Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
Mark Brown <broonie@sirena.org.uk>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
Matthieu CASTET <castet.matthieu@free.fr>
Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
Yusuke Goda <goda.yusuke@renesas.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
int (*permission) (struct inode *, int, unsigned int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
void (*update_time)(struct inode *, struct timespec *, int);
[recommended]
->readlink is optional for symlinks. Don't set, unless filesystem needs
to fake something for readlink(2).
+--
+[mandatory]
+ ->getattr() is now passed a struct path rather than a vfsmount and
+ dentry separately, and it now has request_mask and query_flags arguments
+ to specify the fields and sync type requested by statx. Filesystems not
+ supporting any statx-specific features may ignore the new arguments.
int (*permission) (struct inode *, int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
int __init foo_probe(void)
{
+ int error;
+
struct pinctrl_dev *pctl;
- return pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ error = pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ if (error)
+ return error;
+
+ return pinctrl_enable(pctl);
}
To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and
.. code-block:: none
- Cc: <stable@vger.kernel.org> # 3.3.x-
+ Cc: <stable@vger.kernel.org> # 3.3.x
The tag has the meaning of:
Bits for undefined preemption levels are RAZ/WI.
+ For historical reasons and to provide ABI compatibility with userspace we
+ export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
+ field in the lower 5 bits of a word, meaning that userspace must always
+ use the lower 5 bits to communicate with the KVM device and must shift the
+ value left by 3 places to obtain the actual priority mask level.
+
Limitations:
- Priorities are not implemented, and registers are RAZ/WI
- Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
F: lib/lru_cache.c
F: Documentation/blockdev/drbd/
-DRIVER CORE, KOBJECTS, DEBUGFS, KERNFS AND SYSFS
+DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
S: Supported
F: Documentation/kobject.txt
F: drivers/base/
F: fs/debugfs/
-F: fs/kernfs/
F: fs/sysfs/
F: include/linux/debugfs.h
F: include/linux/kobj*
F: arch/mips/include/asm/kvm*
F: arch/mips/kvm/
+KERNFS
+M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M: Tejun Heo <tj@kernel.org>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+S: Supported
+F: include/linux/kernfs.h
+F: fs/kernfs/
+
KEXEC
M: Eric Biederman <ebiederm@xmission.com>
W: http://kernel.org/pub/linux/utils/kernel/kexec/
F: tools/virtio/
F: drivers/net/virtio_net.c
F: drivers/block/virtio_blk.c
-F: include/linux/virtio_*.h
+F: include/linux/virtio*.h
F: include/uapi/linux/virtio_*.h
F: drivers/crypto/virtio/
VERSION = 4
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Fearless Coyote
# *DOCUMENTATION*
/* copy relevant bits of struct timex. */
if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) ||
copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) -
- offsetof(struct timex32, time)))
+ offsetof(struct timex32, tick)))
return -EFAULT;
ret = do_adjtimex(&txc);
if (__hyp_get_vectors() == hyp_default_vectors)
cpu_init_hyp_mode(NULL);
}
+
+ if (vgic_present)
+ kvm_vgic_init_cpu_hardware();
}
static void cpu_hyp_reset(void)
phys_addr_t addr = start, end = start + size;
phys_addr_t next;
+ assert_spin_locked(&kvm->mmu_lock);
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
next = stage2_pgd_addr_end(addr, end);
if (!stage2_pgd_none(*pgd))
unmap_stage2_puds(kvm, pgd, addr, next);
+ /*
+ * If the range is too large, release the kvm->mmu_lock
+ * to prevent starvation and lockup detector warnings.
+ */
+ if (next != end)
+ cond_resched_lock(&kvm->mmu_lock);
} while (pgd++, addr = next, addr != end);
}
int idx;
idx = srcu_read_lock(&kvm->srcu);
+ down_read(¤t->mm->mmap_sem);
spin_lock(&kvm->mmu_lock);
slots = kvm_memslots(kvm);
stage2_unmap_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+ up_read(¤t->mm->mmap_sem);
srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm->arch.pgd == NULL)
return;
+ spin_lock(&kvm->mmu_lock);
unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ spin_unlock(&kvm->mmu_lock);
+
/* Free the HW pgd, one page at a time */
free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
kvm->arch.pgd = NULL;
(KVM_PHYS_SIZE >> PAGE_SHIFT))
return -EFAULT;
+ down_read(¤t->mm->mmap_sem);
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them to find out if we can map
pa += vm_start - vma->vm_start;
/* IO region dirty page logging not allowed */
- if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
- return -EINVAL;
+ if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+ ret = -EINVAL;
+ goto out;
+ }
ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
vm_end - vm_start,
} while (hva < reg_end);
if (change == KVM_MR_FLAGS_ONLY)
- return ret;
+ goto out;
spin_lock(&kvm->mmu_lock);
if (ret)
else
stage2_flush_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+out:
+ up_read(¤t->mm->mmap_sem);
return ret;
}
__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
}
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable. This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ * a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ * as we will try to flush the memory through a different alias to that
+ * actually being used (and the flushes are redundant.)
+ */
int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size,
unsigned long attrs)
{
- struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+ unsigned long pfn = dma_to_pfn(dev, handle);
+ struct page *page;
int ret;
+ /* If the PFN is not valid, we do not have a struct page */
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+
+ page = pfn_to_page(pfn);
+
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (unlikely(ret))
return ret;
*/
static inline bool security_extensions_enabled(void)
{
- return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ /* Check CPUID Identification Scheme before ID_PFR1 read */
+ if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
+ return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ return 0;
}
static unsigned long __init setup_vectors_base(void)
#endif
if (p) {
- if (cur) {
+ if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ /*
+ * Probe hit but conditional execution check failed,
+ * so just skip the instruction and continue as if
+ * nothing had happened.
+ * In this case, we can skip recursing check too.
+ */
+ singlestep_skip(p, regs);
+ } else if (cur) {
/* Kprobe is pending, so we're recursing. */
switch (kcb->kprobe_status) {
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
+ case KPROBE_HIT_SS:
/* A pre- or post-handler probe got us here. */
kprobes_inc_nmissed_count(p);
save_previous_kprobe(kcb);
singlestep(p, regs, kcb);
restore_previous_kprobe(kcb);
break;
+ case KPROBE_REENTER:
+ /* A nested probe was hit in FIQ, it is a BUG */
+ pr_warn("Unrecoverable kprobe detected at %p.\n",
+ p->addr);
+ /* fall through */
default:
/* impossible cases */
BUG();
}
- } else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ } else {
/* Probe hit and conditional execution check ok. */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
}
reset_current_kprobe();
}
- } else {
- /*
- * Probe hit but conditional execution check failed,
- * so just skip the instruction and continue as if
- * nothing had happened.
- */
- singlestep_skip(p, regs);
}
} else if (cur) {
/* We probably hit a jprobe. Call its break handler. */
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+ kprobe_opcode_t *correct_ret_addr = NULL;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* another task is sharing our hash bucket */
continue;
+ orig_ret_address = (unsigned long)ri->ret_addr;
+
+ if (orig_ret_address != trampoline_address)
+ /*
+ * This is the real return address. Any other
+ * instances associated with this task are for
+ * other calls deeper on the call stack
+ */
+ break;
+ }
+
+ kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+ correct_ret_addr = ri->ret_addr;
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ if (ri->task != current)
+ /* another task is sharing our hash bucket */
+ continue;
+
+ orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+ ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
__this_cpu_write(current_kprobe, NULL);
}
- orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
break;
}
- kretprobe_assert(ri, orig_ret_address, trampoline_address);
kretprobe_hash_unlock(current, &flags);
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
void __naked __kprobes_test_case_start(void)
{
__asm__ __volatile__ (
- "stmdb sp!, {r4-r11} \n\t"
+ "mov r2, sp \n\t"
+ "bic r3, r2, #7 \n\t"
+ "mov sp, r3 \n\t"
+ "stmdb sp!, {r2-r11} \n\t"
"sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
"bic r0, lr, #1 @ r0 = inline data \n\t"
"mov r1, sp \n\t"
"movne pc, r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"mov pc, r0 \n\t"
);
}
"bxne r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"bx r0 \n\t"
);
}
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+ int (*fn)(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+ int sig;
+ int code;
+ const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+ return fault_info + (esr & 63);
+}
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
struct pt_regs *regs)
{
struct siginfo si;
+ const struct fault_info *inf;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+ inf = esr_to_fault_info(esr);
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ tsk->comm, task_pid_nr(tsk), inf->name, sig,
addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
+ const struct fault_info *inf;
/*
* If we are in kernel mode at this point, we have no context to
* handle this fault with.
*/
- if (user_mode(regs))
- __do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
- else
+ if (user_mode(regs)) {
+ inf = esr_to_fault_info(esr);
+ __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+ } else
__do_kernel_fault(mm, addr, esr, regs);
}
return 1;
}
-static const struct fault_info {
- int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
- int sig;
- int code;
- const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
{ do_bad, SIGBUS, 0, "ttbr address size fault" },
{ do_bad, SIGBUS, 0, "level 1 address size fault" },
{ do_bad, SIGBUS, 0, "level 2 address size fault" },
{ do_bad, SIGBUS, 0, "unknown 63" },
};
-static const char *fault_name(unsigned int esr)
-{
- const struct fault_info *inf = fault_info + (esr & 63);
- return inf->name;
-}
-
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = fault_info + (esr & 63);
+ const struct fault_info *inf = esr_to_fault_info(esr);
struct siginfo info;
if (!inf->fn(addr, esr, regs))
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else if (ps == (PAGE_SIZE * CONT_PTES)) {
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- } else if (ps == (PMD_SIZE * CONT_PMDS)) {
- hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
- if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
--- /dev/null
+#ifndef _ASM_IA64_ASM_PROTOTYPES_H
+#define _ASM_IA64_ASM_PROTOTYPES_H
+
+#include <asm/cacheflush.h>
+#include <asm/checksum.h>
+#include <asm/esi.h>
+#include <asm/ftrace.h>
+#include <asm/page.h>
+#include <asm/pal.h>
+#include <asm/string.h>
+#include <asm/uaccess.h>
+#include <asm/unwind.h>
+#include <asm/xor.h>
+
+extern const char ia64_ivt[];
+
+signed int __divsi3(signed int, unsigned int);
+signed int __modsi3(signed int, unsigned int);
+
+signed long long __divdi3(signed long long, unsigned long long);
+signed long long __moddi3(signed long long, unsigned long long);
+
+unsigned int __udivsi3(unsigned int, unsigned int);
+unsigned int __umodsi3(unsigned int, unsigned int);
+
+unsigned long long __udivdi3(unsigned long long, unsigned long long);
+unsigned long long __umoddi3(unsigned long long, unsigned long long);
+
+#endif /* _ASM_IA64_ASM_PROTOTYPES_H */
AFLAGS___umodsi3.o = -DUNSIGNED -DMODULO
$(obj)/__divdi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__udivdi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__moddi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__umoddi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__divsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__udivsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__modsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__umodsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
#define strlen_user(str) strnlen_user(str, 32767)
-extern unsigned long __must_check __copy_user_zeroing(void *to,
- const void __user *from,
- unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+ unsigned long n);
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ unsigned long res = n;
if (likely(access_ok(VERIFY_READ, from, n)))
- return __copy_user_zeroing(to, from, n);
- memset(to, 0, n);
- return n;
+ res = raw_copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
+#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n)
#define __copy_from_user_inatomic __copy_from_user
extern unsigned long __must_check __copy_user(void __user *to,
COPY \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
FIXUP \
" MOVT D1Ar1,#HI(1b)\n" \
" JUMP D1Ar1,#LO(1b)\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #32\n" \
"23:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "SUB %3, %3, #32\n" \
"24:\n" \
+ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "25:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26:\n" \
"SUB %3, %3, #32\n" \
"DCACHE [%1+#-64], D0Ar6\n" \
"BR $Lloop"id"\n" \
\
"MOV RAPF, %1\n" \
- "25:\n" \
+ "27:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\n" \
+ "28:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29:\n" \
"SUB %3, %3, #32\n" \
- "27:\n" \
+ "30:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "28:\n" \
+ "31:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32:\n" \
"SUB %0, %0, #8\n" \
- "29:\n" \
+ "33:\n" \
"SETL [%0++], D0.7, D1.7\n" \
"SUB %3, %3, #32\n" \
"1:" \
" .long 26b,3b\n" \
" .long 27b,3b\n" \
" .long 28b,3b\n" \
- " .long 29b,4b\n" \
+ " .long 29b,3b\n" \
+ " .long 30b,3b\n" \
+ " .long 31b,3b\n" \
+ " .long 32b,3b\n" \
+ " .long 33b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_64bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #16\n" \
"23:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "24:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
"SUB %3, %3, #16\n" \
- "25:\n" \
+ "24:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\n" \
+ "25:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26:\n" \
"SUB %3, %3, #16\n" \
"27:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"28:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29:\n" \
+ "SUB %3, %3, #16\n" \
+ "30:\n" \
+ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "31:\n" \
+ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32:\n" \
"SUB %3, %3, #16\n" \
"DCACHE [%1+#-64], D0Ar6\n" \
"BR $Lloop"id"\n" \
\
"MOV RAPF, %1\n" \
- "29:\n" \
+ "33:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "30:\n" \
+ "34:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "35:\n" \
"SUB %3, %3, #16\n" \
- "31:\n" \
+ "36:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "32:\n" \
+ "37:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "38:\n" \
"SUB %3, %3, #16\n" \
- "33:\n" \
+ "39:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "34:\n" \
+ "40:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "41:\n" \
"SUB %3, %3, #16\n" \
- "35:\n" \
+ "42:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "36:\n" \
+ "43:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "44:\n" \
"SUB %0, %0, #4\n" \
- "37:\n" \
+ "45:\n" \
"SETD [%0++], D0.7\n" \
"SUB %3, %3, #16\n" \
"1:" \
" .long 34b,3b\n" \
" .long 35b,3b\n" \
" .long 36b,3b\n" \
- " .long 37b,4b\n" \
+ " .long 37b,3b\n" \
+ " .long 38b,3b\n" \
+ " .long 39b,3b\n" \
+ " .long 40b,3b\n" \
+ " .long 41b,3b\n" \
+ " .long 42b,3b\n" \
+ " .long 43b,3b\n" \
+ " .long 44b,3b\n" \
+ " .long 45b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
if ((unsigned long) src & 1) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
while (n > 0) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
while (n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
}
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
if (n >= RAPF_MIN_BUF_SIZE) {
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
#endif
while (n >= 16) {
__asm_copy_to_user_16(dst, src, retn);
n -= 16;
+ if (retn)
+ return retn + n;
}
while (n >= 4) {
__asm_copy_to_user_4(dst, src, retn);
n -= 4;
+ if (retn)
+ return retn + n;
}
switch (n) {
break;
}
+ /*
+ * If we get here, retn correctly reflects the number of failing
+ * bytes.
