
- za_sector = z->z_sector + (za_bio->append_offset >> SECTOR_SHIFT);
- if (bio->bi_iter.bi_sector != za_sector) {
- zonefs_warn(za_bio->inode->i_sb,
- "Invalid write sector %llu for zone at %llu\n",
- bio->bi_iter.bi_sector, z->z_sector);
- bio->bi_status = BLK_STS_IOERR;
- }
-
-bio_end:
- iomap_dio_bio_end_io(bio);
-}
-
-static void zonefs_file_zone_append_dio_submit_io(const struct iomap_iter *iter,
- struct bio *bio,
- loff_t file_offset)
-{
- struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio);
- struct inode *inode = iter->inode;
- struct zonefs_zone *z = zonefs_inode_zone(inode);
-
- /*
- * Issue a zone append BIO to process sync dio writes. The append
- * file offset is saved to check the zone append write location
- * on completion of the BIO.
- */
- za_bio->inode = inode;
- za_bio->append_offset = file_offset;
-
- bio->bi_opf &= ~REQ_OP_WRITE;
- bio->bi_opf |= REQ_OP_ZONE_APPEND;
- bio->bi_iter.bi_sector = z->z_sector;
- bio->bi_end_io = zonefs_file_zone_append_dio_bio_end_io;
-
- submit_bio(bio);
-}
-
static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
int error, unsigned int flags)
{
return 0;
}
-static struct bio_set zonefs_zone_append_bio_set;
-
-static const struct iomap_dio_ops zonefs_zone_append_dio_ops = {
- .submit_io = zonefs_file_zone_append_dio_submit_io,
- .end_io = zonefs_file_write_dio_end_io,
- .bio_set = &zonefs_zone_append_bio_set,
-};
-
static const struct iomap_dio_ops zonefs_write_dio_ops = {
.end_io = zonefs_file_write_dio_end_io,
};
struct zonefs_inode_info *zi = ZONEFS_I(inode);
struct zonefs_zone *z = zonefs_inode_zone(inode);
struct super_block *sb = inode->i_sb;
- const struct iomap_dio_ops *dio_ops;
- bool sync = is_sync_kiocb(iocb);
- bool append = false;
ssize_t ret, count;
/*
* as this can cause write reordering (e.g. the first aio gets EAGAIN
* on the inode lock but the second goes through but is now unaligned).
*/
- if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT))
+ if (zonefs_zone_is_seq(z) && !is_sync_kiocb(iocb) &&
+ (iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
if (iocb->ki_flags & IOCB_NOWAIT) {
goto inode_unlock;
}
mutex_unlock(&zi->i_truncate_mutex);
- append = sync;
- }
-
- if (append) {
- unsigned int max = bdev_max_zone_append_sectors(sb->s_bdev);
-
- max = ALIGN_DOWN(max << SECTOR_SHIFT, sb->s_blocksize);
- iov_iter_truncate(from, max);
-
- dio_ops = &zonefs_zone_append_dio_ops;
- } else {
- dio_ops = &zonefs_write_dio_ops;
}
/*
* the user can make sense of the error.
*/
ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
- dio_ops, 0, NULL, 0);
+ &zonefs_write_dio_ops, 0, NULL, 0);
if (ret == -ENOTBLK)
ret = -EBUSY;
.splice_write = iter_file_splice_write,
.iopoll = iocb_bio_iopoll,
};
-
-int zonefs_file_bioset_init(void)
-{
- return bioset_init(&zonefs_zone_append_bio_set, BIO_POOL_SIZE,
- offsetof(struct zonefs_zone_append_bio, bio),
- BIOSET_NEED_BVECS);
-}
-
-void zonefs_file_bioset_exit(void)
-{
- bioset_exit(&zonefs_zone_append_bio_set);
-}
BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE);
- ret = zonefs_file_bioset_init();
- if (ret)
- return ret;
-
ret = zonefs_init_inodecache();
if (ret)
- goto destroy_bioset;
+ return ret;
ret = zonefs_sysfs_init();
if (ret)
zonefs_sysfs_exit();
destroy_inodecache:
zonefs_destroy_inodecache();
-destroy_bioset:
- zonefs_file_bioset_exit();
return ret;
}
unregister_filesystem(&zonefs_type);
zonefs_sysfs_exit();
zonefs_destroy_inodecache();
- zonefs_file_bioset_exit();
}
MODULE_AUTHOR("Damien Le Moal");
extern const struct address_space_operations zonefs_file_aops;
extern const struct file_operations zonefs_file_operations;
int zonefs_file_truncate(struct inode *inode, loff_t isize);
-int zonefs_file_bioset_init(void);
-void zonefs_file_bioset_exit(void);
/* In sysfs.c */
int zonefs_sysfs_register(struct super_block *sb);
u8 vfreq_aspect;
} __attribute__((packed));
-#define DRM_EDID_PT_SYNC_MASK (3 << 3)
-# define DRM_EDID_PT_ANALOG_CSYNC (0 << 3)
-# define DRM_EDID_PT_BIPOLAR_ANALOG_CSYNC (1 << 3)
-# define DRM_EDID_PT_DIGITAL_CSYNC (2 << 3)
-# define DRM_EDID_PT_CSYNC_ON_RGB (1 << 1) /* analog csync only */
-# define DRM_EDID_PT_CSYNC_SERRATE (1 << 2)
-# define DRM_EDID_PT_DIGITAL_SEPARATE_SYNC (3 << 3)
-# define DRM_EDID_PT_HSYNC_POSITIVE (1 << 1) /* also digital csync */
-# define DRM_EDID_PT_VSYNC_POSITIVE (1 << 2)
+#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 1)
+#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 2)
+#define DRM_EDID_PT_SEPARATE_SYNC (3 << 3)
#define DRM_EDID_PT_STEREO (1 << 5)
#define DRM_EDID_PT_INTERLACED (1 << 7)
static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
{
bio->bi_opf |= REQ_POLLED;
- if (!is_sync_kiocb(kiocb))
+ if (kiocb->ki_flags & IOCB_NOWAIT)
bio->bi_opf |= REQ_NOWAIT;
}
bool multiple_queues;
bool has_elevator;
- bool nowait;
struct list_head cb_list; /* md requires an unplug callback */
};
struct btf_member;
#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+/**
+ * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to
+ * define a BPF_MAP_TYPE_STRUCT_OPS map type composed
+ * of BPF_PROG_TYPE_STRUCT_OPS progs.
+ * @verifier_ops: A structure of callbacks that are invoked by the verifier
+ * when determining whether the struct_ops progs in the
+ * struct_ops map are valid.
+ * @init: A callback that is invoked a single time, and before any other
+ * callback, to initialize the structure. A nonzero return value means
+ * the subsystem could not be initialized.
+ * @check_member: When defined, a callback invoked by the verifier to allow
+ * the subsystem to determine if an entry in the struct_ops map
+ * is valid. A nonzero return value means that the map is
+ * invalid and should be rejected by the verifier.
+ * @init_member: A callback that is invoked for each member of the struct_ops
+ * map to allow the subsystem to initialize the member. A nonzero
+ * value means the member could not be initialized. This callback
+ * is exclusive with the @type, @type_id, @value_type, and
+ * @value_id fields.
+ * @reg: A callback that is invoked when the struct_ops map has been
+ * initialized and is being attached to. Zero means the struct_ops map
+ * has been successfully registered and is live. A nonzero return value
+ * means the struct_ops map could not be registered.
+ * @unreg: A callback that is invoked when the struct_ops map should be
+ * unregistered.
+ * @update: A callback that is invoked when the live struct_ops map is being
+ * updated to contain new values. This callback is only invoked when
+ * the struct_ops map is loaded with BPF_F_LINK. If not defined, the
+ * it is assumed that the struct_ops map cannot be updated.
+ * @validate: A callback that is invoked after all of the members have been
+ * initialized. This callback should perform static checks on the
+ * map, meaning that it should either fail or succeed
+ * deterministically. A struct_ops map that has been validated may
+ * not necessarily succeed in being registered if the call to @reg
+ * fails. For example, a valid struct_ops map may be loaded, but
+ * then fail to be registered due to there being another active
+ * struct_ops map on the system in the subsystem already. For this
+ * reason, if this callback is not defined, the check is skipped as
+ * the struct_ops map will have final verification performed in
+ * @reg.
+ * @type: BTF type.
+ * @value_type: Value type.
+ * @name: The name of the struct bpf_struct_ops object.
+ * @func_models: Func models
+ * @type_id: BTF type id.
+ * @value_id: BTF value id.
+ */
struct bpf_struct_ops {
const struct bpf_verifier_ops *verifier_ops;
int (*init)(struct btf *btf);
void bpf_link_inc(struct bpf_link *link);
void bpf_link_put(struct bpf_link *link);
int bpf_link_new_fd(struct bpf_link *link);
-struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
struct bpf_link *bpf_link_get_from_fd(u32 ufd);
struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
prefetch() should be defined by the architecture, if not, the
#define below provides a no-op define.
- There are 3 prefetch() macros:
+ There are 2 prefetch() macros:
prefetch(x) - prefetches the cacheline at "x" for read
prefetchw(x) - prefetches the cacheline at "x" for write
- spin_lock_prefetch(x) - prefetches the spinlock *x for taking
there is also PREFETCH_STRIDE which is the architecure-preferred
"lookahead" size for prefetching streamed operations.
#define prefetchw(x) __builtin_prefetch(x,1)
#endif
-#ifndef ARCH_HAS_SPINLOCK_PREFETCH
-#define spin_lock_prefetch(x) prefetchw(x)
-#endif
-
#ifndef PREFETCH_STRIDE
#define PREFETCH_STRIDE (4*L1_CACHE_BYTES)
#endif
if (gso_type & SKB_GSO_UDP)
nh_off -= thlen;
+ /* Kernel has a special handling for GSO_BY_FRAGS. */
+ if (gso_size == GSO_BY_FRAGS)
+ return -EINVAL;
+
/* Too small packets are not really GSO ones. */
if (skb->len - nh_off > gso_size) {
shinfo->gso_size = gso_size;
if (!sk)
return NULL;
- if (!prefetched)
+ if (!prefetched || !sk_fullsock(sk))
return sk;
if (sk->sk_protocol == IPPROTO_TCP) {
if (!sk)
return NULL;
- if (!prefetched)
+ if (!prefetched || !sk_fullsock(sk))
return sk;
if (sk->sk_protocol == IPPROTO_TCP) {
* @expr: stateful expression
* @ops: set ops
* @flags: set flags
+ * @dead: set will be freed, never cleared
* @genmask: generation mask
* @klen: key length
* @dlen: data length
return sk->sk_prot->memory_pressure != NULL;
}
+static inline bool sk_under_global_memory_pressure(const struct sock *sk)
+{
+ return sk->sk_prot->memory_pressure &&
+ !!*sk->sk_prot->memory_pressure;
+}
+
static inline bool sk_under_memory_pressure(const struct sock *sk)
{
if (!sk->sk_prot->memory_pressure)
if (dev->xfrmdev_ops->xdo_dev_state_free)
dev->xfrmdev_ops->xdo_dev_state_free(x);
xso->dev = NULL;
+ xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
netdev_put(dev, &xso->dev_tracker);
}
}
TCA_NETEM_JITTER64,
TCA_NETEM_SLOT,
TCA_NETEM_SLOT_DIST,
+ TCA_NETEM_PRNG_SEED,
__TCA_NETEM_MAX,
};
* - use the kernel virtual address of the shared io_uring context
* (instead of the userspace-provided address, which has to be 0UL
* anyway).
+ * - use the same pgoff which the get_unmapped_area() uses to
+ * calculate the page colouring.
* For architectures without such aliasing requirements, the
* architecture will return any suitable mapping because addr is 0.
*/
pgoff = 0; /* has been translated to ptr above */
#ifdef SHM_COLOUR
addr = (uintptr_t) ptr;
+ pgoff = addr >> PAGE_SHIFT;
#else
addr = 0UL;
#endif
{
/*
* Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
- * it'll always -EAGAIN
+ * it'll always -EAGAIN. Note that we test for __O_TMPFILE because
+ * O_TMPFILE includes O_DIRECTORY, which isn't a flag we need to force
+ * async for.
*/
- return open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE);
+ return open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE);
}
static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
}
if (st_map->map.map_flags & BPF_F_LINK) {
- err = st_ops->validate(kdata);
- if (err)
- goto reset_unlock;
+ err = 0;
+ if (st_ops->validate) {
+ err = st_ops->validate(kdata);
+ if (err)
+ goto reset_unlock;
+ }
set_memory_rox((long)st_map->image, 1);
/* Let bpf_link handle registration & unregistration.
*
if (attr->value_size != vt->size)
return ERR_PTR(-EINVAL);
- if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
- return ERR_PTR(-EOPNOTSUPP);
-
t = st_ops->type;
st_map_size = sizeof(*st_map) +
if (!bpf_struct_ops_valid_to_reg(new_map))
return -EINVAL;
+ if (!st_map->st_ops->update)
+ return -EOPNOTSUPP;
+
mutex_lock(&update_mutex);
old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
if (!ulen ^ !uname)
return -EINVAL;
- if (!uname)
- return 0;
err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
probe_offset, probe_addr);
if (err)
return err;
-
+ if (!uname)
+ return 0;
if (buf) {
len = strlen(buf);
err = bpf_copy_to_user(uname, buf, ulen, len);
int error;
if (!hibernation_available())
- return 0;
+ return n;
if (len && buf[len-1] == '\n')
len--;
failed:
while (sgtable->nents > sgtable->orig_nents)
- put_page(sg_page(&sgtable->sgl[--sgtable->nents]));
+ unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents]));
return res;
}
/*
* Check if the pageblock has already been marked skipped.
- * Only the aligned PFN is checked as the caller isolates
+ * Only the first PFN is checked as the caller isolates
* COMPACT_CLUSTER_MAX at a time so the second call must
* not falsely conclude that the block should be skipped.
*/
- if (!valid_page && pageblock_aligned(low_pfn)) {
+ if (!valid_page && (pageblock_aligned(low_pfn) ||
+ low_pfn == cc->zone->zone_start_pfn)) {
if (!isolation_suitable(cc, page)) {
low_pfn = end_pfn;
folio = NULL;
* before making it "skip" so other compaction instances do
* not scan the same block.
*/
- if (pageblock_aligned(low_pfn) &&
+ if ((pageblock_aligned(low_pfn) ||
+ low_pfn == cc->zone->zone_start_pfn) &&
!fast_find_block && !isolation_suitable(cc, page))
continue;
return NULL;
filter->type = type;
filter->matching = matching;
+ INIT_LIST_HEAD(&filter->list);
return filter;
}
unsigned int order) { }
#endif
+static inline void __clear_hugetlb_destructor(struct hstate *h,
+ struct folio *folio)
+{
+ lockdep_assert_held(&hugetlb_lock);
+
+ /*
+ * Very subtle
+ *
+ * For non-gigantic pages set the destructor to the normal compound
+ * page dtor. This is needed in case someone takes an additional
+ * temporary ref to the page, and freeing is delayed until they drop
+ * their reference.
+ *
+ * For gigantic pages set the destructor to the null dtor. This
+ * destructor will never be called. Before freeing the gigantic
+ * page destroy_compound_gigantic_folio will turn the folio into a
+ * simple group of pages. After this the destructor does not
+ * apply.
+ *
+ */
+ if (hstate_is_gigantic(h))
+ folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
+ else
+ folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
+}
+
/*
- * Remove hugetlb folio from lists, and update dtor so that the folio appears
- * as just a compound page.
+ * Remove hugetlb folio from lists.
+ * If vmemmap exists for the folio, update dtor so that the folio appears
+ * as just a compound page. Otherwise, wait until after allocating vmemmap
+ * to update dtor.
*
* A reference is held on the folio, except in the case of demote.
*
}
/*
- * Very subtle
- *
- * For non-gigantic pages set the destructor to the normal compound
- * page dtor. This is needed in case someone takes an additional
- * temporary ref to the page, and freeing is delayed until they drop
- * their reference.
- *
- * For gigantic pages set the destructor to the null dtor. This
- * destructor will never be called. Before freeing the gigantic
- * page destroy_compound_gigantic_folio will turn the folio into a
- * simple group of pages. After this the destructor does not
- * apply.
- *
- * This handles the case where more than one ref is held when and
- * after update_and_free_hugetlb_folio is called.
- *
- * In the case of demote we do not ref count the page as it will soon
- * be turned into a page of smaller size.
+ * We can only clear the hugetlb destructor after allocating vmemmap
+ * pages. Otherwise, someone (memory error handling) may try to write
+ * to tail struct pages.
+ */
+ if (!folio_test_hugetlb_vmemmap_optimized(folio))
+ __clear_hugetlb_destructor(h, folio);
+
+ /*
+ * In the case of demote we do not ref count the page as it will soon
+ * be turned into a page of smaller size.
*/
if (!demote)
folio_ref_unfreeze(folio, 1);
- if (hstate_is_gigantic(h))
- folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
- else
- folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
h->nr_huge_pages--;
h->nr_huge_pages_node[nid]--;
{
int i;
struct page *subpage;
+ bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio);
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return;
if (unlikely(folio_test_hwpoison(folio)))
folio_clear_hugetlb_hwpoison(folio);
+ /*
+ * If vmemmap pages were allocated above, then we need to clear the
+ * hugetlb destructor under the hugetlb lock.
+ */
+ if (clear_dtor) {
+ spin_lock_irq(&hugetlb_lock);
+ __clear_hugetlb_destructor(h, folio);
+ spin_unlock_irq(&hugetlb_lock);
+ }
+
for (i = 0; i < pages_per_huge_page(h); i++) {
subpage = folio_page(folio, i);
subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
anon_vma->root == vma->anon_vma->root) {
return page; /* still no need to copy it */
}
+ if (PageHWPoison(page))
+ return ERR_PTR(-EHWPOISON);
if (!PageUptodate(page))
return page; /* let do_swap_page report the error */
{
struct folio *folio;
struct page *p;
- int ret = -EBUSY;
+ int ret = -EBUSY, ghp;
unsigned long count = 1;
bool huge = false;
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
goto unlock_mutex;
}
+ if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
+ goto unlock_mutex;
+
+ /*
+ * Note that folio->_mapcount is overloaded in SLAB, so the simple test
+ * in folio_mapped() has to be done after folio_test_slab() is checked.
+ */
if (folio_mapped(folio)) {
unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
pfn, &unpoison_rs);
goto unlock_mutex;
}
- if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
- goto unlock_mutex;
-
- ret = get_hwpoison_page(p, MF_UNPOISON);
- if (!ret) {
+ ghp = get_hwpoison_page(p, MF_UNPOISON);
+ if (!ghp) {
if (PageHuge(p)) {
huge = true;
count = folio_free_raw_hwp(folio, false);
- if (count == 0) {
- ret = -EBUSY;
+ if (count == 0)
goto unlock_mutex;
- }
}
ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY;
- } else if (ret < 0) {
- if (ret == -EHWPOISON) {
+ } else if (ghp < 0) {
+ if (ghp == -EHWPOISON) {
ret = put_page_back_buddy(p) ? 0 : -EBUSY;
- } else
+ } else {
+ ret = ghp;
unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
pfn, &unpoison_rs);
+ }
} else {
if (PageHuge(p)) {
huge = true;
count = folio_free_raw_hwp(folio, false);
if (count == 0) {
- ret = -EBUSY;
folio_put(folio);
goto unlock_mutex;
}
struct page *swapcache;
spinlock_t *ptl;
pte_t *pte, new_pte, old_pte;
- bool hwposioned = false;
+ bool hwpoisoned = PageHWPoison(page);
int ret = 1;
swapcache = page;
if (unlikely(!page))
return -ENOMEM;
else if (unlikely(PTR_ERR(page) == -EHWPOISON))
- hwposioned = true;
+ hwpoisoned = true;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
old_pte = ptep_get(pte);
- if (unlikely(hwposioned || !PageUptodate(page))) {
+ if (unlikely(hwpoisoned || !PageUptodate(page))) {
swp_entry_t swp_entry;
dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
- if (hwposioned) {
+ if (hwpoisoned) {
swp_entry = make_hwpoison_entry(swapcache);
page = swapcache;
} else {
static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
{
+ struct zs_pool *pool;
struct zspage *zspage;
/*
VM_BUG_ON_PAGE(PageIsolated(page), page);
zspage = get_zspage(page);
- migrate_write_lock(zspage);
+ pool = zspage->pool;
+ spin_lock(&pool->lock);
inc_zspage_isolation(zspage);
- migrate_write_unlock(zspage);
+ spin_unlock(&pool->lock);
return true;
}
kunmap_atomic(s_addr);
replace_sub_page(class, zspage, newpage, page);
+ dec_zspage_isolation(zspage);
/*
* Since we complete the data copy and set up new zspage structure,
* it's okay to release the pool's lock.