+ */
return retn;
}
EXPORT_SYMBOL(__copy_user);
__asm_copy_user_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"2: SETB [%0++],D1Ar1\n", \
- "3: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "3: ADD %2,%2,#1\n", \
" .long 2b,3b\n")
#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETW D1Ar1,[%1++]\n" \
"2: SETW [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#2\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_2(to, from, ret) \
__asm_copy_from_user_2x_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "5: ADD %2,%2,#1\n", \
" .long 4b,5b\n")
#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETD D1Ar1,[%1++]\n" \
"2: SETD [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#4\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_4(to, from, ret) \
__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
-#define __asm_copy_from_user_5(to, from, ret) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "4: SETW [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "4: SETD [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "6: SETW [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "6: SETD [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "8: SETW [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "10: SETB [%0++],D1Ar1\n", \
- "11: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "8: SETD [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
- __asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
#define __asm_copy_from_user_8x64(to, from, ret) \
asm volatile ( \
" GETL D0Ar2,D1Ar1,[%1++]\n" \
"2: SETL [%0++],D0Ar2,D1Ar1\n" \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
- " MOV D0Ar2,#0\n" \
"3: ADD %2,%2,#8\n" \
- " SETL [%0++],D0Ar2,D1Ar1\n" \
" MOVT D0Ar2,#HI(1b)\n" \
" JUMP D0Ar2,#LO(1b)\n" \
" .previous\n" \
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 8 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*8 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #8\n")
+ "LSR D0Ar2, D0Ar2, #5\n" \
+ "ANDS D0Ar2, D0Ar2, #0x38\n" \
+ "ADDZ D0Ar2, D0Ar2, #32\n" \
+ "SUB %1, %1, D0Ar2\n")
/* rewind 'from' pointer when a fault occurs
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 4 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*4 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #4\n")
+ "LSR D0Ar2, D0Ar2, #6\n" \
+ "ANDS D0Ar2, D0Ar2, #0x1c\n" \
+ "ADDZ D0Ar2, D0Ar2, #16\n" \
+ "SUB %1, %1, D0Ar2\n")
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
- userland. The return-value is the number of bytes that were
- inaccessible. */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
- unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+ unsigned long n)
{
register char *dst asm ("A0.2") = pdst;
register const char __user *src asm ("A1.2") = psrc;
if ((unsigned long) src & 1) {
__asm_copy_from_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
__asm_copy_from_user_1(dst, src, retn);
n--;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
- /* We only need one check after the unalignment-adjustments,
- because if both adjustments were done, either both or
- neither reference had an exception. */
- if (retn != 0)
- goto copy_exception_bytes;
-
#ifdef USE_RAPF
/* 64 bit copy loop */
if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
#endif
n -= 4;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
/* If we get here, there were no memory read faults. */
/* If we get here, retn correctly reflects the number of failing
bytes. */
return retn;
-
- copy_exception_bytes:
- /* We already have "retn" bytes cleared, and need to clear the
- remaining "n" bytes. A non-optimized simple byte-for-byte in-line
- memset is preferred here, since this isn't speed-critical code and
- we'd rather have this a leaf-function than calling memset. */
- {
- char *endp;
- for (endp = dst + n; dst < endp; dst++)
- *dst = 0;
- }
-
- return retn + n;
}
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
#define __asm_clear_8x64(to, ret) \
asm volatile ( \
select CPU_SUPPORTS_HIGHMEM
select CPU_SUPPORTS_MSA
select GENERIC_CSUM
- select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+ select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
select HAVE_KVM
help
Choose this option to build a kernel for release 6 or later of the
#include <asm/cpu-features.h>
#include <asm/fpu_emulator.h>
#include <asm/hazards.h>
+#include <asm/ptrace.h>
#include <asm/processor.h>
#include <asm/current.h>
#include <asm/msa.h>
#include <irq.h>
#define IRQ_STACK_SIZE THREAD_SIZE
+#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long))
extern void *irq_stack[NR_CPUS];
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ * top ------------
+ * | task sp | <- irq_stack[cpu] + IRQ_STACK_START
+ * ------------
+ * | | <- First frame of IRQ context
+ * ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
static inline bool on_irq_stack(int cpu, unsigned long sp)
{
unsigned long low = (unsigned long)irq_stack[cpu];
" andi %[ticket], %[ticket], 0xffff \n"
" bne %[ticket], %[my_ticket], 4f \n"
" subu %[ticket], %[my_ticket], %[ticket] \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"4: andi %[ticket], %[ticket], 0xffff \n"
" sll %[ticket], 5 \n"
" sc %[ticket], %[ticket_ptr] \n"
" beqz %[ticket], 1b \n"
" li %[ticket], 1 \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"3: b 2b \n"
" li %[ticket], 0 \n"
" .set reorder \n"
__WEAK_LLSC_MB
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
: "memory");
" lui %1, 0x8000 \n"
" sc %1, %0 \n"
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
"=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
#define __NR_pkey_mprotect (__NR_Linux + 363)
#define __NR_pkey_alloc (__NR_Linux + 364)
#define __NR_pkey_free (__NR_Linux + 365)
+#define __NR_statx (__NR_Linux + 366)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 365
+#define __NR_Linux_syscalls 366
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 365
+#define __NR_O32_Linux_syscalls 366
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_pkey_mprotect (__NR_Linux + 323)
#define __NR_pkey_alloc (__NR_Linux + 324)
#define __NR_pkey_free (__NR_Linux + 325)
+#define __NR_statx (__NR_Linux + 326)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 325
+#define __NR_Linux_syscalls 326
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 325
+#define __NR_64_Linux_syscalls 326
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_pkey_mprotect (__NR_Linux + 327)
#define __NR_pkey_alloc (__NR_Linux + 328)
#define __NR_pkey_free (__NR_Linux + 329)
+#define __NR_statx (__NR_Linux + 330)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 329
+#define __NR_Linux_syscalls 330
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 329
+#define __NR_N32_Linux_syscalls 330
#endif /* _UAPI_ASM_UNISTD_H */
DEFINE(_THREAD_SIZE, THREAD_SIZE);
DEFINE(_THREAD_MASK, THREAD_MASK);
DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+ DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
BLANK();
}
END(mips_cps_get_bootcfg)
LEAF(mips_cps_boot_vpes)
- PTR_L ta2, COREBOOTCFG_VPEMASK(a0)
+ lw ta2, COREBOOTCFG_VPEMASK(a0)
PTR_L ta3, COREBOOTCFG_VPECONFIG(a0)
#if defined(CONFIG_CPU_MIPSR6)
}
decode_configs(c);
- c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+ c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
c->writecombine = _CACHE_UNCACHED_ACCELERATED;
break;
default:
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jal plat_irq_dispatch
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jalr v0
BUILD_HANDLER reserved reserved sti verbose /* others */
.align 5
- LEAF(handle_ri_rdhwr_vivt)
+ LEAF(handle_ri_rdhwr_tlbp)
.set push
.set noat
.set noreorder
.set pop
bltz k1, handle_ri /* slow path */
/* fall thru */
- END(handle_ri_rdhwr_vivt)
+ END(handle_ri_rdhwr_tlbp)
LEAF(handle_ri_rdhwr)
.set push
unsigned long pc,
unsigned long *ra)
{
+ unsigned long low, high, irq_stack_high;
struct mips_frame_info info;
unsigned long size, ofs;
+ struct pt_regs *regs;
int leaf;
- extern void ret_from_irq(void);
- extern void ret_from_exception(void);
if (!stack_page)
return 0;
/*
- * If we reached the bottom of interrupt context,
- * return saved pc in pt_regs.
+ * IRQ stacks start at IRQ_STACK_START
+ * task stacks at THREAD_SIZE - 32
*/
- if (pc == (unsigned long)ret_from_irq ||
- pc == (unsigned long)ret_from_exception) {
- struct pt_regs *regs;
- if (*sp >= stack_page &&
- *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
- regs = (struct pt_regs *)*sp;
- pc = regs->cp0_epc;
- if (!user_mode(regs) && __kernel_text_address(pc)) {
- *sp = regs->regs[29];
- *ra = regs->regs[31];
- return pc;
- }
+ low = stack_page;
+ if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+ high = stack_page + IRQ_STACK_START;
+ irq_stack_high = high;
+ } else {
+ high = stack_page + THREAD_SIZE - 32;
+ irq_stack_high = 0;
+ }
+
+ /*
+ * If we reached the top of the interrupt stack, start unwinding
+ * the interrupted task stack.
+ */
+ if (unlikely(*sp == irq_stack_high)) {
+ unsigned long task_sp = *(unsigned long *)*sp;
+
+ /*
+ * Check that the pointer saved in the IRQ stack head points to
+ * something within the stack of the current task
+ */
+ if (!object_is_on_stack((void *)task_sp))
+ return 0;
+
+ /*
+ * Follow pointer to tasks kernel stack frame where interrupted
+ * state was saved.
+ */
+ regs = (struct pt_regs *)task_sp;
+ pc = regs->cp0_epc;
+ if (!user_mode(regs) && __kernel_text_address(pc)) {
+ *sp = regs->regs[29];
+ *ra = regs->regs[31];
+ return pc;
}
return 0;
}
if (leaf < 0)
return 0;
- if (*sp < stack_page ||
- *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+ if (*sp < low || *sp + info.frame_size > high)
return 0;
if (leaf)
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 5325 */
+ PTR sys_statx
.size sys_call_table,.-sys_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free
+ PTR sys_statx /* 6330 */
.size sysn32_call_table,.-sysn32_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
.size sys32_call_table,.-sys32_call_table
extern asmlinkage void handle_sys(void);
extern asmlinkage void handle_bp(void);
extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
extern asmlinkage void handle_ri_rdhwr(void);
extern asmlinkage void handle_cpu(void);
extern asmlinkage void handle_ov(void);
set_except_vector(EXCCODE_SYS, handle_sys);
set_except_vector(EXCCODE_BP, handle_bp);
- set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
- (cpu_has_vtag_icache ?
- handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+ if (rdhwr_noopt)
+ set_except_vector(EXCCODE_RI, handle_ri);
+ else {
+ if (cpu_has_vtag_icache)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else if (current_cpu_type() == CPU_LOONGSON3)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+ }
+
set_except_vector(EXCCODE_CPU, handle_cpu);
set_except_vector(EXCCODE_OV, handle_ov);
set_except_vector(EXCCODE_TR, handle_tr);
if (!np_xbar)
panic("Failed to load xbar nodes from devicetree");
- if (of_address_to_resource(np_pmu, 0, &res_xbar))
+ if (of_address_to_resource(np_xbar, 0, &res_xbar))
panic("Failed to get xbar resources");
if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
res_xbar.name))
vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
c->vcache.waybit = 0;
+ c->vcache.waysize = vcache_size / c->vcache.ways;
pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
scache_size *= 4;
c->scache.waybit = 0;
+ c->scache.waysize = scache_size / c->scache.ways;
pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
if (scache_size)
static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
struct uasm_label **l,
unsigned int pte,
- unsigned int ptr)
+ unsigned int ptr,
+ unsigned int flush)
{
#ifdef CONFIG_SMP
UASM_i_SC(p, pte, 0, ptr);
#else
UASM_i_SW(p, pte, 0, ptr);
#endif
+ if (cpu_has_ftlb && flush) {
+ BUG_ON(!cpu_has_tlbinv);
+
+ UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+ uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_tlb_write_entry(p, l, r, tlb_indexed);
+
+ uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_huge_update_entries(p, pte, ptr);
+ build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+ return;
+ }
+
build_huge_update_entries(p, pte, ptr);
build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
}
uasm_l_tlbl_goaround2(&l, p);
}
uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbl(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbs(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
#endif
uasm_l_nopage_tlbm(&l, p);
static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
static struct rt2880_pmx_func pci_func[] = {
FUNC("pci-dev", 0, 40, 32),
FUNC("pci-host2", 1, 40, 32),
FUNC("pci-fnc", 3, 40, 32)
};
static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
static struct rt2880_pmx_group rt3883_pinmux_data[] = {
GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
}
if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
pagefault_enable();
+ preempt_enable();
}
tail = len & VMX_ALIGN_MASK;
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
- /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
- if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
- nb = 8;
- flags = LD+SW;
- } else if (IS_XFORM(instruction) &&
- ((instruction >> 1) & 0x3ff) == 660) {
- nb = 8;
- flags = ST+SW;
+ /*
+ * Handle some cases which give overlaps in the DSISR values.
+ */
+ if (IS_XFORM(instruction)) {
+ switch (get_xop(instruction)) {
+ case 532: /* ldbrx */
+ nb = 8;
+ flags = LD+SW;
+ break;
+ case 660: /* stdbrx */
+ nb = 8;
+ flags = ST+SW;
+ break;
+ case 20: /* lwarx */
+ case 84: /* ldarx */
+ case 116: /* lharx */
+ case 276: /* lqarx */
+ return 0; /* not emulated ever */
+ }
}
/* Byteswap little endian loads and stores */
* flush all bytes from start through stop-1 inclusive
*/
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
BEGIN_FTR_SECTION
PURGE_PREFETCHED_INS
blr
*
* flush all bytes from start to stop-1 inclusive
*/
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
/*
* Flush the data cache to memory
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
+ /*
+ * Fixup HFSCR:TM based on CPU features. The bit is set by our
+ * early asm init because at that point we haven't updated our
+ * CPU features from firmware and device-tree. Here we have,
+ * so let's do it.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
/* start new resize */
resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+ if (!resize) {
+ ret = -ENOMEM;
+ goto out;
+ }
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
unsigned long psize = batch->psize;
int ssize = batch->ssize;
int i;
+ unsigned int use_local;
+
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+ mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
local_irq_save(flags);
} pte_iterate_hashed_end();
}
- if (mmu_has_feature(MMU_FTR_TLBIEL) &&
- mmu_psize_defs[psize].tlbiel && local) {
+ if (use_local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
vpn = batch->vpn[i];
unsigned long z : 1; /* Zero Bit */
unsigned long i : 1; /* Page-Invalid Bit */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long co : 1; /* Change-Recording Override */
- unsigned long : 8;
+ unsigned long : 9;
};
};
return PGM_PAGE_TRANSLATION;
if (pte.z)
return PGM_TRANSLATION_SPEC;
- if (pte.co && !edat1)
- return PGM_TRANSLATION_SPEC;
dat_protection |= pte.p;
raddr.pfra = pte.pfra;
real_address:
rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
if (!rc && pte.i)
rc = PGM_PAGE_TRANSLATION;
- if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+ if (!rc && pte.z)
rc = PGM_TRANSLATION_SPEC;
shadow_page:
pte.p |= dat_protection;
#define HPAGE_SHIFT 23
#define REAL_HPAGE_SHIFT 22
+#define HPAGE_2GB_SHIFT 31
#define HPAGE_256MB_SHIFT 28
#define HPAGE_64K_SHIFT 16
#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT)
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE 3
+#define HUGE_MAX_HSTATE 4
#endif
#ifndef __ASSEMBLY__
return pte_pfn(pte);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_dirty(pte);
+ return pte_write(pte);
}
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_young(pte);
+ return pte_dirty(pte);
}
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_write(pte);
+ return pte_young(pte);
}
static inline unsigned long pmd_trans_huge(pmd_t pmd)
#include <asm/signal.h>
#include <asm/page.h>
-/*
- * The sparc has no problems with write protection
- */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too...