*/
spin_unlock(&pool->lock);
- dec_zspage_isolation(zspage);
migrate_write_unlock(zspage);
get_page(newpage);
static void zs_page_putback(struct page *page)
{
+ struct zs_pool *pool;
struct zspage *zspage;
VM_BUG_ON_PAGE(!PageIsolated(page), page);
zspage = get_zspage(page);
- migrate_write_lock(zspage);
+ pool = zspage->pool;
+ spin_lock(&pool->lock);
dec_zspage_isolation(zspage);
- migrate_write_unlock(zspage);
+ spin_unlock(&pool->lock);
}
static const struct movable_operations zsmalloc_mops = {
dev->name);
vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
}
- if (event == NETDEV_DOWN)
+ if (event == NETDEV_DOWN &&
+ (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
vlan_info = rtnl_dereference(dev->vlan_info);
},
.gw = {
.init_sel_class = batadv_iv_init_sel_class,
+ .sel_class_max = BATADV_TQ_MAX_VALUE,
.get_best_gw_node = batadv_iv_gw_get_best_gw_node,
.is_eligible = batadv_iv_gw_is_eligible,
.dump = batadv_iv_gw_dump,
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kref.h>
+#include <linux/limits.h>
#include <linux/list.h>
#include <linux/minmax.h>
#include <linux/netdevice.h>
#include "bat_v_elp.h"
#include "bat_v_ogm.h"
#include "gateway_client.h"
-#include "gateway_common.h"
#include "hard-interface.h"
#include "hash.h"
#include "log.h"
atomic_set(&bat_priv->gw.sel_class, 50);
}
-static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv,
- char *buff, size_t count)
-{
- u32 old_class, class;
-
- if (!batadv_parse_throughput(bat_priv->soft_iface, buff,
- "B.A.T.M.A.N. V GW selection class",
- &class))
- return -EINVAL;
-
- old_class = atomic_read(&bat_priv->gw.sel_class);
- atomic_set(&bat_priv->gw.sel_class, class);
-
- if (old_class != class)
- batadv_gw_reselect(bat_priv);
-
- return count;
-}
-
/**
* batadv_v_gw_throughput_get() - retrieve the GW-bandwidth for a given GW
* @gw_node: the GW to retrieve the metric for
},
.gw = {
.init_sel_class = batadv_v_init_sel_class,
- .store_sel_class = batadv_v_store_sel_class,
+ .sel_class_max = U32_MAX,
.get_best_gw_node = batadv_v_gw_get_best_gw_node,
.is_eligible = batadv_v_gw_is_eligible,
.dump = batadv_v_gw_dump,
#include <linux/atomic.h>
#include <linux/byteorder/generic.h>
-#include <linux/errno.h>
-#include <linux/kstrtox.h>
-#include <linux/limits.h>
-#include <linux/math64.h>
-#include <linux/netdevice.h>
#include <linux/stddef.h>
-#include <linux/string.h>
+#include <linux/types.h>
#include <uapi/linux/batadv_packet.h>
#include <uapi/linux/batman_adv.h>
#include "gateway_client.h"
-#include "log.h"
#include "tvlv.h"
/**
- * batadv_parse_throughput() - parse supplied string buffer to extract
- * throughput information
- * @net_dev: the soft interface net device
- * @buff: string buffer to parse
- * @description: text shown when throughput string cannot be parsed
- * @throughput: pointer holding the returned throughput information
- *
- * Return: false on parse error and true otherwise.
- */
-bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
- const char *description, u32 *throughput)
-{
- enum batadv_bandwidth_units bw_unit_type = BATADV_BW_UNIT_KBIT;
- u64 lthroughput;
- char *tmp_ptr;
- int ret;
-
- if (strlen(buff) > 4) {
- tmp_ptr = buff + strlen(buff) - 4;
-
- if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
- bw_unit_type = BATADV_BW_UNIT_MBIT;
-
- if (strncasecmp(tmp_ptr, "kbit", 4) == 0 ||
- bw_unit_type == BATADV_BW_UNIT_MBIT)
- *tmp_ptr = '\0';
- }
-
- ret = kstrtou64(buff, 10, <hroughput);
- if (ret) {
- batadv_err(net_dev,
- "Invalid throughput speed for %s: %s\n",
- description, buff);
- return false;
- }
-
- switch (bw_unit_type) {
- case BATADV_BW_UNIT_MBIT:
- /* prevent overflow */
- if (U64_MAX / 10 < lthroughput) {
- batadv_err(net_dev,
- "Throughput speed for %s too large: %s\n",
- description, buff);
- return false;
- }
-
- lthroughput *= 10;
- break;
- case BATADV_BW_UNIT_KBIT:
- default:
- lthroughput = div_u64(lthroughput, 100);
- break;
- }
-
- if (lthroughput > U32_MAX) {
- batadv_err(net_dev,
- "Throughput speed for %s too large: %s\n",
- description, buff);
- return false;
- }
-
- *throughput = lthroughput;
-
- return true;
-}
-
-/**
- * batadv_parse_gw_bandwidth() - parse supplied string buffer to extract
- * download and upload bandwidth information
- * @net_dev: the soft interface net device
- * @buff: string buffer to parse
- * @down: pointer holding the returned download bandwidth information
- * @up: pointer holding the returned upload bandwidth information
- *
- * Return: false on parse error and true otherwise.
- */
-static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff,
- u32 *down, u32 *up)
-{
- char *slash_ptr;
- bool ret;
-
- slash_ptr = strchr(buff, '/');
- if (slash_ptr)
- *slash_ptr = 0;
-
- ret = batadv_parse_throughput(net_dev, buff, "download gateway speed",
- down);
- if (!ret)
- return false;
-
- /* we also got some upload info */
- if (slash_ptr) {
- ret = batadv_parse_throughput(net_dev, slash_ptr + 1,
- "upload gateway speed", up);
- if (!ret)
- return false;
- }
-
- return true;
-}
-
-/**
* batadv_gw_tvlv_container_update() - update the gw tvlv container after
* gateway setting change
* @bat_priv: the bat priv with all the soft interface information
}
/**
- * batadv_gw_bandwidth_set() - Parse and set download/upload gateway bandwidth
- * from supplied string buffer
- * @net_dev: netdev struct of the soft interface
- * @buff: the buffer containing the user data
- * @count: number of bytes in the buffer
- *
- * Return: 'count' on success or a negative error code in case of failure
- */
-ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
- size_t count)
-{
- struct batadv_priv *bat_priv = netdev_priv(net_dev);
- u32 down_curr;
- u32 up_curr;
- u32 down_new = 0;
- u32 up_new = 0;
- bool ret;
-
- down_curr = (unsigned int)atomic_read(&bat_priv->gw.bandwidth_down);
- up_curr = (unsigned int)atomic_read(&bat_priv->gw.bandwidth_up);
-
- ret = batadv_parse_gw_bandwidth(net_dev, buff, &down_new, &up_new);
- if (!ret)
- return -EINVAL;
-
- if (!down_new)
- down_new = 1;
-
- if (!up_new)
- up_new = down_new / 5;
-
- if (!up_new)
- up_new = 1;
-
- if (down_curr == down_new && up_curr == up_new)
- return count;
-
- batadv_gw_reselect(bat_priv);
- batadv_info(net_dev,
- "Changing gateway bandwidth from: '%u.%u/%u.%u MBit' to: '%u.%u/%u.%u MBit'\n",
- down_curr / 10, down_curr % 10, up_curr / 10, up_curr % 10,
- down_new / 10, down_new % 10, up_new / 10, up_new % 10);
-
- atomic_set(&bat_priv->gw.bandwidth_down, down_new);
- atomic_set(&bat_priv->gw.bandwidth_up, up_new);
- batadv_gw_tvlv_container_update(bat_priv);
-
- return count;
-}
-
-/**
* batadv_gw_tvlv_ogm_handler_v1() - process incoming gateway tvlv container
* @bat_priv: the bat priv with all the soft interface information
* @orig: the orig_node of the ogm
#include "main.h"
-#include <linux/netdevice.h>
-#include <linux/types.h>
-
/**
* enum batadv_bandwidth_units - bandwidth unit types
*/
#define BATADV_GW_MODE_CLIENT_NAME "client"
#define BATADV_GW_MODE_SERVER_NAME "server"
-ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
- size_t count);
void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv);
void batadv_gw_init(struct batadv_priv *bat_priv);
void batadv_gw_free(struct batadv_priv *bat_priv);
-bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
- const char *description, u32 *throughput);
#endif /* _NET_BATMAN_ADV_GATEWAY_COMMON_H_ */
#include <linux/atomic.h>
#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
#include <linux/container_of.h>
#include <linux/errno.h>
#include <linux/gfp.h>
struct batadv_priv *bat_priv;
__be16 ethertype = htons(ETH_P_BATMAN);
int max_header_len = batadv_max_header_len();
+ unsigned int required_mtu;
+ unsigned int hardif_mtu;
int ret;
- if (hard_iface->net_dev->mtu < ETH_MIN_MTU + max_header_len)
+ hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu);
+ required_mtu = READ_ONCE(soft_iface->mtu) + max_header_len;
+
+ if (hardif_mtu < ETH_MIN_MTU + max_header_len)
return -EINVAL;
if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
hard_iface->net_dev->name);
if (atomic_read(&bat_priv->fragmentation) &&
- hard_iface->net_dev->mtu < ETH_DATA_LEN + max_header_len)
+ hardif_mtu < required_mtu)
batadv_info(hard_iface->soft_iface,
"The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %i would solve the problem.\n",
- hard_iface->net_dev->name, hard_iface->net_dev->mtu,
- ETH_DATA_LEN + max_header_len);
+ hard_iface->net_dev->name, hardif_mtu,
+ required_mtu);
if (!atomic_read(&bat_priv->fragmentation) &&
- hard_iface->net_dev->mtu < ETH_DATA_LEN + max_header_len)
+ hardif_mtu < required_mtu)
batadv_info(hard_iface->soft_iface,
"The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %i.\n",
- hard_iface->net_dev->name, hard_iface->net_dev->mtu,
- ETH_DATA_LEN + max_header_len);
+ hard_iface->net_dev->name, hardif_mtu,
+ required_mtu);
if (batadv_hardif_is_iface_up(hard_iface))
batadv_hardif_activate_interface(hard_iface);
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2023.1"
+#define BATADV_SOURCE_VERSION "2023.3"
#endif
/* B.A.T.M.A.N. parameters */
*
* Return: 0 on success, < 0 on error
*/
-int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
+static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
{
struct sk_buff *msg;
int ret;
* algorithm in use implements the GW API
*/
- u32 sel_class_max = 0xffffffffu;
+ u32 sel_class_max = bat_priv->algo_ops->gw.sel_class_max;
u32 sel_class;
attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS];
sel_class = nla_get_u32(attr);
- if (!bat_priv->algo_ops->gw.store_sel_class)
- sel_class_max = BATADV_TQ_MAX_VALUE;
-
if (sel_class >= 1 && sel_class <= sel_class_max) {
atomic_set(&bat_priv->gw.sel_class, sel_class);
batadv_gw_reselect(bat_priv);
*
* Return: 0 on success, < 0 on error
*/
-int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
- struct batadv_hard_iface *hard_iface)
+static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
+ struct batadv_hard_iface *hard_iface)
{
struct sk_buff *msg;
int ret;
*
* Return: 0 on success, < 0 on error
*/
-int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
- struct batadv_softif_vlan *vlan)
+static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
+ struct batadv_softif_vlan *vlan)
{
struct sk_buff *msg;
int ret;
u8 result, u32 test_time, u64 total_bytes,
u32 cookie);
-int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv);
-int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
- struct batadv_hard_iface *hard_iface);
-int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
- struct batadv_softif_vlan *vlan);
-
extern struct genl_family batadv_netlink_family;
#endif /* _NET_BATMAN_ADV_NETLINK_H_ */
struct batadv_hard_iface *iface);
int batadv_recv_bcast_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
-int batadv_recv_tt_query(struct sk_buff *skb,
- struct batadv_hard_iface *recv_if);
-int batadv_recv_roam_adv(struct sk_buff *skb,
- struct batadv_hard_iface *recv_if);
int batadv_recv_unicast_tvlv(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
{
/* check ranges */
- if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
+ if (new_mtu < ETH_MIN_MTU || new_mtu > batadv_hardif_min_mtu(dev))
return -EINVAL;
dev->mtu = new_mtu;
void (*init_sel_class)(struct batadv_priv *bat_priv);
/**
- * @store_sel_class: parse and stores a new GW selection class
- * (optional)
+ * @sel_class_max: maximum allowed GW selection class
*/
- ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff,
- size_t count);
+ u32 sel_class_max;
+
/**
* @get_best_gw_node: select the best GW from the list of available
* nodes (optional)
static void skb_extensions_init(void) {}
#endif
+/* The SKB kmem_cache slab is critical for network performance. Never
+ * merge/alias the slab with similar sized objects. This avoids fragmentation
+ * that hurts performance of kmem_cache_{alloc,free}_bulk APIs.
+ */
+#ifndef CONFIG_SLUB_TINY
+#define FLAG_SKB_NO_MERGE SLAB_NO_MERGE
+#else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */
+#define FLAG_SKB_NO_MERGE 0
+#endif
+
void __init skb_init(void)
{
skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
sizeof(struct sk_buff),
0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|
+ FLAG_SKB_NO_MERGE,
offsetof(struct sk_buff, cb),
sizeof_field(struct sk_buff, cb),
NULL);
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
- if (sk_under_memory_pressure(sk) &&
+ if (sk_under_global_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
}
switch (skb->protocol) {
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
case htons(ETH_P_IPV6):
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
default:
goto tx_err;
tcp_stream_is_thin(tp) &&
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
- icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
+ icsk->icsk_rto = clamp(__tcp_set_rto(tp),
+ tcp_rto_min(sk),
+ TCP_RTO_MAX);
} else if (sk->sk_state != TCP_SYN_SENT ||
icsk->icsk_backoff >
READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
default n
config IPV6_VTI
-tristate "Virtual (secure) IPv6: tunneling"
+ tristate "Virtual (secure) IPv6: tunneling"
select IPV6_TUNNEL
select NET_IP_TUNNEL
select XFRM
vti6_addr_conflict(t, ipv6_hdr(skb)))
goto tx_err;
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
default:
goto tx_err;
if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
- if ((xfilter->sadb_x_filter_splen >=
+ if ((xfilter->sadb_x_filter_splen >
(sizeof(xfrm_address_t) << 3)) ||
- (xfilter->sadb_x_filter_dplen >=
+ (xfilter->sadb_x_filter_dplen >
(sizeof(xfrm_address_t) << 3))) {
mutex_unlock(&pfk->dump_lock);
return -EINVAL;
return NULL;
}
+
+BTF_SET8_START(bpf_mptcp_fmodret_ids)
+BTF_ID_FLAGS(func, update_socket_protocol)
+BTF_SET8_END(bpf_mptcp_fmodret_ids)
+
+static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = {
+ .owner = THIS_MODULE,
+ .set = &bpf_mptcp_fmodret_ids,
+};
+
+static int __init bpf_mptcp_kfunc_init(void)
+{
+ return register_btf_fmodret_id_set(&bpf_mptcp_fmodret_set);
+}
+late_initcall(bpf_mptcp_kfunc_init);
proc_do_sync_threshold(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
+ struct netns_ipvs *ipvs = table->extra2;
int *valp = table->data;
int val[2];
int rc;
.mode = table->mode,
};
+ mutex_lock(&ipvs->sync_mutex);
memcpy(val, valp, sizeof(val));
rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write) {
else
memcpy(valp, val, sizeof(val));
}
+ mutex_unlock(&ipvs->sync_mutex);
return rc;
}
ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
tbl[idx].data = &ipvs->sysctl_sync_threshold;
+ tbl[idx].extra2 = ipvs;
tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
[SCTP_CONNTRACK_ESTABLISHED] = 210 SECS,
- [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000,
- [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000,
+ [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS,
+ [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS,
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
};
{
/* ORIGINAL */
/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
-/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW},
/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},
ret = __nft_set_catchall_flush(ctx, set, &elem);
if (ret < 0)
break;
+ nft_set_elem_change_active(ctx->net, set, ext);
}
return ret;
if (!trans)
return NULL;
+ trans->net = maybe_get_net(net);
+ if (!trans->net) {
+ kfree(trans);
+ return NULL;
+ }
+
refcount_inc(&set->refs);
trans->set = set;
- trans->net = get_net(net);
trans->seq = gc_seq;
return trans;
}
}
+static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net)
+{
+ unsigned int gc_seq;
+
+ /* Bump gc counter, it becomes odd, this is the busy mark. */
+ gc_seq = READ_ONCE(nft_net->gc_seq);
+ WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+
+ return gc_seq;
+}
+
+static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq)
+{
+ WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+}
+
static int nf_tables_commit(struct net *net, struct sk_buff *skb)
{
struct nftables_pernet *nft_net = nft_pernet(net);
WRITE_ONCE(nft_net->base_seq, base_seq);
- /* Bump gc counter, it becomes odd, this is the busy mark. */
- gc_seq = READ_ONCE(nft_net->gc_seq);
- WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+ gc_seq = nft_gc_seq_begin(nft_net);
/* step 3. Start new generation, rules_gen_X now in use. */
net->nft.gencursor = nft_gencursor_next(net);
nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
nf_tables_commit_audit_log(&adl, nft_net->base_seq);
- WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+ nft_gc_seq_end(nft_net, gc_seq);
nf_tables_commit_release(net);
return 0;
struct net *net = n->net;
unsigned int deleted;
bool restart = false;
+ unsigned int gc_seq;
if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER)
return NOTIFY_DONE;
nft_net = nft_pernet(net);
deleted = 0;
mutex_lock(&nft_net->commit_mutex);
+
+ gc_seq = nft_gc_seq_begin(nft_net);
+
if (!list_empty(&nf_tables_destroy_list))
rcu_barrier();
again:
if (restart)
goto again;
}
+ nft_gc_seq_end(nft_net, gc_seq);
+
mutex_unlock(&nft_net->commit_mutex);
return NOTIFY_DONE;
static void __net_exit nf_tables_exit_net(struct net *net)
{
struct nftables_pernet *nft_net = nft_pernet(net);
+ unsigned int gc_seq;
mutex_lock(&nft_net->commit_mutex);
+
+ gc_seq = nft_gc_seq_begin(nft_net);
+
if (!list_empty(&nft_net->commit_list) ||
!list_empty(&nft_net->module_list))
__nf_tables_abort(net, NFNL_ABORT_NONE);
+
__nft_release_tables(net);
+
+ nft_gc_seq_end(nft_net, gc_seq);
+
mutex_unlock(&nft_net->commit_mutex);
WARN_ON_ONCE(!list_empty(&nft_net->tables));
WARN_ON_ONCE(!list_empty(&nft_net->module_list));
if (IS_ERR(set))
return PTR_ERR(set);
+ if (set->flags & NFT_SET_OBJECT)
+ return -EOPNOTSUPP;
+
if (set->ops->update == NULL)
return -EOPNOTSUPP;
goto out;
if (last) {
+ if (nft_set_elem_expired(&f->mt[b].e->ext))
+ goto next_match;
if ((genmask &&
!nft_set_elem_active(&f->mt[b].e->ext, genmask)))
goto next_match;
static void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem, unsigned int flags)
{
- struct nft_pipapo_elem *ret;
-
- ret = pipapo_get(net, set, (const u8 *)elem->key.val.data,
+ return pipapo_get(net, set, (const u8 *)elem->key.val.data,
nft_genmask_cur(net));
- if (IS_ERR(ret))
- return ret;
-
- if (nft_set_elem_expired(&ret->ext))
- return ERR_PTR(-ENOENT);
-
- return ret;
}
/**
/**
* pipapo_gc() - Drop expired entries from set, destroy start and end elements
- * @set: nftables API set representation
+ * @_set: nftables API set representation
* @m: Matching data
*/
static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m)
priv->clone = new_clone;
}
+static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set)
+{
+#ifdef CONFIG_PROVE_LOCKING
+ const struct net *net = read_pnet(&set->net);
+
+ return lockdep_is_held(&nft_pernet(net)->commit_mutex);
+#else
+ return true;
+#endif
+}
+
static void nft_pipapo_abort(const struct nft_set *set)
{
struct nft_pipapo *priv = nft_set_priv(set);
if (!priv->dirty)
return;
- m = rcu_dereference(priv->match);
+ m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set));
new_clone = pipapo_clone(m);
if (IS_ERR(new_clone))
const struct nft_set *set,
const struct nft_set_elem *elem)
{
- struct nft_pipapo_elem *e;
-
- e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0);
- if (IS_ERR(e))
- return;
+ struct nft_pipapo_elem *e = elem->priv;
nft_set_elem_change_active(net, set, &e->ext);
}
data = (const u8 *)nft_set_ext_key(&e->ext);
- e = pipapo_get(net, set, data, 0);
- if (IS_ERR(e))
- return;
-
while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
const u8 *match_start, *match_end;
parms.port_no = OVSP_LOCAL;
parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX]
- ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0;
+ ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0;
/* So far only local changes have been made, now need the lock. */
ovs_lock();
[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
[OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0,
PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
- [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 },
+ [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0),
};
static const struct genl_small_ops dp_datapath_genl_ops[] = {
parms.port_no = port_no;
parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID];
parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX]
- ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
+ ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
vport = new_vport(&parms);
err = PTR_ERR(vport);
[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC },
[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
- [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0),
[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
[OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED },
};
u32 rho;
} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
+ struct prng {
+ u64 seed;
+ struct rnd_state prng_state;
+ } prng;
+
struct disttable *delay_dist;
enum {
* Next number depends on last value.