* That one page is used to protect kernel from intruders, so that
* we can make our access_ok test faster
#include <asm/ptrace.h>
#include <asm/page.h>
-/* The sparc has no problems with write protection */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/*
* User lives in his very own context, and cannot reference us. Note
* that TASK_SIZE is a misnomer, it really gives maximum user virtual
andn %g1, PSTATE_AM, %g1
wrpr %g1, 0x0, %pstate
ba,a,pt %xcc, 1f
+ nop
.globl prom_finddev_name, prom_chosen_path, prom_root_node
.globl prom_getprop_name, prom_mmu_name, prom_peer_name
nop
ba,a,pt %xcc, 80f
+ nop
niagara4_patch:
call niagara4_patch_copyops
nop
nop
ba,a,pt %xcc, 80f
+ nop
niagara2_patch:
call niagara2_patch_copyops
nop
ba,a,pt %xcc, 80f
+ nop
niagara_patch:
call niagara_patch_copyops
call handle_stdfmna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
.size do_stdfmna,.-do_stdfmna
.type breakpoint_trap,#function
bne,pt %xcc, user_rtt_fill_32bit
wrpr %g1, %cwp
ba,a,pt %xcc, user_rtt_fill_64bit
+ nop
user_rtt_fill_fixup_dax:
ba,pt %xcc, user_rtt_fill_fixup_common
rd %pc, %g7
ba,a,pt %xcc, 2f
+ nop
1: ba,pt %xcc, etrap_irq
rd %pc, %g7
call sun4v_do_mna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
/* Privileged Action. */
sun4v_privact:
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
blu 170f
nop
ba,a,pt %xcc, 180f
+ nop
4: /* 32 <= low bits < 48 */
blu 150f
nop
ba,a,pt %xcc, 160f
+ nop
5: /* 0 < low bits < 32 */
blu,a 6f
cmp %g2, 8
blu 130f
nop
ba,a,pt %xcc, 140f
+ nop
6: /* 0 < low bits < 16 */
bgeu 120f
nop
brz,pt %o2, 85f
sub %o0, %o1, GLOBAL_SPARE
ba,a,pt %XCC, 90f
+ nop
.align 64
75: /* 16 < len <= 64 */
bne,pt %icc, 1b
EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
ba,a,pt %icc, .Lexit
+ nop
.size FUNC_NAME, .-FUNC_NAME
bne,pt %icc, 1b
add %o0, 0x30, %o0
ba,a,pt %icc, .Lpostloop
+ nop
.size NG4bzero,.-NG4bzero
brz,pt %i2, 85f
sub %o0, %i1, %i3
ba,a,pt %XCC, 90f
+ nop
.align 64
70: /* 16 < len <= 64 */
pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
switch (shift) {
+ case HPAGE_2GB_SHIFT:
+ hugepage_size = _PAGE_SZ2GB_4V;
+ pte_val(entry) |= _PAGE_PMD_HUGE;
+ break;
case HPAGE_256MB_SHIFT:
hugepage_size = _PAGE_SZ256MB_4V;
pte_val(entry) |= _PAGE_PMD_HUGE;
unsigned int shift;
switch (tte_szbits) {
+ case _PAGE_SZ2GB_4V:
+ shift = HPAGE_2GB_SHIFT;
+ break;
case _PAGE_SZ256MB_4V:
shift = HPAGE_256MB_SHIFT;
break;
if (!pmd)
return NULL;
- if (sz == PMD_SHIFT)
+ if (sz >= PMD_SIZE)
pte = (pte_t *)pmd;
else
pte = pte_alloc_map(mm, pmd, addr);
hugepage_shift = ilog2(hugepage_size);
switch (hugepage_shift) {
+ case HPAGE_2GB_SHIFT:
+ hv_pgsz_mask = HV_PGSZ_MASK_2GB;
+ hv_pgsz_idx = HV_PGSZ_IDX_2GB;
+ break;
case HPAGE_256MB_SHIFT:
hv_pgsz_mask = HV_PGSZ_MASK_256MB;
hv_pgsz_idx = HV_PGSZ_IDX_256MB;
if ((long)addr < 0L) {
unsigned long pa = __pa(addr);
- if ((addr >> max_phys_bits) != 0UL)
+ if ((pa >> max_phys_bits) != 0UL)
return false;
return pfn_valid(pa >> PAGE_SHIFT);
enum mbus_module srmmu_modtype;
static unsigned int hwbug_bitmask;
int vac_cache_size;
+EXPORT_SYMBOL(vac_cache_size);
int vac_line_size;
extern struct resource sparc_iomap;
if (pte_val(*pte) & _PAGE_VALID) {
bool exec = pte_exec(*pte);
- tlb_batch_add_one(mm, vaddr, exec, false);
+ tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT);
}
pte++;
vaddr += PAGE_SIZE;
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
- tlb_batch_add_one(mm, addr, exec, true);
+ tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
- true);
+ REAL_HPAGE_SHIFT);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
spin_lock_irqsave(&mm->context.lock, flags);
- if (tb->hugepage_shift < HPAGE_SHIFT) {
+ if (tb->hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
spin_lock_irqsave(&mm->context.lock, flags);
- if (hugepage_shift < HPAGE_SHIFT) {
+ if (hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
{
vdso32_enabled = simple_strtoul(s, NULL, 0);
- if (vdso32_enabled > 1)
+ if (vdso32_enabled > 1) {
pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+ vdso32_enabled = 0;
+ }
return 1;
}
/* Register vsyscall32 into the ABI table */
#include <linux/sysctl.h>
+static const int zero;
+static const int one = 1;
+
static struct ctl_table abi_table2[] = {
{
.procname = "vsyscall32",
.data = &vdso32_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (int *)&zero,
+ .extra2 = (int *)&one,
},
{}
};
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].mispred = 0;
cpuc->lbr_entries[i].predicted = 0;
+ cpuc->lbr_entries[i].in_tx = 0;
+ cpuc->lbr_entries[i].abort = 0;
+ cpuc->lbr_entries[i].cycles = 0;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
#define ARCH_DLINFO_IA32 \
do { \
- if (vdso32_enabled) { \
+ if (VDSO_CURRENT_BASE) { \
NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} \
}
out:
- rdtgroup_kn_unlock(of->kn);
for_each_enabled_rdt_resource(r) {
kfree(r->tmp_cbms);
r->tmp_cbms = NULL;
}
+ rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
me->comm, me->pid, where, frame,
regs->ip, regs->sp, regs->orig_ax);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
if (from->si_signo == SIGSEGV) {
if (from->si_code == SEGV_BNDERR) {
- compat_uptr_t lower = (unsigned long)&to->si_lower;
- compat_uptr_t upper = (unsigned long)&to->si_upper;
+ compat_uptr_t lower = (unsigned long)from->si_lower;
+ compat_uptr_t upper = (unsigned long)from->si_upper;
put_user_ex(lower, &to->si_lower);
put_user_ex(upper, &to->si_upper);
}
pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
tsk->comm, tsk->pid, str,
regs->ip, regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
tsk->comm, task_pid_nr(tsk),
regs->ip, regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
case EXIT_REASON_PREEMPTION_TIMER:
return false;
+ case EXIT_REASON_PML_FULL:
+ /* We don't expose PML support to L1. */
+ return false;
default:
return true;
}
}
+ if (enable_pml) {
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit, this happens
+ * to be equivalent to simply resetting the fields in vmcs02.
+ */
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number.
*
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (pagenr < 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+ if (page_is_ram(pagenr)) {
+ /*
+ * For disallowed memory regions in the low 1MB range,
+ * request that the page be shown as all zeros.
+ */
+ if (pagenr < 256)
+ return 2;
+
+ return 0;
+ }
+
+ /*
+ * This must follow RAM test, since System RAM is considered a
+ * restricted resource under CONFIG_STRICT_IOMEM.
+ */
+ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+ /* Low 1MB bypasses iomem restrictions. */
+ if (pagenr < 256)
+ return 1;
+
return 0;
- if (!page_is_ram(pagenr))
- return 1;
- return 0;
+ }
+
+ return 1;
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
return;
}
+ /* No need to reserve regions that will never be freed. */
+ if (md.attribute & EFI_MEMORY_RUNTIME)
+ return;
+
size += addr % EFI_PAGE_SIZE;
size = round_up(size, EFI_PAGE_SIZE);
addr = round_down(addr, EFI_PAGE_SIZE);
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
- struct elevator_queue *e = hctx->queue->elevator;
+ struct request_queue *q = hctx->queue;
+ struct elevator_queue *e = q->elevator;
const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
bool did_work = false;
LIST_HEAD(rq_list);
*/
if (!list_empty(&rq_list)) {
blk_mq_sched_mark_restart_hctx(hctx);
- did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+ did_work = blk_mq_dispatch_rq_list(q, &rq_list);
} else if (!has_sched_dispatch) {
blk_mq_flush_busy_ctxs(hctx, &rq_list);
- blk_mq_dispatch_rq_list(hctx, &rq_list);
+ blk_mq_dispatch_rq_list(q, &rq_list);
}
/*
if (!rq)
break;
list_add(&rq->queuelist, &rq_list);
- } while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+ } while (blk_mq_dispatch_rq_list(q, &rq_list));
}
}
return true;
}
-static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (blk_mq_hctx_has_pending(hctx))
+ if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
+ return true;
+ }
}
+ return false;
}
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
- unsigned int i;
+/**
+ * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
+ * @pos: loop cursor.
+ * @skip: the list element that will not be examined. Iteration starts at
+ * @skip->next.
+ * @head: head of the list to examine. This list must have at least one
+ * element, namely @skip.
+ * @member: name of the list_head structure within typeof(*pos).
+ */
+#define list_for_each_entry_rcu_rr(pos, skip, head, member) \
+ for ((pos) = (skip); \
+ (pos = (pos)->member.next != (head) ? list_entry_rcu( \
+ (pos)->member.next, typeof(*pos), member) : \
+ list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
+ (pos) != (skip); )
- if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_restart_hctx(hctx);
+/*
+ * Called after a driver tag has been freed to check whether a hctx needs to
+ * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
+ * queues in a round-robin fashion if the tag set of @hctx is shared with other
+ * hardware queues.
+ */
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
+{
+ struct blk_mq_tags *const tags = hctx->tags;
+ struct blk_mq_tag_set *const set = hctx->queue->tag_set;
+ struct request_queue *const queue = hctx->queue, *q;
+ struct blk_mq_hw_ctx *hctx2;
+ unsigned int i, j;
+
+ if (set->flags & BLK_MQ_F_TAG_SHARED) {
+ rcu_read_lock();
+ list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
+ tag_set_list) {
+ queue_for_each_hw_ctx(q, hctx2, i)
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ goto done;
+ }
+ j = hctx->queue_num + 1;
+ for (i = 0; i < queue->nr_hw_queues; i++, j++) {
+ if (j == queue->nr_hw_queues)
+ j = 0;
+ hctx2 = queue->queue_hw_ctx[j];
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ break;
}
+done:
+ rcu_read_unlock();
} else {
blk_mq_sched_restart_hctx(hctx);
}
}
}
-int blk_mq_sched_setup(struct request_queue *q)
+static int blk_mq_sched_alloc_tags(struct request_queue *q,
+ struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct blk_mq_tag_set *set = q->tag_set;
+ int ret;
+
+ hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
+ set->reserved_tags);
+ if (!hctx->sched_tags)
+ return -ENOMEM;
+
+ ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
+ if (ret)
+ blk_mq_sched_free_tags(set, hctx, hctx_idx);
+
+ return ret;
+}
+
+static void blk_mq_sched_tags_teardown(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
- int ret, i;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ blk_mq_sched_free_tags(set, hctx, i);
+}
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (!e)
+ return 0;
+
+ return blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+}
+
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (!e)
+ return;
+
+ blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+}
+
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+ int ret;
+
+ if (!e) {
+ q->elevator = NULL;
+ return 0;
+ }
/*
* Default to 256, since we don't split into sync/async like the
*/
q->nr_requests = 2 * BLKDEV_MAX_RQ;
- /*
- * We're switching to using an IO scheduler, so setup the hctx
- * scheduler tags and switch the request map from the regular
- * tags to scheduler tags. First allocate what we need, so we
- * can safely fail and fallback, if needed.
- */
- ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
- q->nr_requests, set->reserved_tags);
- if (!hctx->sched_tags) {
- ret = -ENOMEM;
- break;
- }
- ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+ ret = blk_mq_sched_alloc_tags(q, hctx, i);
if (ret)
- break;
+ goto err;
}
- /*
- * If we failed, free what we did allocate
- */
- if (ret) {
- queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx->sched_tags)
- continue;
- blk_mq_sched_free_tags(set, hctx, i);
- }
-
- return ret;
- }
+ ret = e->ops.mq.init_sched(q, e);
+ if (ret)
+ goto err;
return 0;
+
+err:
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
+ return ret;
}
-void blk_mq_sched_teardown(struct request_queue *q)
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
{
- struct blk_mq_tag_set *set = q->tag_set;
- struct blk_mq_hw_ctx *hctx;
- int i;
-
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_free_tags(set, hctx, i);
+ if (e->type->ops.mq.exit_sched)
+ e->type->ops.mq.exit_sched(e);
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
}
int blk_mq_sched_init(struct request_queue *q)
struct request **merged_request);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
bool run_queue, bool async, bool can_block);
struct list_head *rq_list,
struct request *(*get_rq)(struct blk_mq_hw_ctx *));
-int blk_mq_sched_setup(struct request_queue *q);
-void blk_mq_sched_teardown(struct request_queue *q);
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
int blk_mq_sched_init(struct request_queue *q);
set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
-/*
- * Mark a hardware queue and the request queue it belongs to as needing a
- * restart.
- */
-static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
-
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
- set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-}
-
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
- blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
if (!rq)
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
blk_mq_sched_completed_request(hctx, rq);
- blk_mq_sched_restart_queues(hctx);
+ blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
};
- if (rq->tag != -1) {
-done:
- if (hctx)
- *hctx = data.hctx;
- return true;
- }
+ if (rq->tag != -1)
+ goto done;
if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
data.flags |= BLK_MQ_REQ_RESERVED;
atomic_inc(&data.hctx->nr_active);
}
data.hctx->tags->rqs[rq->tag] = rq;
- goto done;
}
- return false;
+done:
+ if (hctx)
+ *hctx = data.hctx;
+ return rq->tag != -1;
}
static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
return true;
}
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
- struct request_queue *q = hctx->queue;
+ struct blk_mq_hw_ctx *hctx;
struct request *rq;
LIST_HEAD(driver_list);
struct list_head *dptr;
int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
+ if (list_empty(list))
+ return false;
+
/*
* Start off with dptr being NULL, so we start the first request
* immediately, even if we have more pending.
* Now process all the entries, sending them to the driver.