* rho is scaled to avoid floating point.
*/
-static u32 get_crandom(struct crndstate *state)
+static u32 get_crandom(struct crndstate *state, struct prng *p)
{
u64 value, rho;
unsigned long answer;
+ struct rnd_state *s = &p->prng_state;
if (!state || state->rho == 0) /* no correlation */
- return get_random_u32();
+ return prandom_u32_state(s);
- value = get_random_u32();
+ value = prandom_u32_state(s);
rho = (u64)state->rho + 1;
answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
state->last = answer;
static bool loss_4state(struct netem_sched_data *q)
{
struct clgstate *clg = &q->clg;
- u32 rnd = get_random_u32();
+ u32 rnd = prandom_u32_state(&q->prng.prng_state);
/*
* Makes a comparison between rnd and the transition
static bool loss_gilb_ell(struct netem_sched_data *q)
{
struct clgstate *clg = &q->clg;
+ struct rnd_state *s = &q->prng.prng_state;
switch (clg->state) {
case GOOD_STATE:
- if (get_random_u32() < clg->a1)
+ if (prandom_u32_state(s) < clg->a1)
clg->state = BAD_STATE;
- if (get_random_u32() < clg->a4)
+ if (prandom_u32_state(s) < clg->a4)
return true;
break;
case BAD_STATE:
- if (get_random_u32() < clg->a2)
+ if (prandom_u32_state(s) < clg->a2)
clg->state = GOOD_STATE;
- if (get_random_u32() > clg->a3)
+ if (prandom_u32_state(s) > clg->a3)
return true;
}
switch (q->loss_model) {
case CLG_RANDOM:
/* Random packet drop 0 => none, ~0 => all */
- return q->loss && q->loss >= get_crandom(&q->loss_cor);
+ return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng);
case CLG_4_STATES:
/* 4state loss model algorithm (used also for GI model)
*/
static s64 tabledist(s64 mu, s32 sigma,
struct crndstate *state,
+ struct prng *prng,
const struct disttable *dist)
{
s64 x;
if (sigma == 0)
return mu;
- rnd = get_crandom(state);
+ rnd = get_crandom(state, prng);
/* default uniform distribution */
if (dist == NULL)
skb->prev = NULL;
/* Random duplication */
- if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng))
++count;
/* Drop packet? */
* If packet is going to be hardware checksummed, then
* do it now in software before we mangle it.
*/
- if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) {
if (skb_is_gso(skb)) {
skb = netem_segment(skb, sch, to_free);
if (!skb)
cb = netem_skb_cb(skb);
if (q->gap == 0 || /* not doing reordering */
q->counter < q->gap - 1 || /* inside last reordering gap */
- q->reorder < get_crandom(&q->reorder_cor)) {
+ q->reorder < get_crandom(&q->reorder_cor, &q->prng)) {
u64 now;
s64 delay;
delay = tabledist(q->latency, q->jitter,
- &q->delay_cor, q->delay_dist);
+ &q->delay_cor, &q->prng, q->delay_dist);
now = ktime_get_ns();
else
next_delay = tabledist(q->slot_config.dist_delay,
(s32)(q->slot_config.dist_jitter),
- NULL, q->slot_dist);
+ NULL, &q->prng, q->slot_dist);
q->slot.slot_next = now + next_delay;
q->slot.packets_left = q->slot_config.max_packets;
[TCA_NETEM_LATENCY64] = { .type = NLA_S64 },
[TCA_NETEM_JITTER64] = { .type = NLA_S64 },
[TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) },
+ [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 },
};
static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
/* capping jitter to the range acceptable by tabledist() */
q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+ if (tb[TCA_NETEM_PRNG_SEED])
+ q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]);
+ else
+ q->prng.seed = get_random_u64();
+ prandom_seed_state(&q->prng.prng_state, q->prng.seed);
+
unlock:
sch_tree_unlock(sch);
goto nla_put_failure;
}
+ if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed,
+ TCA_NETEM_PAD))
+ goto nla_put_failure;
+
return nla_nest_end(skb, nla);
nla_put_failure:
return sock_alloc_file(sock, flags, NULL);
}
+/* A hook for bpf progs to attach to and update socket protocol.
+ *
+ * A static noinline declaration here could cause the compiler to
+ * optimize away the function. A global noinline declaration will
+ * keep the definition, but may optimize away the callsite.
+ * Therefore, __weak is needed to ensure that the call is still
+ * emitted, by telling the compiler that we don't know what the
+ * function might eventually be.
+ *
+ * __diag_* below are needed to dismiss the missing prototype warning.
+ */
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+ "A fmod_ret entry point for BPF programs");
+
+__weak noinline int update_socket_protocol(int family, int type, int protocol)
+{
+ return protocol;
+}
+
+__diag_pop();
+
int __sys_socket(int family, int type, int protocol)
{
struct socket *sock;
int flags;
- sock = __sys_socket_create(family, type, protocol);
+ sock = __sys_socket_create(family, type,
+ update_socket_protocol(family, type, protocol));
if (IS_ERR(sock))
return PTR_ERR(sock);
if (ret != head->iov_len)
goto out;
+ if (xdr_buf_pagecount(xdr))
+ xdr->bvec[0].bv_offset = offset_in_page(xdr->page_base);
+
msg.msg_flags = MSG_SPLICE_PAGES;
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
xdr_buf_pagecount(xdr), xdr->page_len);
[XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) },
[XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) },
- [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) },
+ [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) },
[XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) },
[XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) },
[XFRMA_REPLAY_THRESH] = { .type = NLA_U32 },
int optlen = 0;
int err = -EINVAL;
+ skb->protocol = htons(ETH_P_IP);
+
if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
struct ip_beet_phdr *ph;
int phlen;
{
int err = -EINVAL;
+ skb->protocol = htons(ETH_P_IP);
+
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
{
int err = -EINVAL;
+ skb->protocol = htons(ETH_P_IPV6);
+
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
int size = sizeof(struct ipv6hdr);
int err;
+ skb->protocol = htons(ETH_P_IPV6);
+
err = skb_cow_head(skb, size + skb->mac_len);
if (err)
goto out;
return xfrm6_remove_tunnel_encap(x, skb);
break;
}
+ return -EINVAL;
}
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
}
- switch (XFRM_MODE_SKB_CB(skb)->protocol) {
- case IPPROTO_IPIP:
- case IPPROTO_BEETPH:
- skb->protocol = htons(ETH_P_IP);
- break;
- case IPPROTO_IPV6:
- skb->protocol = htons(ETH_P_IPV6);
- break;
- default:
- WARN_ON_ONCE(1);
- break;
- }
-
return xfrm_inner_mode_encap_remove(x, skb);
}
switch (skb->protocol) {
case htons(ETH_P_IPV6):
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
if (!dst) {
fl.u.ip6.flowi6_oif = dev->ifindex;
fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
}
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
if (!dst) {
struct rtable *rt;
struct xfrm_dev_offload *xso = &x->xso;
if (xso->type == XFRM_DEV_OFFLOAD_PACKET) {
- xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
- xso->dir = 0;
- netdev_put(xso->dev, &xso->dev_tracker);
- xso->dev = NULL;
- xso->real_dev = NULL;
- xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+ xfrm_dev_state_delete(x);
+ xfrm_dev_state_free(x);
}
#endif
x->km.state = XFRM_STATE_DEAD;
struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH];
- if (re) {
+ if (re && x->replay_esn && x->preplay_esn) {
struct xfrm_replay_state_esn *replay_esn;
replay_esn = nla_data(re);
memcpy(x->replay_esn, replay_esn,
sizeof(*filter), GFP_KERNEL);
if (filter == NULL)
return -ENOMEM;
+
+ /* see addr_match(), (prefix length >> 5) << 2
+ * will be used to compare xfrm_address_t
+ */
+ if (filter->splen > (sizeof(xfrm_address_t) << 3) ||
+ filter->dplen > (sizeof(xfrm_address_t) << 3)) {
+ kfree(filter);
+ return -EINVAL;
+ }
}
if (attrs[XFRMA_PROTO])
NETLINK_CB(skb).portid);
}
} else {
+ xfrm_dev_policy_delete(xp);
xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
if (err != 0)
[XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) },
[XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) },
- [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) },
+ [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) },
[XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) },
[XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) },
[XFRMA_REPLAY_THRESH] = { .type = NLA_U32 },
[XFRMA_SET_MARK] = { .type = NLA_U32 },
[XFRMA_SET_MARK_MASK] = { .type = NLA_U32 },
[XFRMA_IF_ID] = { .type = NLA_U32 },
+ [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 },
};
EXPORT_SYMBOL_GPL(xfrma_policy);
ssize_t readlen;
struct sym_entry *sym;
+ errno = 0;
readlen = getline(buf, buf_len, in);
if (readlen < 0) {
if (errno) {
jsonw_uint_field(wtr, "attach_type", attach_type);
}
+static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr)
+{
+ char devname[IF_NAMESIZE] = "(unknown)";
+
+ if (ifindex)
+ if_indextoname(ifindex, devname);
+ else
+ snprintf(devname, sizeof(devname), "(detached)");
+ jsonw_string_field(wtr, "devname", devname);
+ jsonw_uint_field(wtr, "ifindex", ifindex);
+}
+
static bool is_iter_map_target(const char *target_name)
{
return strcmp(target_name, "bpf_map_elem") == 0 ||
case BPF_LINK_TYPE_NETFILTER:
netfilter_dump_json(info, json_wtr);
break;
+ case BPF_LINK_TYPE_TCX:
+ show_link_ifindex_json(info->tcx.ifindex, json_wtr);
+ show_link_attach_type_json(info->tcx.attach_type, json_wtr);
+ break;
+ case BPF_LINK_TYPE_XDP:
+ show_link_ifindex_json(info->xdp.ifindex, json_wtr);
+ break;
case BPF_LINK_TYPE_STRUCT_OPS:
jsonw_uint_field(json_wtr, "map_id",
info->struct_ops.map_id);
printf("attach_type %u ", attach_type);
}
+static void show_link_ifindex_plain(__u32 ifindex)
+{
+ char devname[IF_NAMESIZE * 2] = "(unknown)";
+ char tmpname[IF_NAMESIZE];
+ char *ret = NULL;
+
+ if (ifindex)
+ ret = if_indextoname(ifindex, tmpname);
+ else
+ snprintf(devname, sizeof(devname), "(detached)");
+ if (ret)
+ snprintf(devname, sizeof(devname), "%s(%d)",
+ tmpname, ifindex);
+ printf("ifindex %s ", devname);
+}
+
static void show_iter_plain(struct bpf_link_info *info)
{
const char *target_name = u64_to_ptr(info->iter.target_name);
case BPF_LINK_TYPE_NETFILTER:
netfilter_dump_plain(info);
break;
+ case BPF_LINK_TYPE_TCX:
+ printf("\n\t");
+ show_link_ifindex_plain(info->tcx.ifindex);
+ show_link_attach_type_plain(info->tcx.attach_type);
+ break;
+ case BPF_LINK_TYPE_XDP:
+ printf("\n\t");
+ show_link_ifindex_plain(info->xdp.ifindex);
+ break;
case BPF_LINK_TYPE_KPROBE_MULTI:
show_kprobe_multi_plain(info);
break;
{
fprintf(stderr,
"Usage: %1$s %2$s { show | list }\n"
- " %1$s %2$s help }\n"
+ " %1$s %2$s help\n"
"\n"
" " HELP_SPEC_OPTIONS " }\n"
"",
clean:
rm -f $(ALL_PROGRAMS)
rm -rf $(OUTPUT)include/linux/counter.h
- rmdir -p $(OUTPUT)include/linux
+ rm -df $(OUTPUT)include/linux
+ rm -df $(OUTPUT)include
find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
install: $(ALL_PROGRAMS)
return -ENAMETOOLONG;
/* gzopen also accepts uncompressed files. */
- file = gzopen(buf, "r");
+ file = gzopen(buf, "re");
if (!file)
- file = gzopen("/proc/config.gz", "r");
+ file = gzopen("/proc/config.gz", "re");
if (!file) {
pr_warn("failed to open system Kconfig\n");
nr_threads = 2;
pthread_barrier_init(&worker_barrier, NULL, nr_threads);
- threads = malloc(nr_threads * sizeof(pthread_t *));
+ threads = malloc(nr_threads * sizeof(*threads));
for (i = 0; i < nr_threads; i++) {
arg = i;
module_attach # prog 'kprobe_multi': failed to auto-attach: -95
fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
+fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95
+fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95
+fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95
set -eufo pipefail
-for i in base kprobe kretprobe rawtp fentry fexit fmodret
+for i in base kprobe kretprobe rawtp fentry fexit
do
summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
printf "%-10s: %s\n" $i "$summary"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/limits.h>
+#include <test_progs.h>
+#include "trace_helpers.h"
+#include "test_fill_link_info.skel.h"
+
+#define TP_CAT "sched"
+#define TP_NAME "sched_switch"
+
+static const char *kmulti_syms[] = {
+ "bpf_fentry_test2",
+ "bpf_fentry_test1",
+ "bpf_fentry_test3",
+};
+#define KMULTI_CNT ARRAY_SIZE(kmulti_syms)
+static __u64 kmulti_addrs[KMULTI_CNT];
+
+#define KPROBE_FUNC "bpf_fentry_test1"
+static __u64 kprobe_addr;
+
+#define UPROBE_FILE "/proc/self/exe"
+static ssize_t uprobe_offset;
+/* uprobe attach point */
+static noinline void uprobe_func(void)
+{
+ asm volatile ("");
+}
+
+static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr,
+ ssize_t offset, ssize_t entry_offset)
+{
+ struct bpf_link_info info;
+ __u32 len = sizeof(info);
+ char buf[PATH_MAX];
+ int err;
+
+ memset(&info, 0, sizeof(info));
+ buf[0] = '\0';
+
+again:
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type"))
+ return -1;
+ if (!ASSERT_EQ(info.perf_event.type, type, "perf_type_match"))
+ return -1;
+
+ switch (info.perf_event.type) {
+ case BPF_PERF_EVENT_KPROBE:
+ case BPF_PERF_EVENT_KRETPROBE:
+ ASSERT_EQ(info.perf_event.kprobe.offset, offset, "kprobe_offset");
+
+ /* In case kernel.kptr_restrict is not permitted or MAX_SYMS is reached */
+ if (addr)
+ ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset,
+ "kprobe_addr");
+
+ if (!info.perf_event.kprobe.func_name) {
+ ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len");
+ info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
+ info.perf_event.kprobe.name_len = sizeof(buf);
+ goto again;
+ }
+
+ err = strncmp(u64_to_ptr(info.perf_event.kprobe.func_name), KPROBE_FUNC,
+ strlen(KPROBE_FUNC));
+ ASSERT_EQ(err, 0, "cmp_kprobe_func_name");
+ break;
+ case BPF_PERF_EVENT_TRACEPOINT:
+ if (!info.perf_event.tracepoint.tp_name) {
+ ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len");
+ info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf);
+ info.perf_event.tracepoint.name_len = sizeof(buf);
+ goto again;
+ }
+
+ err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME,
+ strlen(TP_NAME));
+ ASSERT_EQ(err, 0, "cmp_tp_name");
+ break;
+ case BPF_PERF_EVENT_UPROBE:
+ case BPF_PERF_EVENT_URETPROBE:
+ ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset");
+
+ if (!info.perf_event.uprobe.file_name) {
+ ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len");
+ info.perf_event.uprobe.file_name = ptr_to_u64(&buf);
+ info.perf_event.uprobe.name_len = sizeof(buf);
+ goto again;
+ }
+
+ err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE,
+ strlen(UPROBE_FILE));
+ ASSERT_EQ(err, 0, "cmp_file_name");
+ break;
+ default:
+ err = -1;
+ break;
+ }
+ return err;
+}
+
+static void kprobe_fill_invalid_user_buffer(int fd)
+{
+ struct bpf_link_info info;
+ __u32 len = sizeof(info);
+ int err;
+
+ memset(&info, 0, sizeof(info));
+
+ info.perf_event.kprobe.func_name = 0x1; /* invalid address */
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EINVAL, "invalid_buff_and_len");
+
+ info.perf_event.kprobe.name_len = 64;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EFAULT, "invalid_buff");
+
+ info.perf_event.kprobe.func_name = 0;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EINVAL, "invalid_len");
+
+ ASSERT_EQ(info.perf_event.kprobe.addr, 0, "func_addr");
+ ASSERT_EQ(info.perf_event.kprobe.offset, 0, "func_offset");
+ ASSERT_EQ(info.perf_event.type, 0, "type");
+}
+
+static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
+ enum bpf_perf_event_type type,
+ bool invalid)
+{
+ DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts,
+ .attach_mode = PROBE_ATTACH_MODE_LINK,
+ .retprobe = type == BPF_PERF_EVENT_KRETPROBE,
+ );
+ ssize_t entry_offset = 0;
+ int link_fd, err;
+
+ skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run,
+ KPROBE_FUNC, &opts);
+ if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe"))
+ return;
+
+ link_fd = bpf_link__fd(skel->links.kprobe_run);
+ if (!invalid) {
+ /* See also arch_adjust_kprobe_addr(). */
+ if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
+ entry_offset = 4;
+ err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset);
+ ASSERT_OK(err, "verify_perf_link_info");
+ } else {
+ kprobe_fill_invalid_user_buffer(link_fd);
+ }
+ bpf_link__detach(skel->links.kprobe_run);
+}
+
+static void test_tp_fill_link_info(struct test_fill_link_info *skel)
+{
+ int link_fd, err;
+
+ skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+ if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp"))
+ return;
+
+ link_fd = bpf_link__fd(skel->links.tp_run);
+ err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
+ ASSERT_OK(err, "verify_perf_link_info");
+ bpf_link__detach(skel->links.tp_run);
+}
+
+static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
+ enum bpf_perf_event_type type)
+{
+ int link_fd, err;
+
+ skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run,
+ type == BPF_PERF_EVENT_URETPROBE,
+ 0, /* self pid */
+ UPROBE_FILE, uprobe_offset);
+ if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe"))
+ return;
+
+ link_fd = bpf_link__fd(skel->links.uprobe_run);
+ err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
+ ASSERT_OK(err, "verify_perf_link_info");
+ bpf_link__detach(skel->links.uprobe_run);
+}
+
+static int verify_kmulti_link_info(int fd, bool retprobe)
+{
+ struct bpf_link_info info;
+ __u32 len = sizeof(info);
+ __u64 addrs[KMULTI_CNT];
+ int flags, i, err;
+
+ memset(&info, 0, sizeof(info));
+
+again:
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_KPROBE_MULTI, "kmulti_type"))
+ return -1;
+
+ ASSERT_EQ(info.kprobe_multi.count, KMULTI_CNT, "func_cnt");
+ flags = info.kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN;
+ if (!retprobe)
+ ASSERT_EQ(flags, 0, "kmulti_flags");
+ else
+ ASSERT_NEQ(flags, 0, "kretmulti_flags");
+
+ if (!info.kprobe_multi.addrs) {
+ info.kprobe_multi.addrs = ptr_to_u64(addrs);
+ goto again;
+ }
+ for (i = 0; i < KMULTI_CNT; i++)
+ ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+ return 0;
+}
+
+static void verify_kmulti_invalid_user_buffer(int fd)
+{
+ struct bpf_link_info info;
+ __u32 len = sizeof(info);
+ __u64 addrs[KMULTI_CNT];
+ int err, i;
+
+ memset(&info, 0, sizeof(info));
+
+ info.kprobe_multi.count = KMULTI_CNT;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EINVAL, "no_addr");
+
+ info.kprobe_multi.addrs = ptr_to_u64(addrs);
+ info.kprobe_multi.count = 0;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EINVAL, "no_cnt");
+
+ for (i = 0; i < KMULTI_CNT; i++)
+ addrs[i] = 0;
+ info.kprobe_multi.count = KMULTI_CNT - 1;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -ENOSPC, "smaller_cnt");
+ for (i = 0; i < KMULTI_CNT - 1; i++)
+ ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+ ASSERT_EQ(addrs[i], 0, "kmulti_addrs");
+
+ for (i = 0; i < KMULTI_CNT; i++)
+ addrs[i] = 0;
+ info.kprobe_multi.count = KMULTI_CNT + 1;
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, 0, "bigger_cnt");
+ for (i = 0; i < KMULTI_CNT; i++)
+ ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+
+ info.kprobe_multi.count = KMULTI_CNT;
+ info.kprobe_multi.addrs = 0x1; /* invalid addr */
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ ASSERT_EQ(err, -EFAULT, "invalid_buff");
+}
+
+static int symbols_cmp_r(const void *a, const void *b)
+{
+ const char **str_a = (const char **) a;
+ const char **str_b = (const char **) b;
+
+ return strcmp(*str_a, *str_b);
+}
+
+static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+ bool retprobe, bool invalid)
+{
+ LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+ int link_fd, err;
+
+ opts.syms = kmulti_syms;
+ opts.cnt = KMULTI_CNT;
+ opts.retprobe = retprobe;
+ skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run,
+ NULL, &opts);
+ if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi"))
+ return;
+
+ link_fd = bpf_link__fd(skel->links.kmulti_run);
+ if (!invalid) {
+ err = verify_kmulti_link_info(link_fd, retprobe);
+ ASSERT_OK(err, "verify_kmulti_link_info");
+ } else {
+ verify_kmulti_invalid_user_buffer(link_fd);
+ }
+ bpf_link__detach(skel->links.kmulti_run);