*/
errors = queued = 0;
- while (!list_empty(list)) {
+ do {
struct blk_mq_queue_data bd;
rq = list_first_entry(list, struct request, queuelist);
*/
if (!dptr && list->next != list->prev)
dptr = &driver_list;
- }
+ } while (!list_empty(list));
hctx->dispatched[queued_to_index(queued)]++;
return hctx->next_cpu;
}
-void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
+ unsigned long msecs)
{
if (unlikely(blk_mq_hctx_stopped(hctx) ||
!blk_mq_hw_queue_mapped(hctx)))
put_cpu();
}
- kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);
+ if (msecs == 0)
+ kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work);
+ else
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->delayed_run_work,
+ msecs_to_jiffies(msecs));
+}
+
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
+{
+ __blk_mq_delay_run_hw_queue(hctx, true, msecs);
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+ __blk_mq_delay_run_hw_queue(hctx, async, 0);
}
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
__blk_mq_run_hw_queue(hctx);
}
+static void blk_mq_delayed_run_work_fn(struct work_struct *work)
+{
+ struct blk_mq_hw_ctx *hctx;
+
+ hctx = container_of(work, struct blk_mq_hw_ctx, delayed_run_work.work);
+
+ __blk_mq_run_hw_queue(hctx);
+}
+
static void blk_mq_delay_work_fn(struct work_struct *work)
{
struct blk_mq_hw_ctx *hctx;
hctx->fq->flush_rq, hctx_idx,
flush_start_tag + hctx_idx);
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
+
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
node = hctx->numa_node = set->numa_node;
INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);
+ INIT_DELAYED_WORK(&hctx->delayed_run_work, blk_mq_delayed_run_work_fn);
INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
goto free_bitmap;
+ if (blk_mq_sched_init_hctx(q, hctx, hctx_idx))
+ goto exit_hctx;
+
hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
if (!hctx->fq)
- goto exit_hctx;
+ goto sched_exit_hctx;
if (set->ops->init_request &&
set->ops->init_request(set->driver_data,
free_fq:
kfree(hctx->fq);
+ sched_exit_hctx:
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
exit_hctx:
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
struct blk_mq_hw_ctx *hctx;
unsigned int i;
- blk_mq_sched_teardown(q);
-
/* hctx kobj stays in hctx */
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
return 0;
}
+static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+{
+ if (set->ops->map_queues)
+ return set->ops->map_queues(set);
+ else
+ return blk_mq_map_queues(set);
+}
+
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
if (!set->mq_map)
goto out_free_tags;
- if (set->ops->map_queues)
- ret = set->ops->map_queues(set);
- else
- ret = blk_mq_map_queues(set);
+ ret = blk_mq_update_queue_map(set);
if (ret)
goto out_free_mq_map;
blk_mq_freeze_queue(q);
set->nr_hw_queues = nr_hw_queues;
+ blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
if (q->elevator) {
ioc_clear_queue(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
}
blk_exit_rl(&q->root_rl);
}
}
- if (e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = e->ops.mq.init_sched(q, e);
- } else
+ if (e->uses_mq)
+ err = blk_mq_init_sched(q, e);
+ else
err = e->ops.sq.elevator_init_fn(q, e);
- if (err) {
- if (e->uses_mq)
- blk_mq_sched_teardown(q);
+ if (err)
elevator_put(e);
- }
return err;
}
EXPORT_SYMBOL(elevator_init);
-void elevator_exit(struct elevator_queue *e)
+void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->uses_mq && e->type->ops.mq.exit_sched)
- e->type->ops.mq.exit_sched(e);
+ blk_mq_exit_sched(q, e);
else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
e->type->ops.sq.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);
+static int elevator_switch_mq(struct request_queue *q,
+ struct elevator_type *new_e)
+{
+ int ret;
+
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
+
+ if (q->elevator) {
+ if (q->elevator->registered)
+ elv_unregister_queue(q);
+ ioc_clear_queue(q);
+ elevator_exit(q, q->elevator);
+ }
+
+ ret = blk_mq_init_sched(q, new_e);
+ if (ret)
+ goto out;
+
+ if (new_e) {
+ ret = elv_register_queue(q);
+ if (ret) {
+ elevator_exit(q, q->elevator);
+ goto out;
+ }
+ }
+
+ if (new_e)
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+ else
+ blk_add_trace_msg(q, "elv switch: none");
+
+out:
+ blk_mq_unfreeze_queue(q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ return ret;
+
+}
+
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
bool old_registered = false;
int err;
- if (q->mq_ops) {
- blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
- }
+ if (q->mq_ops)
+ return elevator_switch_mq(q, new_e);
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
if (old) {
old_registered = old->registered;
- if (old->uses_mq)
- blk_mq_sched_teardown(q);
-
- if (!q->mq_ops)
- blk_queue_bypass_start(q);
+ blk_queue_bypass_start(q);
/* unregister and clear all auxiliary data of the old elevator */
if (old_registered)
}
/* allocate, init and register new elevator */
- if (new_e) {
- if (new_e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = new_e->ops.mq.init_sched(q, new_e);
- } else
- err = new_e->ops.sq.elevator_init_fn(q, new_e);
- if (err)
- goto fail_init;
+ err = new_e->ops.sq.elevator_init_fn(q, new_e);
+ if (err)
+ goto fail_init;
- err = elv_register_queue(q);
- if (err)
- goto fail_register;
- } else
- q->elevator = NULL;
+ err = elv_register_queue(q);
+ if (err)
+ goto fail_register;
/* done, kill the old one and finish */
if (old) {
- elevator_exit(old);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
+ elevator_exit(q, old);
+ blk_queue_bypass_end(q);
}
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
- }
-
- if (new_e)
- blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
- else
- blk_add_trace_msg(q, "elv switch: none");
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
return 0;
fail_register:
- if (q->mq_ops)
- blk_mq_sched_teardown(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
fail_init:
/* switch failed, restore and re-register old elevator */
if (old) {
q->elevator = old;
elv_register_queue(q);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
- }
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_queue_bypass_end(q);
}
return err;
ACPI_FUNCTION_TRACE(ut_walk_aml_resources);
- /*
- * The absolute minimum resource template is one end_tag descriptor.
- * However, we will treat a lone end_tag as just a simple buffer.
- */
+ /* The absolute minimum resource template is one end_tag descriptor */
+
if (aml_length < sizeof(struct aml_resource_end_tag)) {
return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
}
/* Invoke the user function */
if (user_function) {
- status = user_function(aml, length, offset,
- resource_index, context);
+ status =
+ user_function(aml, length, offset, resource_index,
+ context);
if (ACPI_FAILURE(status)) {
return_ACPI_STATUS(status);
}
*context = aml;
}
- /* Check if buffer is defined to be longer than the resource length */
-
- if (aml_length > (offset + length)) {
- return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
- }
-
/* Normal exit */
return_ACPI_STATUS(AE_OK);
return -ENODEV;
/*
- * If the device has a _HID (or _CID) returning a valid ACPI/PNP
- * device ID, it is better to make it look less attractive here, so that
- * the other device with the same _ADR value (that may not have a valid
- * device ID) can be matched going forward. [This means a second spec
- * violation in a row, so whatever we do here is best effort anyway.]
+ * If the device has a _HID returning a valid ACPI/PNP device ID, it is
+ * better to make it look less attractive here, so that the other device
+ * with the same _ADR value (that may not have a valid device ID) can be
+ * matched going forward. [This means a second spec violation in a row,
+ * so whatever we do here is best effort anyway.]
*/
- return sta_present && list_empty(&adev->pnp.ids) ?
+ return sta_present && !adev->pnp.type.platform_id ?
FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
}
return;
device->flags.match_driver = true;
- if (!ret) {
- ret = device_attach(&device->dev);
- if (ret < 0)
- return;
-
- if (!ret && device->pnp.type.platform_id)
- acpi_default_enumeration(device);
+ if (ret > 0) {
+ acpi_device_set_enumerated(device);
+ goto ok;
}
+ ret = device_attach(&device->dev);
+ if (ret < 0)
+ return;
+
+ if (ret > 0 || !device->pnp.type.platform_id)
+ acpi_device_set_enumerated(device);
+ else
+ acpi_default_enumeration(device);
+
ok:
list_for_each_entry(child, &device->children, node)
acpi_bus_attach(child);
};
const struct ata_port_info *ppi[] = { &info, &info };
- /* SB600/700 don't have secondary port wired */
- if ((pdev->device == PCI_DEVICE_ID_ATI_IXP600_IDE) ||
- (pdev->device == PCI_DEVICE_ID_ATI_IXP700_IDE))
- ppi[1] = &ata_dummy_port_info;
-
return ata_pci_bmdma_init_one(pdev, ppi, &atiixp_sht, NULL,
ATA_HOST_PARALLEL_SCAN);
}
pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8);
}
- /* enable IRQ on hotplug */
- pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
- if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
- dev_dbg(&pdev->dev,
- "enabling SATA hotplug (0x%x)\n",
- (int) tmp8);
- tmp8 |= SATA_HOTPLUG;
- pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+ if (board_id == vt6421) {
+ /* enable IRQ on hotplug */
+ pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
+ if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
+ dev_dbg(&pdev->dev,
+ "enabling SATA hotplug (0x%x)\n",
+ (int) tmp8);
+ tmp8 |= SATA_HOTPLUG;
+ pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+ }
}
/*
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE) {
- copy_page(mem, cmem);
+ memcpy(mem, cmem, PAGE_SIZE);
} else {
struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
src = kmap_atomic(page);
- copy_page(cmem, src);
+ memcpy(cmem, src, PAGE_SIZE);
kunmap_atomic(src);
} else {
memcpy(cmem, src, clen);
}
index = sector >> SECTORS_PER_PAGE_SHIFT;
- offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+ offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
#endif
#ifdef CONFIG_STRICT_DEVMEM
+static inline int page_is_allowed(unsigned long pfn)
+{
+ return devmem_is_allowed(pfn);
+}
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
u64 from = ((u64)pfn) << PAGE_SHIFT;
return 1;
}
#else
+static inline int page_is_allowed(unsigned long pfn)
+{
+ return 1;
+}
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
return 1;
while (count > 0) {
unsigned long remaining;
+ int allowed;
sz = size_inside_page(p, count);
- if (!range_is_allowed(p >> PAGE_SHIFT, count))
+ allowed = page_is_allowed(p >> PAGE_SHIFT);
+ if (!allowed)
return -EPERM;
+ if (allowed == 2) {
+ /* Show zeros for restricted memory. */
+ remaining = clear_user(buf, sz);
+ } else {
+ /*
+ * On ia64 if a page has been mapped somewhere as
+ * uncached, then it must also be accessed uncached
+ * by the kernel or data corruption may occur.
+ */
+ ptr = xlate_dev_mem_ptr(p);
+ if (!ptr)
+ return -EFAULT;
- /*
- * On ia64 if a page has been mapped somewhere as uncached, then
- * it must also be accessed uncached by the kernel or data
- * corruption may occur.
- */
- ptr = xlate_dev_mem_ptr(p);
- if (!ptr)
- return -EFAULT;
+ remaining = copy_to_user(buf, ptr, sz);
+
+ unxlate_dev_mem_ptr(p, ptr);
+ }
- remaining = copy_to_user(buf, ptr, sz);
- unxlate_dev_mem_ptr(p, ptr);
if (remaining)
return -EFAULT;
#endif
while (count > 0) {
+ int allowed;
+
sz = size_inside_page(p, count);
- if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+ allowed = page_is_allowed(p >> PAGE_SHIFT);
+ if (!allowed)
return -EPERM;
- /*
- * On ia64 if a page has been mapped somewhere as uncached, then
- * it must also be accessed uncached by the kernel or data
- * corruption may occur.
- */
- ptr = xlate_dev_mem_ptr(p);
- if (!ptr) {
- if (written)
- break;
- return -EFAULT;
- }
+ /* Skip actual writing when a page is marked as restricted. */
+ if (allowed == 1) {
+ /*
+ * On ia64 if a page has been mapped somewhere as
+ * uncached, then it must also be accessed uncached
+ * by the kernel or data corruption may occur.
+ */
+ ptr = xlate_dev_mem_ptr(p);
+ if (!ptr) {
+ if (written)
+ break;
+ return -EFAULT;
+ }
- copied = copy_from_user(ptr, buf, sz);
- unxlate_dev_mem_ptr(p, ptr);
- if (copied) {
- written += sz - copied;
- if (written)
- break;
- return -EFAULT;
+ copied = copy_from_user(ptr, buf, sz);
+ unxlate_dev_mem_ptr(p, ptr);
+ if (copied) {
+ written += sz - copied;
+ if (written)
+ break;
+ return -EFAULT;
+ }
}
buf += sz;
vdev->config->reset(vdev);
- virtqueue_disable_cb(portdev->c_ivq);
+ if (use_multiport(portdev))
+ virtqueue_disable_cb(portdev->c_ivq);
cancel_work_sync(&portdev->control_work);
cancel_work_sync(&portdev->config_work);
/*
* Once more: if control_work_handler() was running, it would
* enable the cb as the last step.
*/
- virtqueue_disable_cb(portdev->c_ivq);
+ if (use_multiport(portdev))
+ virtqueue_disable_cb(portdev->c_ivq);
remove_controlq_data(portdev);
list_for_each_entry(port, &portdev->ports, list) {
*********************************************************************/
static enum cpuhp_state hp_online;
+static int cpuhp_cpufreq_online(unsigned int cpu)
+{
+ cpufreq_online(cpu);
+
+ return 0;
+}
+
+static int cpuhp_cpufreq_offline(unsigned int cpu)
+{
+ cpufreq_offline(cpu);
+
+ return 0;
+}
+
/**
* cpufreq_register_driver - register a CPU Frequency driver
* @driver_data: A struct cpufreq_driver containing the values#
}
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
- cpufreq_online,
- cpufreq_offline);
+ cpuhp_cpufreq_online,
+ cpuhp_cpufreq_offline);
if (ret < 0)
goto err_if_unreg;
hp_online = ret;
ctx->dev = caam_jr_alloc();
if (IS_ERR(ctx->dev)) {
- dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n");
+ pr_err("Job Ring Device allocation for transform failed\n");
return PTR_ERR(ctx->dev);
}
/* Try to run it through DECO0 */
ret = run_descriptor_deco0(ctrldev, desc, &status);
- if (ret || status) {
+ if (ret ||
+ (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
dev_err(ctrldev,
"Failed to deinstantiate RNG4 SH%d\n",
sh_idx);
struct device *ctrldev;
struct caam_drv_private *ctrlpriv;
struct caam_ctrl __iomem *ctrl;
- int ring;
ctrldev = &pdev->dev;
ctrlpriv = dev_get_drvdata(ctrldev);
ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl;
- /* Remove platform devices for JobRs */
- for (ring = 0; ring < ctrlpriv->total_jobrs; ring++)
- of_device_unregister(ctrlpriv->jrpdev[ring]);
+ /* Remove platform devices under the crypto node */
+ of_platform_depopulate(ctrldev);
/* De-initialize RNG state handles initialized by this driver. */
if (ctrlpriv->rng4_sh_init)
DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
#endif
+static const struct of_device_id caam_match[] = {
+ {
+ .compatible = "fsl,sec-v4.0",
+ },
+ {
+ .compatible = "fsl,sec4.0",
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, caam_match);
+
/* Probe routine for CAAM top (controller) level */
static int caam_probe(struct platform_device *pdev)
{
- int ret, ring, ridx, rspec, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
+ int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
u64 caam_id;
struct device *dev;
struct device_node *nprop, *np;
goto iounmap_ctrl;
}
- /*
- * Detect and enable JobRs
- * First, find out how many ring spec'ed, allocate references
- * for all, then go probe each one.
- */
- rspec = 0;
- for_each_available_child_of_node(nprop, np)
- if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
- of_device_is_compatible(np, "fsl,sec4.0-job-ring"))
- rspec++;
-
- ctrlpriv->jrpdev = devm_kcalloc(&pdev->dev, rspec,
- sizeof(*ctrlpriv->jrpdev), GFP_KERNEL);
- if (ctrlpriv->jrpdev == NULL) {
- ret = -ENOMEM;
+ ret = of_platform_populate(nprop, caam_match, NULL, dev);
+ if (ret) {
+ dev_err(dev, "JR platform devices creation error\n");
goto iounmap_ctrl;
}
ring = 0;
- ridx = 0;
- ctrlpriv->total_jobrs = 0;
for_each_available_child_of_node(nprop, np)
if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
of_device_is_compatible(np, "fsl,sec4.0-job-ring")) {
- ctrlpriv->jrpdev[ring] =
- of_platform_device_create(np, NULL, dev);
- if (!ctrlpriv->jrpdev[ring]) {
- pr_warn("JR physical index %d: Platform device creation error\n",
- ridx);
- ridx++;
- continue;
- }
ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *)
((__force uint8_t *)ctrl +
- (ridx + JR_BLOCK_NUMBER) *
+ (ring + JR_BLOCK_NUMBER) *
BLOCK_OFFSET
);
ctrlpriv->total_jobrs++;
ring++;
- ridx++;
- }
+ }
/* Check to see if QI present. If so, enable */
ctrlpriv->qi_present =
return ret;
}
-static struct of_device_id caam_match[] = {
- {
- .compatible = "fsl,sec-v4.0",
- },
- {
- .compatible = "fsl,sec4.0",
- },
- {},
-};
-MODULE_DEVICE_TABLE(of, caam_match);
-
static struct platform_driver caam_driver = {
.driver = {
.name = "caam",
struct caam_drv_private {
struct device *dev;
- struct platform_device **jrpdev; /* Alloc'ed array per sub-device */
struct platform_device *pdev;
/* Physical-presence section */
status = __gop_query32(sys_table_arg, gop32, &info, &size,
¤t_fb_base);
- if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+ info->pixel_format != PIXEL_BLT_ONLY) {
/*
* Systems that use the UEFI Console Splitter may
* provide multiple GOP devices, not all of which are
status = __gop_query64(sys_table_arg, gop64, &info, &size,
¤t_fb_base);
- if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+ info->pixel_format != PIXEL_BLT_ONLY) {
/*
* Systems that use the UEFI Console Splitter may
* provide multiple GOP devices, not all of which are
if (!fence) {
event_free(gpu, event);
ret = -ENOMEM;
- goto out_pm_put;
+ goto out_unlock;
}
gpu->event[event].fence = fence;
hangcheck_timer_reset(gpu);
ret = 0;
+out_unlock:
mutex_unlock(&gpu->lock);
out_pm_put:
{
int ret;
- if (vgpu->failsafe)
- return 0;
-
if (WARN_ON(bytes > 4))
return -EINVAL;
_EL_OFFSET_STATUS_PTR);
ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
- ctx_status_ptr.read_ptr = ctx_status_ptr.write_ptr = 0x7;
+ ctx_status_ptr.read_ptr = 0;
+ ctx_status_ptr.write_ptr = 0x7;
vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
}
struct gvt_firmware_header *h;
void *firmware;
void *p;
- unsigned long size;
+ unsigned long size, crc32_start;
int i;
int ret;
- size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
+ size = sizeof(*h) + info->mmio_size + info->cfg_space_size;
firmware = vzalloc(size);
if (!firmware)
return -ENOMEM;
memcpy(gvt->firmware.mmio, p, info->mmio_size);
+ crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+ h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start);
+
firmware_attr.size = size;
firmware_attr.private = firmware;
firmware->mmio = mem;
- sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state",
+ sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%02x.golden_hw_state",
GVT_FIRMWARE_PATH, pdev->vendor, pdev->device,
pdev->revision);
.vgpu_create = intel_gvt_create_vgpu,
.vgpu_destroy = intel_gvt_destroy_vgpu,
.vgpu_reset = intel_gvt_reset_vgpu,
+ .vgpu_activate = intel_gvt_activate_vgpu,
+ .vgpu_deactivate = intel_gvt_deactivate_vgpu,
};
/**
void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
unsigned int engine_mask);
void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
-
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu);
/* validating GM functions */
#define vgpu_gmadr_is_aperture(vgpu, gmadr) \
struct intel_vgpu_type *);
void (*vgpu_destroy)(struct intel_vgpu *);
void (*vgpu_reset)(struct intel_vgpu *);
+ void (*vgpu_activate)(struct intel_vgpu *);
+ void (*vgpu_deactivate)(struct intel_vgpu *);
};
if (ret)
goto undo_group;
+ intel_gvt_ops->vgpu_activate(vgpu);
+
atomic_set(&vgpu->vdev.released, 0);
return ret;
if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
return;
+ intel_gvt_ops->vgpu_deactivate(vgpu);
+
ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
&vgpu->vdev.iommu_notifier);
WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
{
- struct intel_vgpu *vgpu = info->vgpu;
-
- if (!info) {
- gvt_vgpu_err("kvmgt_guest_info invalid\n");
- return false;
- }
-
kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
kvm_put_kvm(info->kvm);
kvmgt_protect_table_destroy(info);
char *name;
} vgpu_types[] = {
/* Fixed vGPU type table */
- { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" },
+ { MB_TO_BYTES(64), MB_TO_BYTES(384), 4, GVT_EDID_1024_768, "8" },
{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
}
/**
- * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * intel_gvt_active_vgpu - activate a virtual GPU
* @vgpu: virtual GPU
*
- * This function is called when user wants to destroy a virtual GPU.
+ * This function is called when user wants to activate a virtual GPU.
*
*/
-void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
+{
+ mutex_lock(&vgpu->gvt->lock);
+ vgpu->active = true;
+ mutex_unlock(&vgpu->gvt->lock);
+}
+
+/**
+ * intel_gvt_deactive_vgpu - deactivate a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to deactivate a virtual GPU.
+ * All virtual GPU runtime information will be destroyed.
+ *
+ */
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
{
struct intel_gvt *gvt = vgpu->gvt;
mutex_lock(&gvt->lock);
vgpu->active = false;
- idr_remove(&gvt->vgpu_idr, vgpu->id);
if (atomic_read(&vgpu->running_workload_num)) {
mutex_unlock(&gvt->lock);
}
intel_vgpu_stop_schedule(vgpu);
+
+ mutex_unlock(&gvt->lock);
+}
+
+/**
+ * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to destroy a virtual GPU.
+ *
+ */
+void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+
+ mutex_lock(&gvt->lock);
+
+ WARN(vgpu->active, "vGPU is still active!\n");
+
+ idr_remove(&gvt->vgpu_idr, vgpu->id);
intel_vgpu_clean_sched_policy(vgpu);
intel_vgpu_clean_gvt_context(vgpu);
intel_vgpu_clean_execlist(vgpu);
if (ret)
goto out_clean_shadow_ctx;
- vgpu->active = true;
mutex_unlock(&gvt->lock);
return vgpu;
goto out;
}
- intel_guc_suspend(dev_priv);
-
intel_display_suspend(dev);
intel_dp_mst_suspend(dev);
func(has_resource_streamer); \
func(has_runtime_pm); \
func(has_snoop); \
+ func(unfenced_needs_alignment); \
func(cursor_needs_physical); \
func(hws_needs_physical); \
func(overlay_needs_physical); \
i915_gem_context_lost(dev_priv);
mutex_unlock(&dev->struct_mutex);
+ intel_guc_suspend(dev_priv);
+
cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
cancel_delayed_work_sync(&dev_priv->gt.retire_work);
struct list_head ordered_vmas;
struct list_head pinned_vmas;
bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4;
+ bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment;
int retry;
vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
if (!has_fenced_gpu_access)
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
need_fence =
- entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
+ (entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
+ needs_unfenced_map) &&
i915_gem_object_is_tiled(obj);
need_mappable = need_fence || need_reloc_mappable(vma);
struct i915_ggtt *ggtt = &dev_priv->ggtt;
if (unlikely(ggtt->do_idle_maps)) {
- if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) {
+ if (i915_gem_wait_for_idle(dev_priv, 0)) {
DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
/* Wait a bit, in hopes it avoids the hang */
udelay(10);
static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
{
+ /* The timeline struct (as part of the ppgtt underneath a context)
+ * may be freed when the request is no longer in use by the GPU.
+ * We could extend the life of a context to beyond that of all
+ * fences, possibly keeping the hw resource around indefinitely,
+ * or we just give them a false name. Since
+ * dma_fence_ops.get_timeline_name is a debug feature, the occasional
+ * lie seems justifiable.
+ */
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+ return "signaled";
+
return to_request(fence)->timeline->common->name;
}
BUG();
}
+static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock)
+{
+ if (!unlock)
+ return;
+
+ mutex_unlock(&dev->struct_mutex);
+
+ /* expedite the RCU grace period to free some request slabs */
+ synchronize_rcu_expedited();
+}
+
static bool any_vma_pinned(struct drm_i915_gem_object *obj)
{
struct i915_vma *vma;
intel_runtime_pm_put(dev_priv);
i915_gem_retire_requests(dev_priv);
- if (unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
- /* expedite the RCU grace period to free some request slabs */
- synchronize_rcu_expedited();
+ i915_gem_shrinker_unlock(&dev_priv->drm, unlock);
return count;
}
count += obj->base.size >> PAGE_SHIFT;
}
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+ i915_gem_shrinker_unlock(dev, unlock);
return count;
}
sc->nr_to_scan - freed,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND);
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+
+ i915_gem_shrinker_unlock(dev, unlock);
return freed;
}
struct shrinker_lock_uninterruptible *slu)
{
dev_priv->mm.interruptible = slu->was_interruptible;
- if (slu->unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
+ i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock);
}
static int
.has_overlay = 1, .overlay_needs_physical = 1, \
.has_gmch_display = 1, \
.hws_needs_physical = 1, \
+ .unfenced_needs_alignment = 1, \
.ring_mask = RENDER_RING, \
GEN_DEFAULT_PIPEOFFSETS, \
CURSOR_OFFSETS
.platform = INTEL_I915G, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i915gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945g_info = {
.has_hotplug = 1, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_g33_info = {
*/
if (WARN_ON(stream->sample_flags != props->sample_flags)) {
ret = -ENODEV;
- goto err_alloc;
+ goto err_flags;
}
list_add(&stream->link, &dev_priv->perf.streams);
err_open:
list_del(&stream->link);
+err_flags:
if (stream->ops->destroy)
stream->ops->destroy(stream);
err_alloc:
if (ret)
return ret;
+ if (id == 0 || id >= DRM_I915_PERF_PROP_MAX) {
+ DRM_DEBUG("Unknown i915 perf property ID\n");
+ return -EINVAL;
+ }
+
switch ((enum drm_i915_perf_property_id)id) {
case DRM_I915_PERF_PROP_CTX_HANDLE:
props->single_context = 1;
props->oa_periodic = true;
props->oa_period_exponent = value;
break;
- default:
+ case DRM_I915_PERF_PROP_MAX:
MISSING_CASE(id);
- DRM_DEBUG("Unknown i915 perf property ID\n");
return -EINVAL;
}
static struct intel_engine_cs *
pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
{
- struct intel_engine_cs *engine;
+ struct intel_engine_cs *engine =
+ container_of(pt, struct drm_i915_gem_request, priotree)->engine;
+
+ GEM_BUG_ON(!locked);
- engine = container_of(pt,
- struct drm_i915_gem_request,
- priotree)->engine;
if (engine != locked) {
- if (locked)
- spin_unlock_irq(&locked->timeline->lock);
- spin_lock_irq(&engine->timeline->lock);
+ spin_unlock(&locked->timeline->lock);
+ spin_lock(&engine->timeline->lock);
}
return engine;
static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
{
- struct intel_engine_cs *engine = NULL;
+ struct intel_engine_cs *engine;
struct i915_dependency *dep, *p;
struct i915_dependency stack;
LIST_HEAD(dfs);
list_for_each_entry_safe(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
- list_for_each_entry(p, &pt->signalers_list, signal_link)
+ /* Within an engine, there can be no cycle, but we may
+ * refer to the same dependency chain multiple times
+ * (redundant dependencies are not eliminated) and across
+ * engines.
+ */
+ list_for_each_entry(p, &pt->signalers_list, signal_link) {
+ GEM_BUG_ON(p->signaler->priority < pt->priority);
if (prio > READ_ONCE(p->signaler->priority))
list_move_tail(&p->dfs_link, &dfs);
+ }
list_safe_reset_next(dep, p, dfs_link);
- if (!RB_EMPTY_NODE(&pt->node))
- continue;
-
- engine = pt_lock_engine(pt, engine);
-
- /* If it is not already in the rbtree, we can update the
- * priority inplace and skip over it (and its dependencies)
- * if it is referenced *again* as we descend the dfs.
- */
- if (prio > pt->priority && RB_EMPTY_NODE(&pt->node)) {
- pt->priority = prio;
- list_del_init(&dep->dfs_link);
- }
}
+ engine = request->engine;
+ spin_lock_irq(&engine->timeline->lock);
+
/* Fifo and depth-first replacement ensure our deps execute before us */
list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
if (prio <= pt->priority)
continue;
- GEM_BUG_ON(RB_EMPTY_NODE(&pt->node));
-
pt->priority = prio;
- rb_erase(&pt->node, &engine->execlist_queue);
- if (insert_request(pt, &engine->execlist_queue))
- engine->execlist_first = &pt->node;
+ if (!RB_EMPTY_NODE(&pt->node)) {
+ rb_erase(&pt->node, &engine->execlist_queue);
+ if (insert_request(pt, &engine->execlist_queue))
+ engine->execlist_first = &pt->node;
+ }
}
- if (engine)
- spin_unlock_irq(&engine->timeline->lock);
+ spin_unlock_irq(&engine->timeline->lock);
/* XXX Do we need to preempt to make room for us and our deps? */
}
GEM_BUG_ON(request->ctx != port[0].request->ctx);
/* Reset WaIdleLiteRestore:bdw,skl as well */
- request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
+ request->tail =
+ intel_ring_wrap(request->ring,
+ request->wa_tail - WA_TAIL_DWORDS*sizeof(u32));
}
static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
*/
}
+static inline u32
+intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+ return pos & (ring->size - 1);
+}
+
static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr)
{
/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
u32 offset = addr - ring->vaddr;
- return offset & (ring->size - 1);
+ return intel_ring_wrap(ring, offset);
}
int __intel_ring_space(int head, int tail, int size);
{
struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
__drm_atomic_helper_plane_destroy_state(&asyw->state);
- dma_fence_put(asyw->state.fence);
kfree(asyw);
}
if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL)))
return NULL;
__drm_atomic_helper_plane_duplicate_state(plane, &asyw->state);
- asyw->state.fence = NULL;
asyw->interval = 1;
asyw->sema = armw->sema;
asyw->ntfy = armw->ntfy;
u32 vbackp = (mode->vtotal - mode->vsync_end) * vscan / ilace;
u32 hfrontp = mode->hsync_start - mode->hdisplay;
u32 vfrontp = (mode->vsync_start - mode->vdisplay) * vscan / ilace;
+ u32 blankus;
struct nv50_head_mode *m = &asyh->mode;
m->h.active = mode->htotal;
m->v.blanks = m->v.active - vfrontp - 1;
/*XXX: Safe underestimate, even "0" works */
- m->v.blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
- m->v.blankus *= 1000;
- m->v.blankus /= mode->clock;
+ blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
+ blankus *= 1000;
+ blankus /= mode->clock;
+ m->v.blankus = blankus;
if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
m->v.blank2e = m->v.active + m->v.synce + vbackp;
.i2c = nv04_i2c_new,
.imem = nv40_instmem_new,
.mc = nv44_mc_new,
- .mmu = nv44_mmu_new,
+ .mmu = nv04_mmu_new,
.pci = nv40_pci_new,
.therm = nv40_therm_new,
.timer = nv41_timer_new,
.fifo = gp100_fifo_new,
};
+static const struct nvkm_device_chip
+nv137_chipset = {
+ .name = "GP107",
+ .bar = gf100_bar_new,
+ .bios = nvkm_bios_new,
+ .bus = gf100_bus_new,
+ .devinit = gm200_devinit_new,
+ .fb = gp102_fb_new,
+ .fuse = gm107_fuse_new,
+ .gpio = gk104_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .ltc = gp100_ltc_new,
+ .mc = gp100_mc_new,
+ .mmu = gf100_mmu_new,
+ .pci = gp100_pci_new,
+ .pmu = gp102_pmu_new,
+ .timer = gk20a_timer_new,
+ .top = gk104_top_new,
+ .ce[0] = gp102_ce_new,
+ .ce[1] = gp102_ce_new,
+ .ce[2] = gp102_ce_new,
+ .ce[3] = gp102_ce_new,
+ .disp = gp102_disp_new,
+ .dma = gf119_dma_new,
+ .fifo = gp100_fifo_new,
+};
+
static int
nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
struct nvkm_notify *notify)
case 0x132: device->chip = &nv132_chipset; break;
case 0x134: device->chip = &nv134_chipset; break;
case 0x136: device->chip = &nv136_chipset; break;
+ case 0x137: device->chip = &nv137_chipset; break;
default:
nvdev_error(device, "unknown chipset (%08x)\n", boot0);
goto done;
}
if (type == 0x00000010) {
- if (!nv31_mpeg_mthd(mpeg, mthd, data))
+ if (nv31_mpeg_mthd(mpeg, mthd, data))
show &= ~0x01000000;
}
}
}
if (type == 0x00000010) {
- if (!nv44_mpeg_mthd(subdev->device, mthd, data))
+ if (nv44_mpeg_mthd(subdev->device, mthd, data))
show &= ~0x01000000;
}
}
#include <linux/slab.h>
#include <linux/fb.h>
#include <linux/prefetch.h>
+#include <asm/unaligned.h>
#include <drm/drmP.h>
#include "udl_drv.h"
const u8 *const start = pixel;
const uint16_t repeating_pixel_val16 = pixel_val16;
- *(uint16_t *)cmd = cpu_to_be16(pixel_val16);
+ put_unaligned_be16(pixel_val16, cmd);
cmd += 2;
pixel += bpp;
hid->group = HID_GROUP_WACOM;
break;
case USB_VENDOR_ID_SYNAPTICS:
- if (hid->group == HID_GROUP_GENERIC ||
- hid->group == HID_GROUP_MULTITOUCH_WIN_8)
+ if (hid->group == HID_GROUP_GENERIC)
if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC)
&& (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER))
/*
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SMARTJOY_PLUS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SUPER_JOY_BOX_3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD) },
#define USB_DEVICE_ID_UGEE_TABLET_45 0x0045
#define USB_DEVICE_ID_YIYNOVA_TABLET 0x004d
+#define USB_VENDOR_ID_UGEE 0x28bd
+#define USB_DEVICE_ID_UGEE_TABLET_EX07S 0x0071
+
#define USB_VENDOR_ID_UNITEC 0x227d
#define USB_DEVICE_ID_UNITEC_USB_TOUCH_0709 0x0709
#define USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19 0x0a19
}
break;
case USB_DEVICE_ID_UGTIZER_TABLET_GP0610:
+ case USB_DEVICE_ID_UGEE_TABLET_EX07S:
/* If this is the pen interface */
if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
rc = uclogic_tablet_enable(hdev);
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
{ }
};
MODULE_DEVICE_TABLE(hid, uclogic_devices);
name = "accel_3d";
channel_spec = accel_3d_channels;
channel_size = sizeof(accel_3d_channels);
+ indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
} else {
name = "gravity";
channel_spec = gravity_channels;
channel_size = sizeof(gravity_channels);
+ indio_dev->num_channels = ARRAY_SIZE(gravity_channels);
}
ret = hid_sensor_parse_common_attributes(hsdev, hsdev->usage,
&accel_state->common_attributes);
goto error_free_dev_mem;
}
- indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
indio_dev->dev.parent = &pdev->dev;
indio_dev->info = &accel_3d_info;
indio_dev->name = name;
ret = st->core.read_ec_sensors_data(indio_dev, 1 << idx, &data);
if (ret < 0)
break;
-
+ ret = IIO_VAL_INT;
*val = data;
break;
case IIO_CHAN_INFO_CALIBBIAS:
for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++)
st->core.calib[i] =
st->core.resp->sensor_offset.offset[i];
-
+ ret = IIO_VAL_INT;
*val = st->core.calib[idx];
break;
case IIO_CHAN_INFO_SCALE:
{
struct hid_sensor_hub_attribute_info timestamp;
+ s32 value;
+ int ret;
hid_sensor_get_reporting_interval(hsdev, usage_id, st);
st->sensitivity.index, st->sensitivity.report_id,
timestamp.index, timestamp.report_id);
+ ret = sensor_hub_get_feature(hsdev,
+ st->power_state.report_id,
+ st->power_state.index, sizeof(value), &value);
+ if (ret < 0)
+ return ret;
+ if (value < 0)
+ return -EINVAL;
+
return 0;
}
EXPORT_SYMBOL(hid_sensor_parse_common_attributes);
#include <linux/iio/trigger_consumer.h>
#include <linux/iio/triggered_buffer.h>
#include <linux/regmap.h>
+#include <linux/delay.h>
#include "bmg160.h"
#define BMG160_IRQ_NAME "bmg160_event"
#define BMG160_DEF_BW 100
#define BMG160_REG_PMU_BW_RES BIT(7)
+#define BMG160_GYRO_REG_RESET 0x14
+#define BMG160_GYRO_RESET_VAL 0xb6
+
#define BMG160_REG_INT_MAP_0 0x17
#define BMG160_INT_MAP_0_BIT_ANY BIT(1)
int ret;
unsigned int val;
+ /*
+ * Reset chip to get it in a known good state. A delay of 30ms after
+ * reset is required according to the datasheet.