+}
+
+void test_fill_link_info(void)
+{
+ struct test_fill_link_info *skel;
+ int i;
+
+ skel = test_fill_link_info__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ /* load kallsyms to compare the addr */
+ if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+ goto cleanup;
+
+ kprobe_addr = ksym_get_addr(KPROBE_FUNC);
+ if (test__start_subtest("kprobe_link_info"))
+ test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, false);
+ if (test__start_subtest("kretprobe_link_info"))
+ test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KRETPROBE, false);
+ if (test__start_subtest("kprobe_invalid_ubuff"))
+ test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true);
+ if (test__start_subtest("tracepoint_link_info"))
+ test_tp_fill_link_info(skel);
+
+ uprobe_offset = get_uprobe_offset(&uprobe_func);
+ if (test__start_subtest("uprobe_link_info"))
+ test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_UPROBE);
+ if (test__start_subtest("uretprobe_link_info"))
+ test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_URETPROBE);
+
+ qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r);
+ for (i = 0; i < KMULTI_CNT; i++)
+ kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]);
+ if (test__start_subtest("kprobe_multi_link_info"))
+ test_kprobe_multi_fill_link_info(skel, false, false);
+ if (test__start_subtest("kretprobe_multi_link_info"))
+ test_kprobe_multi_fill_link_info(skel, true, false);
+ if (test__start_subtest("kprobe_multi_invalid_ubuff"))
+ test_kprobe_multi_fill_link_info(skel, true, true);
+
+cleanup:
+ test_fill_link_info__destroy(skel);
+}
case tc_test:
topts.data_in = &pkt_v4;
topts.data_size_in = sizeof(pkt_v4);
- break;
topts.repeat = 1;
+ break;
}
skel = kfunc_call_fail__open_opts(&opts);
/* Copyright (c) 2020, Tessares SA. */
/* Copyright (c) 2022, SUSE. */
+#include <linux/const.h>
+#include <netinet/in.h>
#include <test_progs.h>
#include "cgroup_helpers.h"
#include "network_helpers.h"
#include "mptcp_sock.skel.h"
+#include "mptcpify.skel.h"
#define NS_TEST "mptcp_ns"
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+#ifndef MPTCP_INFO
+#define MPTCP_INFO 1
+#endif
+#ifndef MPTCP_INFO_FLAG_FALLBACK
+#define MPTCP_INFO_FLAG_FALLBACK _BITUL(0)
+#endif
+#ifndef MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1)
+#endif
+
#ifndef TCP_CA_NAME_MAX
#define TCP_CA_NAME_MAX 16
#endif
+struct __mptcp_info {
+ __u8 mptcpi_subflows;
+ __u8 mptcpi_add_addr_signal;
+ __u8 mptcpi_add_addr_accepted;
+ __u8 mptcpi_subflows_max;
+ __u8 mptcpi_add_addr_signal_max;
+ __u8 mptcpi_add_addr_accepted_max;
+ __u32 mptcpi_flags;
+ __u32 mptcpi_token;
+ __u64 mptcpi_write_seq;
+ __u64 mptcpi_snd_una;
+ __u64 mptcpi_rcv_nxt;
+ __u8 mptcpi_local_addr_used;
+ __u8 mptcpi_local_addr_max;
+ __u8 mptcpi_csum_enabled;
+ __u32 mptcpi_retransmits;
+ __u64 mptcpi_bytes_retrans;
+ __u64 mptcpi_bytes_sent;
+ __u64 mptcpi_bytes_received;
+ __u64 mptcpi_bytes_acked;
+};
+
struct mptcp_storage {
__u32 invoked;
__u32 is_mptcp;
char ca_name[TCP_CA_NAME_MAX];
};
+static struct nstoken *create_netns(void)
+{
+ SYS(fail, "ip netns add %s", NS_TEST);
+ SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+ return open_netns(NS_TEST);
+fail:
+ return NULL;
+}
+
+static void cleanup_netns(struct nstoken *nstoken)
+{
+ if (nstoken)
+ close_netns(nstoken);
+
+ SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST);
+}
+
static int verify_tsk(int map_fd, int client_fd)
{
int err, cfd = client_fd;
sock_skel = mptcp_sock__open_and_load();
if (!ASSERT_OK_PTR(sock_skel, "skel_open_load"))
- return -EIO;
+ return libbpf_get_error(sock_skel);
err = mptcp_sock__attach(sock_skel);
if (!ASSERT_OK(err, "skel_attach"))
goto out;
prog_fd = bpf_program__fd(sock_skel->progs._sockops);
- if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) {
- err = -EIO;
- goto out;
- }
-
map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map);
- if (!ASSERT_GE(map_fd, 0, "bpf_map__fd")) {
- err = -EIO;
- goto out;
- }
-
err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
if (!ASSERT_OK(err, "bpf_prog_attach"))
goto out;
if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
return;
- SYS(fail, "ip netns add %s", NS_TEST);
- SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
-
- nstoken = open_netns(NS_TEST);
- if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+ nstoken = create_netns();
+ if (!ASSERT_OK_PTR(nstoken, "create_netns"))
goto fail;
/* without MPTCP */
close(server_fd);
fail:
- if (nstoken)
- close_netns(nstoken);
+ cleanup_netns(nstoken);
+ close(cgroup_fd);
+}
- SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+static void send_byte(int fd)
+{
+ char b = 0x55;
+
+ ASSERT_EQ(write(fd, &b, sizeof(b)), 1, "send single byte");
+}
+
+static int verify_mptcpify(int server_fd, int client_fd)
+{
+ struct __mptcp_info info;
+ socklen_t optlen;
+ int protocol;
+ int err = 0;
+
+ optlen = sizeof(protocol);
+ if (!ASSERT_OK(getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen),
+ "getsockopt(SOL_PROTOCOL)"))
+ return -1;
+
+ if (!ASSERT_EQ(protocol, IPPROTO_MPTCP, "protocol isn't MPTCP"))
+ err++;
+ optlen = sizeof(info);
+ if (!ASSERT_OK(getsockopt(client_fd, SOL_MPTCP, MPTCP_INFO, &info, &optlen),
+ "getsockopt(MPTCP_INFO)"))
+ return -1;
+
+ if (!ASSERT_GE(info.mptcpi_flags, 0, "unexpected mptcpi_flags"))
+ err++;
+ if (!ASSERT_FALSE(info.mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK,
+ "MPTCP fallback"))
+ err++;
+ if (!ASSERT_TRUE(info.mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED,
+ "no remote key received"))
+ err++;
+
+ return err;
+}
+
+static int run_mptcpify(int cgroup_fd)
+{
+ int server_fd, client_fd, err = 0;
+ struct mptcpify *mptcpify_skel;
+
+ mptcpify_skel = mptcpify__open_and_load();
+ if (!ASSERT_OK_PTR(mptcpify_skel, "skel_open_load"))
+ return libbpf_get_error(mptcpify_skel);
+
+ err = mptcpify__attach(mptcpify_skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto out;
+
+ /* without MPTCP */
+ server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+ if (!ASSERT_GE(server_fd, 0, "start_server")) {
+ err = -EIO;
+ goto out;
+ }
+
+ client_fd = connect_to_fd(server_fd, 0);
+ if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
+ err = -EIO;
+ goto close_server;
+ }
+
+ send_byte(client_fd);
+
+ err = verify_mptcpify(server_fd, client_fd);
+
+ close(client_fd);
+close_server:
+ close(server_fd);
+out:
+ mptcpify__destroy(mptcpify_skel);
+ return err;
+}
+
+static void test_mptcpify(void)
+{
+ struct nstoken *nstoken = NULL;
+ int cgroup_fd;
+
+ cgroup_fd = test__join_cgroup("/mptcpify");
+ if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
+ return;
+
+ nstoken = create_netns();
+ if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+ goto fail;
+
+ ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify");
+
+fail:
+ cleanup_netns(nstoken);
close(cgroup_fd);
}
{
if (test__start_subtest("base"))
test_base();
+ if (test__start_subtest("mptcpify"))
+ test_mptcpify();
}
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2023 Isovalent */
#include <uapi/linux/if_link.h>
+#include <uapi/linux/pkt_sched.h>
#include <net/if.h>
#include <test_progs.h>
test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
}
+
+static void test_tc_chain_mixed(int target)
+{
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+ LIBBPF_OPTS(bpf_tcx_opts, optl);
+ struct test_tc_link *skel;
+ struct bpf_link *link;
+ __u32 pid1, pid2, pid3;
+ int err;
+
+ skel = test_tc_link__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+ 0, "tc4_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc5, target),
+ 0, "tc5_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc6, target),
+ 0, "tc6_attach_type");
+
+ err = test_tc_link__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+ pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc5));
+ pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc6));
+
+ ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+ ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+ assert_mprog_count(target, 0);
+
+ tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+ BPF_TC_INGRESS : BPF_TC_EGRESS;
+ err = bpf_tc_hook_create(&tc_hook);
+ err = err == -EEXIST ? 0 : err;
+ if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+ goto cleanup;
+
+ tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+ err = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(err, "bpf_tc_attach"))
+ goto cleanup;
+
+ link = bpf_program__attach_tcx(skel->progs.tc6, loopback, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc6 = link;
+
+ assert_mprog_count(target, 1);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+ skel->bss->seen_tc4 = false;
+ skel->bss->seen_tc5 = false;
+ skel->bss->seen_tc6 = false;
+
+ err = bpf_link__update_program(skel->links.tc6, skel->progs.tc4);
+ if (!ASSERT_OK(err, "link_update"))
+ goto cleanup;
+
+ assert_mprog_count(target, 1);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+ skel->bss->seen_tc4 = false;
+ skel->bss->seen_tc5 = false;
+ skel->bss->seen_tc6 = false;
+
+ err = bpf_link__detach(skel->links.tc6);
+ if (!ASSERT_OK(err, "prog_detach"))
+ goto cleanup;
+
+ __assert_mprog_count(target, 0, true, loopback);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup:
+ tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+ err = bpf_tc_detach(&tc_hook, &tc_opts);
+ ASSERT_OK(err, "bpf_tc_detach");
+
+ tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+ bpf_tc_hook_destroy(&tc_hook);
+
+ test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_links_chain_mixed(void)
+{
+ test_tc_chain_mixed(BPF_TCX_INGRESS);
+ test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_ingress(int target, bool chain_tc_old,
+ bool tcx_teardown_first)
+{
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+ .handle = 1,
+ .priority = 1,
+ );
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+ .ifindex = loopback,