+ */
+ regmap_write(data->regmap, BMG160_GYRO_REG_RESET,
+ BMG160_GYRO_RESET_VAL);
+ usleep_range(30000, 30700);
+
ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val);
if (ret < 0) {
dev_err(dev, "Error reading reg_chip_id\n");
tmp0 = (int)div_s64_rem(tmp, 1000000000, &tmp1);
return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_FRACTIONAL_LOG2:
- tmp = (s64)vals[0] * 1000000000LL >> vals[1];
- tmp1 = do_div(tmp, 1000000000LL);
- tmp0 = tmp;
- return snprintf(buf, len, "%d.%09u", tmp0, tmp1);
+ tmp = shift_right((s64)vals[0] * 1000000000LL, vals[1]);
+ tmp0 = (int)div_s64_rem(tmp, 1000000000LL, &tmp1);
+ return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_INT_MULTIPLE:
{
int i;
.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
},
.multi_read_bit = true,
+ .bootime = 2,
},
};
rx_wr->sg_list = &rx_desc->rx_sg;
rx_wr->num_sge = 1;
rx_wr->next = rx_wr + 1;
+ rx_desc->in_use = false;
}
rx_wr--;
rx_wr->next = NULL; /* mark end of work requests list */
struct ib_recv_wr *rx_wr_failed, rx_wr;
int ret;
+ if (!rx_desc->in_use) {
+ /*
+ * if the descriptor is not in-use we already reposted it
+ * for recv, so just silently return
+ */
+ return 0;
+ }
+
+ rx_desc->in_use = false;
rx_wr.wr_cqe = &rx_desc->rx_cqe;
rx_wr.sg_list = &rx_desc->rx_sg;
rx_wr.num_sge = 1;
return;
}
+ rx_desc->in_use = true;
+
ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
ret = isert_check_pi_status(cmd, isert_cmd->rw.sig->sig_mr);
isert_rdma_rw_ctx_destroy(isert_cmd, isert_conn);
- if (ret)
- transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0);
- else
- isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+ if (ret) {
+ /*
+ * transport_generic_request_failure() expects to have
+ * plus two references to handle queue-full, so re-add
+ * one here as target-core will have already dropped
+ * it after the first isert_put_datain() callback.
+ */
+ kref_get(&cmd->cmd_kref);
+ transport_generic_request_failure(cmd, cmd->pi_err);
+ } else {
+ /*
+ * XXX: isert_put_response() failure is not retried.
+ */
+ ret = isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+ if (ret)
+ pr_warn_ratelimited("isert_put_response() ret: %d\n", ret);
+ }
}
static void
cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
spin_unlock_bh(&cmd->istate_lock);
- if (ret) {
- target_put_sess_cmd(se_cmd);
- transport_send_check_condition_and_sense(se_cmd,
- se_cmd->pi_err, 0);
- } else {
+ /*
+ * transport_generic_request_failure() will drop the extra
+ * se_cmd->cmd_kref reference after T10-PI error, and handle
+ * any non-zero ->queue_status() callback error retries.
+ */
+ if (ret)
+ transport_generic_request_failure(se_cmd, se_cmd->pi_err);
+ else
target_execute_cmd(se_cmd);
- }
}
static void
chain_wr = &isert_cmd->tx_desc.send_wr;
}
- isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
- isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ\n", isert_cmd);
- return 1;
+ rc = isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
+ isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ rc: %d\n",
+ isert_cmd, rc);
+ return rc;
}
static int
isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
{
struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+ int ret;
isert_dbg("Cmd: %p RDMA_READ data_length: %u write_data_done: %u\n",
isert_cmd, cmd->se_cmd.data_length, cmd->write_data_done);
isert_cmd->tx_desc.tx_cqe.done = isert_rdma_read_done;
- isert_rdma_rw_ctx_post(isert_cmd, conn->context,
- &isert_cmd->tx_desc.tx_cqe, NULL);
+ ret = isert_rdma_rw_ctx_post(isert_cmd, conn->context,
+ &isert_cmd->tx_desc.tx_cqe, NULL);
- isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
- isert_cmd);
- return 0;
+ isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE rc: %d\n",
+ isert_cmd, ret);
+ return ret;
}
static int
#define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
- sizeof(struct ib_cqe)))
+ sizeof(struct ib_cqe) + sizeof(bool)))
#define ISCSI_ISER_SG_TABLESIZE 256
u64 dma_addr;
struct ib_sge rx_sg;
struct ib_cqe rx_cqe;
+ bool in_use;
char pad[ISER_RX_PAD_SIZE];
} __packed;
{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
{ 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+ { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */
XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */
+ XPAD_XBOXONE_VENDOR(0x1532), /* Razer Wildcat */
XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */
return -ENOMEM;
}
+ raw_spin_lock_init(&cd->rlock);
+
cd->gpc_base = of_iomap(node, 0);
if (!cd->gpc_base) {
pr_err("fsl-gpcv2: unable to map gpc registers\n");
*result = true;
r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
- from_cblock(begin), &cmd->dirty_cursor);
+ from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__);
return r;
return 0;
}
+ begin = to_cblock(from_cblock(begin) + 1);
+ if (begin == end)
+ break;
+
r = dm_bitset_cursor_next(&cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__);
dm_bitset_cursor_end(&cmd->dirty_cursor);
return r;
}
-
- begin = to_cblock(from_cblock(begin) + 1);
}
dm_bitset_cursor_end(&cmd->dirty_cursor);
return r;
/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
- if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+ if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
to_bytes(rs->requested_bitmap_chunk_sectors), 0);
/* Undo dm_start_request() before requeuing */
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
+ blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
return BLK_MQ_RQ_QUEUE_BUSY;
}
block = fec_buffer_rs_block(v, fio, n, i);
res = fec_decode_rs8(v, fio, block, &par[offset], neras);
if (res < 0) {
- dm_bufio_release(buf);
-
r = res;
goto error;
}
done:
r = corrected;
error:
+ dm_bufio_release(buf);
+
if (r < 0 && neras)
DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
v->data_dev->name, (unsigned long long)rsb, r);
&is_zero) == 0) {
/* skip known zero blocks entirely */
if (is_zero)
- continue;
+ goto done;
/*
* skip if we have already found the theoretical
if (!verity_fec_is_enabled(v))
return -EOPNOTSUPP;
+ if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) {
+ DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name);
+ return -EIO;
+ }
+
+ fio->level++;
+
if (type == DM_VERITY_BLOCK_TYPE_METADATA)
block += v->data_blocks;
if (r < 0) {
r = fec_decode_rsb(v, io, fio, rsb, offset, true);
if (r < 0)
- return r;
+ goto done;
}
if (dest)
r = verity_for_bv_block(v, io, iter, fec_bv_copy);
}
+done:
+ fio->level--;
return r;
}
memset(fio->bufs, 0, sizeof(fio->bufs));
fio->nbufs = 0;
fio->output = NULL;
+ fio->level = 0;
}
/*
#define DM_VERITY_FEC_BUF_MAX \
(1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
+/* maximum recursion level for verity_fec_decode */
+#define DM_VERITY_FEC_MAX_RECURSION 4
+
#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device"
#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks"
#define DM_VERITY_OPT_FEC_START "fec_start"
unsigned nbufs; /* number of buffers allocated */
u8 *output; /* buffer for corrected output */
size_t output_pos;
+ unsigned level; /* recursion level */
};
#ifdef CONFIG_DM_VERITY_FEC
int work_done = 0;
u32 stcmd = readl(priv->base + IFI_CANFD_STCMD);
- u32 rxstcmd = readl(priv->base + IFI_CANFD_STCMD);
+ u32 rxstcmd = readl(priv->base + IFI_CANFD_RXSTCMD);
u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR);
/* Handle bus state changes */
devm_can_led_init(ndev);
- dev_info(&pdev->dev, "device registered (regs @ %p, IRQ%d)\n",
- priv->regs, ndev->irq);
+ dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq);
return 0;
fail_candev:
#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
-static void ___team_compute_features(struct team *team)
+static void __team_compute_features(struct team *team)
{
struct team_port *port;
u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
}
-static void __team_compute_features(struct team *team)
-{
- ___team_compute_features(team);
- netdev_change_features(team->dev);
-}
-
static void team_compute_features(struct team *team)
{
mutex_lock(&team->lock);
- ___team_compute_features(team);
+ __team_compute_features(team);
mutex_unlock(&team->lock);
netdev_change_features(team->dev);
}
team_notify_peers_fini(team);
team_queue_override_fini(team);
mutex_unlock(&team->lock);
+ netdev_change_features(dev);
}
static void team_destructor(struct net_device *dev)
mutex_lock(&team->lock);
err = team_port_add(team, port_dev);
mutex_unlock(&team->lock);
+
+ if (!err)
+ netdev_change_features(dev);
+
return err;
}
mutex_lock(&team->lock);
err = team_port_del(team, port_dev);
mutex_unlock(&team->lock);
+
+ if (!err)
+ netdev_change_features(dev);
+
return err;
}
{QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
- {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */
{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */
{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */
{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */
" value=0x%04x index=0x%04x size=%d\n",
cmd, reqtype, value, index, size);
- if (data) {
+ if (size) {
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
goto out;
err = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
cmd, reqtype, value, index, buf, size,
USB_CTRL_GET_TIMEOUT);
- if (err > 0 && err <= size)
- memcpy(data, buf, err);
+ if (err > 0 && err <= size) {
+ if (data)
+ memcpy(data, buf, err);
+ else
+ netdev_dbg(dev->net,
+ "Huh? Data requested but thrown away.\n");
+ }
kfree(buf);
out:
return err;
buf = kmemdup(data, size, GFP_KERNEL);
if (!buf)
goto out;
- }
+ } else {
+ if (size) {
+ WARN_ON_ONCE(1);
+ err = -EINVAL;
+ goto out;
+ }
+ }
err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
cmd, reqtype, value, index, buf, size,
#define MIN_MTU ETH_MIN_MTU
#define MAX_MTU ETH_MAX_MTU
-static int virtnet_probe(struct virtio_device *vdev)
+static int virtnet_validate(struct virtio_device *vdev)
{
- int i, err;
- struct net_device *dev;
- struct virtnet_info *vi;
- u16 max_queue_pairs;
- int mtu;
-
if (!vdev->config->get) {
dev_err(&vdev->dev, "%s failure: config access disabled\n",
__func__);
if (!virtnet_validate_features(vdev))
return -EINVAL;
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
+ int mtu = virtio_cread16(vdev,
+ offsetof(struct virtio_net_config,
+ mtu));
+ if (mtu < MIN_MTU)
+ __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+ }
+
+ return 0;
+}
+
+static int virtnet_probe(struct virtio_device *vdev)
+{
+ int i, err;
+ struct net_device *dev;
+ struct virtnet_info *vi;
+ u16 max_queue_pairs;
+ int mtu;
+
/* Find if host supports multiqueue virtio_net device */
err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ,
struct virtio_net_config,
offsetof(struct virtio_net_config,
mtu));
if (mtu < dev->min_mtu) {
- __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
- } else {
- dev->mtu = mtu;
- dev->max_mtu = mtu;
+ /* Should never trigger: MTU was previously validated
+ * in virtnet_validate.
+ */
+ dev_err(&vdev->dev, "device MTU appears to have changed "
+ "it is now %d < %d", mtu, dev->min_mtu);
+ goto free_stats;
}
+
+ dev->mtu = mtu;
+ dev->max_mtu = mtu;
+
+ /* TODO: size buffers correctly in this case. */
+ if (dev->mtu > ETH_DATA_LEN)
+ vi->big_packets = true;
}
if (vi->any_header_sg)
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = id_table,
+ .validate = virtnet_validate,
.probe = virtnet_probe,
.remove = virtnet_remove,
.config_changed = virtnet_config_changed,
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd->dsm.nr = segments - 1;
+ cmnd->dsm.nr = cpu_to_le32(segments - 1);
cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
req->special_vec.bv_page = virt_to_page(range);
u16 status;
WARN_ON(req == NULL || slog == NULL);
- if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+ if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF))
status = nvmet_get_smart_log_all(req, slog);
else
status = nvmet_get_smart_log_nsid(req, slog);
sector = le64_to_cpu(write_zeroes->slba) <<
(req->ns->blksize_shift - 9);
- nr_sector = (((sector_t)le32_to_cpu(write_zeroes->length)) <<
+ nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) <<
(req->ns->blksize_shift - 9)) + 1;
if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
return 0;
case nvme_cmd_dsm:
req->execute = nvmet_execute_dsm;
- req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
+ req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
sizeof(struct nvme_dsm_range);
return 0;
case nvme_cmd_write_zeroes:
depends on PCI_MSI_IRQ_DOMAIN
select PCIEPORTBUS
select PCIE_DW_HOST
+ select PCI_HOST_COMMON
help
Say Y here if you want PCIe controller support on HiSilicon
Hip05 and Hip06 SoCs
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int artpec6_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
artpec6_pcie->pci = pci;
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int dw_plat_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
dw_plat_pcie->pci = pci;
index -= node * PEM_MAX_DOM_IN_NODE;
res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
FIELD_PREP(PEM_INDX_MASK, index);
- res_pem->end = res_pem->start + SZ_16M - 1;
res_pem->flags = IORESOURCE_MEM;
}
*/
if (ret) {
thunder_pem_legacy_fw(root, res_pem);
- /* Reserve PEM-specific resources and PCI configuration space */
+ /*
+ * Reserve 64K size PEM specific resources. The full 16M range
+ * size is required for thunder_pem_init() call.
+ */
+ res_pem->end = res_pem->start + SZ_64K - 1;
thunder_pem_reserve_range(dev, root->segment, res_pem);
+ res_pem->end = res_pem->start + SZ_16M - 1;
+
+ /* Reserve PCI configuration space as well. */
thunder_pem_reserve_range(dev, root->segment, &cfg->res);
}
return ERR_PTR(ret);
}
-static int pinctrl_create_and_start(struct pinctrl_dev *pctldev)
+static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
{
pctldev->p = create_pinctrl(pctldev->dev, pctldev);
- if (!IS_ERR(pctldev->p)) {
- kref_get(&pctldev->p->users);
- pctldev->hog_default =
- pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
- if (IS_ERR(pctldev->hog_default)) {
- dev_dbg(pctldev->dev,
- "failed to lookup the default state\n");
- } else {
- if (pinctrl_select_state(pctldev->p,
- pctldev->hog_default))
- dev_err(pctldev->dev,
- "failed to select default state\n");
- }
+ if (PTR_ERR(pctldev->p) == -ENODEV) {
+ dev_dbg(pctldev->dev, "no hogs found\n");
- pctldev->hog_sleep =
- pinctrl_lookup_state(pctldev->p,
- PINCTRL_STATE_SLEEP);
- if (IS_ERR(pctldev->hog_sleep))
- dev_dbg(pctldev->dev,
- "failed to lookup the sleep state\n");
+ return 0;
+ }
+
+ if (IS_ERR(pctldev->p)) {
+ dev_err(pctldev->dev, "error claiming hogs: %li\n",
+ PTR_ERR(pctldev->p));
+
+ return PTR_ERR(pctldev->p);
+ }
+
+ kref_get(&pctldev->p->users);
+ pctldev->hog_default =
+ pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
+ if (IS_ERR(pctldev->hog_default)) {
+ dev_dbg(pctldev->dev,
+ "failed to lookup the default state\n");
+ } else {
+ if (pinctrl_select_state(pctldev->p,
+ pctldev->hog_default))
+ dev_err(pctldev->dev,
+ "failed to select default state\n");
+ }
+
+ pctldev->hog_sleep =
+ pinctrl_lookup_state(pctldev->p,
+ PINCTRL_STATE_SLEEP);
+ if (IS_ERR(pctldev->hog_sleep))
+ dev_dbg(pctldev->dev,
+ "failed to lookup the sleep state\n");
+
+ return 0;
+}
+
+int pinctrl_enable(struct pinctrl_dev *pctldev)
+{
+ int error;
+
+ error = pinctrl_claim_hogs(pctldev);
+ if (error) {
+ dev_err(pctldev->dev, "could not claim hogs: %i\n",
+ error);
+ mutex_destroy(&pctldev->mutex);
+ kfree(pctldev);
+
+ return error;
}
mutex_lock(&pinctrldev_list_mutex);
return 0;
}
+EXPORT_SYMBOL_GPL(pinctrl_enable);
/**
* pinctrl_register() - register a pin controller device
if (IS_ERR(pctldev))
return pctldev;
- error = pinctrl_create_and_start(pctldev);
- if (error) {
- mutex_destroy(&pctldev->mutex);
- kfree(pctldev);
-
+ error = pinctrl_enable(pctldev);
+ if (error)
return ERR_PTR(error);
- }
return pctldev;
}
EXPORT_SYMBOL_GPL(pinctrl_register);
+/**
+ * pinctrl_register_and_init() - register and init pin controller device
+ * @pctldesc: descriptor for this pin controller
+ * @dev: parent device for this pin controller
+ * @driver_data: private pin controller data for this pin controller
+ * @pctldev: pin controller device
+ *
+ * Note that pinctrl_enable() still needs to be manually called after
+ * this once the driver is ready.
+ */
int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev)
{
struct pinctrl_dev *p;
- int error;
p = pinctrl_init_controller(pctldesc, dev, driver_data);
if (IS_ERR(p))
*/
*pctldev = p;
- error = pinctrl_create_and_start(p);
- if (error) {
- mutex_destroy(&p->mutex);
- kfree(p);
- *pctldev = NULL;
-
- return error;
- }
-
return 0;
}
EXPORT_SYMBOL_GPL(pinctrl_register_and_init);
dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
- return 0;
+ return pinctrl_enable(ipctl->pctl);
free:
imx_free_resources(ipctl);
* published by the Free Software Foundation.
*/
+#include <linux/dmi.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
chained_irq_exit(chip, desc);
}
+/*
+ * Certain machines seem to hardcode Linux IRQ numbers in their ACPI
+ * tables. Since we leave GPIOs that are not capable of generating
+ * interrupts out of the irqdomain the numbering will be different and
+ * cause devices using the hardcoded IRQ numbers fail. In order not to
+ * break such machines we will only mask pins from irqdomain if the machine
+ * is not listed below.
+ */
+static const struct dmi_system_id chv_no_valid_mask[] = {
+ {
+ /* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */
+ .ident = "Acer Chromebook (CYAN)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"),
+ DMI_MATCH(DMI_BIOS_DATE, "05/21/2016"),
+ },
+ }
+};
+
static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
{
const struct chv_gpio_pinrange *range;
struct gpio_chip *chip = &pctrl->chip;
+ bool need_valid_mask = !dmi_check_system(chv_no_valid_mask);
int ret, i, offset;
*chip = chv_gpio_chip;
chip->label = dev_name(pctrl->dev);
chip->parent = pctrl->dev;
chip->base = -1;
- chip->irq_need_valid_mask = true;
+ chip->irq_need_valid_mask = need_valid_mask;
ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl);
if (ret) {
intsel &= CHV_PADCTRL0_INTSEL_MASK;
intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
- if (intsel >= pctrl->community->nirqs)
+ if (need_valid_mask && intsel >= pctrl->community->nirqs)
clear_bit(i, chip->irq_valid_mask);
}
dev_info(pcs->dev, "%i pins at pa %p size %u\n",
pcs->desc.npins, pcs->base, pcs->size);
- return 0;
+ return pinctrl_enable(pcs->pctl);
free:
pcs_free_resources(pcs);
/* pin banks of exynos5433 pin-controller - ALIVE */
static const struct samsung_pin_bank_data exynos5433_pin_banks0[] __initconst = {
- EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
- EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
- EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
- EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
};
/* pin banks of exynos5433 pin-controller - AUD */
static const struct samsung_pin_bank_data exynos5433_pin_banks1[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
- EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
};
/* pin banks of exynos5433 pin-controller - CPIF */
static const struct samsung_pin_bank_data exynos5433_pin_banks2[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
};
/* pin banks of exynos5433 pin-controller - eSE */
static const struct samsung_pin_bank_data exynos5433_pin_banks3[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
};
/* pin banks of exynos5433 pin-controller - FINGER */
static const struct samsung_pin_bank_data exynos5433_pin_banks4[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
};
/* pin banks of exynos5433 pin-controller - FSYS */
static const struct samsung_pin_bank_data exynos5433_pin_banks5[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
- EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
- EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
- EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
- EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
- EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
};
/* pin banks of exynos5433 pin-controller - IMEM */
static const struct samsung_pin_bank_data exynos5433_pin_banks6[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
};
/* pin banks of exynos5433 pin-controller - NFC */
static const struct samsung_pin_bank_data exynos5433_pin_banks7[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
};
/* pin banks of exynos5433 pin-controller - PERIC */
static const struct samsung_pin_bank_data exynos5433_pin_banks8[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
- EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
- EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
- EXYNOS_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
- EXYNOS_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
- EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
- EXYNOS_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
- EXYNOS_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
- EXYNOS_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
- EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
- EXYNOS_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
- EXYNOS_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
- EXYNOS_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
- EXYNOS_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
- EXYNOS_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
- EXYNOS_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
- EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
};
/* pin banks of exynos5433 pin-controller - TOUCH */
static const struct samsung_pin_bank_data exynos5433_pin_banks9[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
};
/*
.name = id \
}
-#define EXYNOS_PIN_BANK_EINTW_EXT(pins, reg, id, offs, pctl_idx) \
- { \
- .type = &bank_type_alive, \
- .pctl_offset = reg, \
- .nr_pins = pins, \
- .eint_type = EINT_TYPE_WKUP, \
- .eint_offset = offs, \
- .name = id, \
- .pctl_res_idx = pctl_idx, \
- } \
-
#define EXYNOS5433_PIN_BANK_EINTG(pins, reg, id, offs) \
{ \
.type = &exynos5433_bank_type_off, \
pmx->pctl_desc.pins = pmx->pins;
pmx->pctl_desc.npins = pfc->info->nr_pins;
- return devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
- &pmx->pctl);
+ ret = devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
+ &pmx->pctl);
+ if (ret) {
+ dev_err(pfc->dev, "could not register: %i\n", ret);
+
+ return ret;
+ }
+
+ return pinctrl_enable(pmx->pctl);
}
platform_set_drvdata(pdev, iod);
+ return pinctrl_enable(iod->pctl);
+
exit_out:
of_node_put(np);
return ret;
.clk_rate = 19200000,
.npwm = 4,
.base_unit_bits = 22,
+ .bypass = true,
+};
+
+/* Tangier */
+static const struct pwm_lpss_boardinfo pwm_lpss_tng_info = {
+ .clk_rate = 19200000,
+ .npwm = 4,
+ .base_unit_bits = 22,
};
static int pwm_lpss_probe_pci(struct pci_dev *pdev,
{ PCI_VDEVICE(INTEL, 0x0ac8), (unsigned long)&pwm_lpss_bxt_info},
{ PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&pwm_lpss_byt_info},
{ PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&pwm_lpss_byt_info},
- { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_bxt_info},
+ { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_tng_info},
{ PCI_VDEVICE(INTEL, 0x1ac8), (unsigned long)&pwm_lpss_bxt_info},
{ PCI_VDEVICE(INTEL, 0x2288), (unsigned long)&pwm_lpss_bsw_info},
{ PCI_VDEVICE(INTEL, 0x2289), (unsigned long)&pwm_lpss_bsw_info},
.clk_rate = 19200000,
.npwm = 4,
.base_unit_bits = 22,
+ .bypass = true,
};
static int pwm_lpss_probe_platform(struct platform_device *pdev)
writel(value, lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM);
}
-static int pwm_lpss_update(struct pwm_device *pwm)
+static int pwm_lpss_wait_for_update(struct pwm_device *pwm)
{
struct pwm_lpss_chip *lpwm = to_lpwm(pwm->chip);
const void __iomem *addr = lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM;
u32 val;
int err;
- pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
-
/*
* PWM Configuration register has SW_UPDATE bit that is set when a new
* configuration is written to the register. The bit is automatically
pwm_lpss_write(pwm, ctrl);
}
+static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond)
+{
+ if (cond)
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+}
+
static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm,
struct pwm_state *state)
{
return ret;
}
pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
- ret = pwm_lpss_update(pwm);
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+ pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false);
+ ret = pwm_lpss_wait_for_update(pwm);
if (ret) {
pm_runtime_put(chip->dev);
return ret;
}
- pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+ pwm_lpss_cond_enable(pwm, lpwm->info->bypass == true);
} else {
ret = pwm_lpss_is_updating(pwm);
if (ret)
return ret;
pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
- return pwm_lpss_update(pwm);
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+ return pwm_lpss_wait_for_update(pwm);
}
} else if (pwm_is_enabled(pwm)) {
pwm_lpss_write(pwm, pwm_lpss_read(pwm) & ~PWM_ENABLE);
unsigned long clk_rate;
unsigned int npwm;
unsigned long base_unit_bits;
+ bool bypass;
};
struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev, struct resource *r,
return 0;
}
+static int rockchip_pwm_enable(struct pwm_chip *chip,
+ struct pwm_device *pwm,
+ bool enable,
+ enum pwm_polarity polarity)
+{
+ struct rockchip_pwm_chip *pc = to_rockchip_pwm_chip(chip);
+ int ret;
+
+ if (enable) {
+ ret = clk_enable(pc->clk);
+ if (ret)
+ return ret;
+ }
+
+ pc->data->set_enable(chip, pwm, enable, polarity);
+
+ if (!enable)
+ clk_disable(pc->clk);
+
+ return 0;
+}
+
static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
struct pwm_state *state)
{
return ret;
if (state->polarity != curstate.polarity && enabled) {
- pc->data->set_enable(chip, pwm, false, state->polarity);
+ ret = rockchip_pwm_enable(chip, pwm, false, state->polarity);
+ if (ret)
+ goto out;
enabled = false;
}
ret = rockchip_pwm_config(chip, pwm, state->duty_cycle, state->period);
if (ret) {
if (enabled != curstate.enabled)
- pc->data->set_enable(chip, pwm, !enabled,
- state->polarity);
-
+ rockchip_pwm_enable(chip, pwm, !enabled,
+ state->polarity);
goto out;
}
- if (state->enabled != enabled)
- pc->data->set_enable(chip, pwm, state->enabled,
- state->polarity);
+ if (state->enabled != enabled) {
+ ret = rockchip_pwm_enable(chip, pwm, state->enabled,
+ state->polarity);
+ if (ret)
+ goto out;
+ }
/*
* Update the state with the real hardware, which can differ a bit
scsi_starved_list_run(sdev->host);
if (q->mq_ops)
- blk_mq_start_stopped_hw_queues(q, false);
+ blk_mq_run_hw_queues(q, false);
else
blk_run_queue(q);
}
!list_empty(&sdev->host->starved_list))
kblockd_schedule_work(&sdev->requeue_work);
else
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_mq_run_hw_queues(q, true);
} else {
unsigned long flags;
case BLK_MQ_RQ_QUEUE_BUSY:
if (atomic_read(&sdev->device_busy) == 0 &&
!scsi_device_blocked(sdev))
- blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
+ blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
break;
case BLK_MQ_RQ_QUEUE_ERROR:
/*
ret = PTR_ERR(vmfile);
goto out;
}
+ vmfile->f_mode |= FMODE_LSEEK;
asma->file = vmfile;
}
get_file(asma->file);
int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
}
EXPORT_SYMBOL(iscsit_queue_rsp);
static int lio_queue_data_in(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_DATAIN;
- cmd->conn->conn_transport->iscsit_queue_data_in(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_data_in(conn, cmd);
}
static int lio_write_pending(struct se_cmd *se_cmd)
static int lio_queue_status(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_STATUS;
if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
}
- cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_status(conn, cmd);
}
static void lio_queue_tm_rsp(struct se_cmd *se_cmd)
if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH))
SET_PSTATE_REPLY_OPTIONAL(param);
/*
- * The GlobalSAN iSCSI Initiator for MacOSX does
- * not respond to MaxBurstLength, FirstBurstLength,
- * DefaultTime2Wait or DefaultTime2Retain parameter keys.