+ .attach_point = BPF_TC_CUSTOM,
+ .parent = TC_H_INGRESS,
+ );
+ bool hook_created = false, tc_attached = false;
+ LIBBPF_OPTS(bpf_tcx_opts, optl);
+ __u32 pid1, pid2, pid3;
+ struct test_tc_link *skel;
+ struct bpf_link *link;
+ int err;
+
+ skel = test_tc_link__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+ 0, "tc1_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+ 0, "tc2_attach_type");
+
+ err = test_tc_link__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+ pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+ pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+ ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+ ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+ assert_mprog_count(target, 0);
+
+ if (chain_tc_old) {
+ ASSERT_OK(system("tc qdisc add dev lo ingress"), "add_ingress");
+ hook_created = true;
+
+ tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3);
+ err = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(err, "bpf_tc_attach"))
+ goto cleanup;
+ tc_attached = true;
+ }
+
+ link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc1 = link;
+
+ link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc2 = link;
+
+ assert_mprog_count(target, 2);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+ ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+ ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+ skel->bss->seen_tc1 = false;
+ skel->bss->seen_tc2 = false;
+ skel->bss->seen_tc3 = false;
+
+ err = bpf_link__detach(skel->links.tc2);
+ if (!ASSERT_OK(err, "prog_detach"))
+ goto cleanup;
+
+ assert_mprog_count(target, 1);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+ ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+ ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+cleanup:
+ if (tc_attached) {
+ tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+ err = bpf_tc_detach(&tc_hook, &tc_opts);
+ ASSERT_OK(err, "bpf_tc_detach");
+ }
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+ assert_mprog_count(target, 1);
+ if (hook_created && tcx_teardown_first)
+ ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+ test_tc_link__destroy(skel);
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+ if (hook_created && !tcx_teardown_first)
+ ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+ assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_ingress(void)
+{
+ test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
+ test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
+ test_tc_links_ingress(BPF_TCX_INGRESS, false, false);
+}
+
+static void test_tc_links_dev_mixed(int target)
+{
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook);
+ LIBBPF_OPTS(bpf_tcx_opts, optl);
+ __u32 pid1, pid2, pid3, pid4;
+ struct test_tc_link *skel;
+ struct bpf_link *link;
+ int err, ifindex;
+
+ ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+ ifindex = if_nametoindex("tcx_opts1");
+ ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+ skel = test_tc_link__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+ 0, "tc1_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+ 0, "tc2_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+ 0, "tc3_attach_type");
+ ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+ 0, "tc4_attach_type");
+
+ err = test_tc_link__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+ pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+ pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+ pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+ ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+ ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+ ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+ assert_mprog_count(target, 0);
+
+ link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc1 = link;
+
+ assert_mprog_count_ifindex(ifindex, target, 1);
+
+ link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc2 = link;
+
+ assert_mprog_count_ifindex(ifindex, target, 2);
+
+ link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc3 = link;
+
+ assert_mprog_count_ifindex(ifindex, target, 3);
+
+ link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl);
+ if (!ASSERT_OK_PTR(link, "link_attach"))
+ goto cleanup;
+
+ skel->links.tc4 = link;
+
+ assert_mprog_count_ifindex(ifindex, target, 4);
+
+ tc_hook.ifindex = ifindex;
+ tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+ BPF_TC_INGRESS : BPF_TC_EGRESS;
+
+ err = bpf_tc_hook_create(&tc_hook);
+ err = err == -EEXIST ? 0 : err;
+ if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+ goto cleanup;
+
+ tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+ err = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(err, "bpf_tc_attach"))
+ goto cleanup;
+
+ ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+ ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+ ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+
+ ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex");
+ ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex");
+ ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex");
+ ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex");
+
+ test_tc_link__destroy(skel);
+ return;
+cleanup:
+ test_tc_link__destroy(skel);
+
+ ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+ ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+ ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void serial_test_tc_links_dev_mixed(void)
+{
+ test_tc_links_dev_mixed(BPF_TCX_INGRESS);
+ test_tc_links_dev_mixed(BPF_TCX_EGRESS);
+}
test_tc_opts_delete_empty(BPF_TCX_INGRESS, true);
test_tc_opts_delete_empty(BPF_TCX_EGRESS, true);
}
+
+static void test_tc_chain_mixed(int target)
+{
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+ __u32 fd1, fd2, fd3, id1, id2, id3;
+ struct test_tc_link *skel;
+ int err, detach_fd;
+
+ skel = test_tc_link__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.tc4);
+ fd2 = bpf_program__fd(skel->progs.tc5);
+ fd3 = bpf_program__fd(skel->progs.tc6);
+
+ id1 = id_from_prog_fd(fd1);
+ id2 = id_from_prog_fd(fd2);
+ id3 = id_from_prog_fd(fd3);
+
+ ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+ ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+ assert_mprog_count(target, 0);
+
+ tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+ BPF_TC_INGRESS : BPF_TC_EGRESS;
+ err = bpf_tc_hook_create(&tc_hook);
+ err = err == -EEXIST ? 0 : err;
+ if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+ goto cleanup;
+
+ tc_opts.prog_fd = fd2;
+ err = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(err, "bpf_tc_attach"))
+ goto cleanup_hook;
+
+ err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup_filter;
+
+ detach_fd = fd3;
+
+ assert_mprog_count(target, 1);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+ skel->bss->seen_tc4 = false;
+ skel->bss->seen_tc5 = false;
+ skel->bss->seen_tc6 = false;
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_REPLACE,
+ .replace_prog_fd = fd3,
+ );
+
+ err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup_opts;
+
+ detach_fd = fd1;
+
+ assert_mprog_count(target, 1);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+ skel->bss->seen_tc4 = false;
+ skel->bss->seen_tc5 = false;
+ skel->bss->seen_tc6 = false;
+
+cleanup_opts:
+ err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+ ASSERT_OK(err, "prog_detach");
+ __assert_mprog_count(target, 0, true, loopback);
+
+ ASSERT_OK(system(ping_cmd), ping_cmd);
+
+ ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+ ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+ ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup_filter:
+ tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+ err = bpf_tc_detach(&tc_hook, &tc_opts);
+ ASSERT_OK(err, "bpf_tc_detach");
+
+cleanup_hook:
+ tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+ bpf_tc_hook_destroy(&tc_hook);
+
+cleanup:
+ test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_chain_mixed(void)
+{
+ test_tc_chain_mixed(BPF_TCX_INGRESS);
+ test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, SUSE. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fmod_ret/update_socket_protocol")
+int BPF_PROG(mptcpify, int family, int type, int protocol)
+{
+ if ((family == AF_INET || family == AF_INET6) &&
+ type == SOCK_STREAM &&
+ (!protocol || protocol == IPPROTO_TCP)) {
+ return IPPROTO_MPTCP;
+ }
+
+ return protocol;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+
+extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak;
+
+/* This function is here to have CONFIG_X86_KERNEL_IBT
+ * used and added to object BTF.
+ */
+int unused(void)
+{
+ return CONFIG_X86_KERNEL_IBT ? 0 : 1;
+}
+
+SEC("kprobe")
+int BPF_PROG(kprobe_run)
+{
+ return 0;
+}
+
+SEC("uprobe")
+int BPF_PROG(uprobe_run)
+{
+ return 0;
+}
+
+SEC("tracepoint")
+int BPF_PROG(tp_run)
+{
+ return 0;
+}
+
+SEC("kprobe.multi")
+int BPF_PROG(kmulti_run)
+{
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
bool seen_tc2;
bool seen_tc3;
bool seen_tc4;
+bool seen_tc5;
+bool seen_tc6;
SEC("tc/ingress")
int tc1(struct __sk_buff *skb)
seen_tc4 = true;
return TCX_NEXT;
}
+
+SEC("tc/egress")
+int tc5(struct __sk_buff *skb)
+{
+ seen_tc5 = true;
+ return TCX_PASS;
+}
+
+SEC("tc/egress")
+int tc6(struct __sk_buff *skb)
+{
+ seen_tc6 = true;
+ return TCX_PASS;
+}
goto cleanup;
cg_write(cg, "memory.high", "1M");
+
+ /* wait for RCU freeing */
+ sleep(1);
+
slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
if (slab1 <= 0)
goto cleanup;
printf("Size must be greater than 0\n");
return KSFT_FAIL;
}
+ break;
case 't':
{
int tmp = atoi(optarg);
RET=0
- mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ mirror_install $swp1 ingress $tundev \
+ "prot ip flower $tcflags ip_prot icmp"
tc filter add dev $h3 ingress pref 77 prot $prot \
flower skip_hw ip_ttl 50 action pass
projects / platform / kernel / linux-rpi.git / commitdiff