- * So, we set them to 'reply optional' here, and assume the
- * the defaults from iscsi_parameters.h if the initiator
- * is not RFC compliant and the keys are not negotiated.
- */
- if (!strcmp(param->name, MAXBURSTLENGTH))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, FIRSTBURSTLENGTH))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, DEFAULTTIME2WAIT))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, DEFAULTTIME2RETAIN))
- SET_PSTATE_REPLY_OPTIONAL(param);
- /*
* Required for gPXE iSCSI boot client
*/
if (!strcmp(param->name, MAXCONNECTIONS))
}
}
-void iscsit_add_cmd_to_response_queue(
+int iscsit_add_cmd_to_response_queue(
struct iscsi_cmd *cmd,
struct iscsi_conn *conn,
u8 state)
if (!qr) {
pr_err("Unable to allocate memory for"
" struct iscsi_queue_req\n");
- return;
+ return -ENOMEM;
}
INIT_LIST_HEAD(&qr->qr_list);
qr->cmd = cmd;
spin_unlock_bh(&conn->response_queue_lock);
wake_up(&conn->queues_wq);
+ return 0;
}
struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *conn)
{
struct se_cmd *se_cmd = NULL;
int rc;
+ bool op_scsi = false;
/*
* Determine if a struct se_cmd is associated with
* this struct iscsi_cmd.
*/
switch (cmd->iscsi_opcode) {
case ISCSI_OP_SCSI_CMD:
- se_cmd = &cmd->se_cmd;
- __iscsit_free_cmd(cmd, true, shutdown);
+ op_scsi = true;
/*
* Fallthrough
*/
case ISCSI_OP_SCSI_TMFUNC:
- rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
- if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
- __iscsit_free_cmd(cmd, true, shutdown);
+ se_cmd = &cmd->se_cmd;
+ __iscsit_free_cmd(cmd, op_scsi, shutdown);
+ rc = transport_generic_free_cmd(se_cmd, shutdown);
+ if (!rc && shutdown && se_cmd->se_sess) {
+ __iscsit_free_cmd(cmd, op_scsi, shutdown);
target_put_sess_cmd(se_cmd);
}
break;
struct iscsi_conn_recovery **, itt_t);
extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *);
-extern void iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
+extern int iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *);
extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_conn *);
extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *);
/*
* Set the ASYMMETRIC ACCESS State
*/
- buf[off++] |= (atomic_read(
- &tg_pt_gp->tg_pt_gp_alua_access_state) & 0xff);
+ buf[off++] |= tg_pt_gp->tg_pt_gp_alua_access_state & 0xff;
/*
* Set supported ASYMMETRIC ACCESS State bits
*/
spin_lock(&lun->lun_tg_pt_gp_lock);
tg_pt_gp = lun->lun_tg_pt_gp;
- out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
+ out_alua_state = tg_pt_gp->tg_pt_gp_alua_access_state;
nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs;
// XXX: keeps using tg_pt_gp witout reference after unlock
}
/*
- * Called with tg_pt_gp->tg_pt_gp_md_mutex held
+ * Called with tg_pt_gp->tg_pt_gp_transition_mutex held
*/
static int core_alua_update_tpg_primary_metadata(
struct t10_alua_tg_pt_gp *tg_pt_gp)
"alua_access_state=0x%02x\n"
"alua_access_status=0x%02x\n",
tg_pt_gp->tg_pt_gp_id,
- tg_pt_gp->tg_pt_gp_alua_pending_state,
+ tg_pt_gp->tg_pt_gp_alua_access_state,
tg_pt_gp->tg_pt_gp_alua_access_status);
snprintf(path, ALUA_METADATA_PATH_LEN,
spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
}
-static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
-{
- struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
- struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work);
- struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
- bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
- ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
-
- /*
- * Update the ALUA metadata buf that has been allocated in
- * core_alua_do_port_transition(), this metadata will be written
- * to struct file.
- *
- * Note that there is the case where we do not want to update the
- * metadata when the saved metadata is being parsed in userspace
- * when setting the existing port access state and access status.
- *
- * Also note that the failure to write out the ALUA metadata to
- * struct file does NOT affect the actual ALUA transition.
- */
- if (tg_pt_gp->tg_pt_gp_write_metadata) {
- mutex_lock(&tg_pt_gp->tg_pt_gp_md_mutex);
- core_alua_update_tpg_primary_metadata(tg_pt_gp);
- mutex_unlock(&tg_pt_gp->tg_pt_gp_md_mutex);
- }
- /*
- * Set the current primary ALUA access state to the requested new state
- */
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- tg_pt_gp->tg_pt_gp_alua_pending_state);
-
- pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
- " from primary access state %s to %s\n", (explicit) ? "explicit" :
- "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
- tg_pt_gp->tg_pt_gp_id,
- core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state),
- core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
-
- core_alua_queue_state_change_ua(tg_pt_gp);
-
- spin_lock(&dev->t10_alua.tg_pt_gps_lock);
- atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
- spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
-
- if (tg_pt_gp->tg_pt_gp_transition_complete)
- complete(tg_pt_gp->tg_pt_gp_transition_complete);
-}
-
static int core_alua_do_transition_tg_pt(
struct t10_alua_tg_pt_gp *tg_pt_gp,
int new_state,
int explicit)
{
- struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
- DECLARE_COMPLETION_ONSTACK(wait);
+ int prev_state;
+ mutex_lock(&tg_pt_gp->tg_pt_gp_transition_mutex);
/* Nothing to be done here */
- if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state)
+ if (tg_pt_gp->tg_pt_gp_alua_access_state == new_state) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
+ }
- if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION)
+ if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return -EAGAIN;
-
- /*
- * Flush any pending transitions
- */
- if (!explicit)
- flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
+ }
/*
* Save the old primary ALUA access state, and set the current state
* to ALUA_ACCESS_STATE_TRANSITION.
*/
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- ALUA_ACCESS_STATE_TRANSITION);
+ prev_state = tg_pt_gp->tg_pt_gp_alua_access_state;
+ tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_TRANSITION;
tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
core_alua_queue_state_change_ua(tg_pt_gp);
- if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+ if (new_state == ALUA_ACCESS_STATE_TRANSITION) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
-
- tg_pt_gp->tg_pt_gp_alua_previous_state =
- atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
- tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
+ }
/*
* Check for the optional ALUA primary state transition delay
msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs);
/*
- * Take a reference for workqueue item
+ * Set the current primary ALUA access state to the requested new state
*/
- spin_lock(&dev->t10_alua.tg_pt_gps_lock);
- atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
- spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+ tg_pt_gp->tg_pt_gp_alua_access_state = new_state;
- schedule_work(&tg_pt_gp->tg_pt_gp_transition_work);
- if (explicit) {
- tg_pt_gp->tg_pt_gp_transition_complete = &wait;
- wait_for_completion(&wait);
- tg_pt_gp->tg_pt_gp_transition_complete = NULL;
+ /*
+ * Update the ALUA metadata buf that has been allocated in
+ * core_alua_do_port_transition(), this metadata will be written
+ * to struct file.
+ *
+ * Note that there is the case where we do not want to update the
+ * metadata when the saved metadata is being parsed in userspace
+ * when setting the existing port access state and access status.
+ *
+ * Also note that the failure to write out the ALUA metadata to
+ * struct file does NOT affect the actual ALUA transition.
+ */
+ if (tg_pt_gp->tg_pt_gp_write_metadata) {
+ core_alua_update_tpg_primary_metadata(tg_pt_gp);
}
+ pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
+ " from primary access state %s to %s\n", (explicit) ? "explicit" :
+ "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+ tg_pt_gp->tg_pt_gp_id,
+ core_alua_dump_state(prev_state),
+ core_alua_dump_state(new_state));
+
+ core_alua_queue_state_change_ua(tg_pt_gp);
+
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
}
}
INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list);
INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list);
- mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
+ mutex_init(&tg_pt_gp->tg_pt_gp_transition_mutex);
spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
- INIT_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
- core_alua_do_transition_tg_pt_work);
tg_pt_gp->tg_pt_gp_dev = dev;
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
+ tg_pt_gp->tg_pt_gp_alua_access_state =
+ ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED;
/*
* Enable both explicit and implicit ALUA support by default
*/
dev->t10_alua.alua_tg_pt_gps_counter--;
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
- flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
-
/*
* Allow a struct t10_alua_tg_pt_gp_member * referenced by
* core_alua_get_tg_pt_gp_by_name() in
"Primary Access Status: %s\nTG Port Secondary Access"
" State: %s\nTG Port Secondary Access Status: %s\n",
config_item_name(tg_pt_ci), tg_pt_gp->tg_pt_gp_id,
- core_alua_dump_state(atomic_read(
- &tg_pt_gp->tg_pt_gp_alua_access_state)),
+ core_alua_dump_state(
+ tg_pt_gp->tg_pt_gp_alua_access_state),
core_alua_dump_status(
tg_pt_gp->tg_pt_gp_alua_access_status),
atomic_read(&lun->lun_tg_pt_secondary_offline) ?
char *page)
{
return sprintf(page, "%d\n",
- atomic_read(&to_tg_pt_gp(item)->tg_pt_gp_alua_access_state));
+ to_tg_pt_gp(item)->tg_pt_gp_alua_access_state);
}
static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item,
pr_err("Source se_lun->lun_se_dev does not exist\n");
return -EINVAL;
}
+ if (lun->lun_shutdown) {
+ pr_err("Unable to create mappedlun symlink because"
+ " lun->lun_shutdown=true\n");
+ return -EINVAL;
+ }
se_tpg = lun->lun_tpg;
nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item;
*/
struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
+ lun->lun_shutdown = true;
+
core_clear_lun_from_tpg(lun, tpg);
/*
* Wait for any active I/O references to percpu se_lun->lun_ref to
}
if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
hlist_del_rcu(&lun->link);
+
+ lun->lun_shutdown = false;
mutex_unlock(&tpg->tpg_lun_mutex);
percpu_ref_exit(&lun->lun_ref);
struct kmem_cache *t10_alua_lba_map_mem_cache;
static void transport_complete_task_attr(struct se_cmd *cmd);
+static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
static void transport_handle_queue_full(struct se_cmd *cmd,
- struct se_device *dev);
+ struct se_device *dev, int err, bool write_pending);
static int transport_put_cmd(struct se_cmd *cmd);
static void target_complete_ok_work(struct work_struct *work);
if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP)
transport_write_pending_qf(cmd);
- else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK)
+ else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK ||
+ cmd->t_state == TRANSPORT_COMPLETE_QF_ERR)
transport_complete_qf(cmd);
}
}
}
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
goto check_stop;
default:
}
ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
check_stop:
return;
queue_full:
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
EXPORT_SYMBOL(transport_generic_request_failure);
int ret = 0;
transport_complete_task_attr(cmd);
+ /*
+ * If a fabric driver ->write_pending() or ->queue_data_in() callback
+ * has returned neither -ENOMEM or -EAGAIN, assume it's fatal and
+ * the same callbacks should not be retried. Return CHECK_CONDITION
+ * if a scsi_status is not already set.
+ *
+ * If a fabric driver ->queue_status() has returned non zero, always
+ * keep retrying no matter what..
+ */
+ if (cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) {
+ if (cmd->scsi_status)
+ goto queue_status;
- if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
- trace_target_cmd_complete(cmd);
- ret = cmd->se_tfo->queue_status(cmd);
- goto out;
+ cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+ cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER;
+ translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
+ goto queue_status;
}
+ if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE)
+ goto queue_status;
+
switch (cmd->data_direction) {
case DMA_FROM_DEVICE:
if (cmd->scsi_status)
break;
}
-out:
if (ret < 0) {
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
return;
}
transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
}
-static void transport_handle_queue_full(
- struct se_cmd *cmd,
- struct se_device *dev)
+static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev,
+ int err, bool write_pending)
{
+ /*
+ * -EAGAIN or -ENOMEM signals retry of ->write_pending() and/or
+ * ->queue_data_in() callbacks from new process context.
+ *
+ * Otherwise for other errors, transport_complete_qf() will send
+ * CHECK_CONDITION via ->queue_status() instead of attempting to
+ * retry associated fabric driver data-transfer callbacks.
+ */
+ if (err == -EAGAIN || err == -ENOMEM) {
+ cmd->t_state = (write_pending) ? TRANSPORT_COMPLETE_QF_WP :
+ TRANSPORT_COMPLETE_QF_OK;
+ } else {
+ pr_warn_ratelimited("Got unknown fabric queue status: %d\n", err);
+ cmd->t_state = TRANSPORT_COMPLETE_QF_ERR;
+ }
+
spin_lock_irq(&dev->qf_cmd_lock);
list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
atomic_inc_mb(&dev->dev_qf_count);
WARN_ON(!cmd->scsi_status);
ret = transport_send_check_condition_and_sense(
cmd, 0, 1);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
} else if (rc) {
ret = transport_send_check_condition_and_sense(cmd,
rc, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
if (target_read_prot_action(cmd)) {
ret = transport_send_check_condition_and_sense(cmd,
cmd->pi_err, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
case DMA_TO_DEVICE:
atomic_long_add(cmd->data_length,
&cmd->se_lun->lun_stats.tx_data_octets);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
}
queue_status:
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
default:
queue_full:
pr_debug("Handling complete_ok QUEUE_FULL: se_cmd: %p,"
" data_direction: %d\n", cmd, cmd->data_direction);
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
void target_free_sgl(struct scatterlist *sgl, int nents)
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
- /* fabric drivers should only return -EAGAIN or -ENOMEM as error */
- WARN_ON(ret);
-
- return (!ret) ? 0 : TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return 0;
queue_full:
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
- cmd->t_state = TRANSPORT_COMPLETE_QF_WP;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
return 0;
}
EXPORT_SYMBOL(transport_generic_new_cmd);
int ret;
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM) {
+ if (ret) {
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n",
cmd);
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
}
}
__releases(&cmd->t_state_lock)
__acquires(&cmd->t_state_lock)
{
+ int ret;
+
assert_spin_locked(&cmd->t_state_lock);
WARN_ON_ONCE(!irqs_disabled());
trace_target_cmd_complete(cmd);
spin_unlock_irq(&cmd->t_state_lock);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
spin_lock_irq(&cmd->t_state_lock);
return 1;
void transport_send_task_abort(struct se_cmd *cmd)
{
unsigned long flags;
+ int ret;
spin_lock_irqsave(&cmd->t_state_lock, flags);
if (cmd->se_cmd_flags & (SCF_SENT_CHECK_CONDITION)) {
cmd->t_task_cdb[0], cmd->tag);
trace_target_cmd_complete(cmd);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
static void target_tmr_work(struct work_struct *work)
DATA_BLOCK_BITS);
}
-static void gather_data_area(struct tcmu_dev *udev, unsigned long *cmd_bitmap,
- struct scatterlist *data_sg, unsigned int data_nents)
+static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
+ bool bidi)
{
+ struct se_cmd *se_cmd = cmd->se_cmd;
int i, block;
int block_remaining = 0;
void *from, *to;
size_t copy_bytes, from_offset;
- struct scatterlist *sg;
+ struct scatterlist *sg, *data_sg;
+ unsigned int data_nents;
+ DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
+
+ bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
+
+ if (!bidi) {
+ data_sg = se_cmd->t_data_sg;
+ data_nents = se_cmd->t_data_nents;
+ } else {
+ uint32_t count;
+
+ /*
+ * For bidi case, the first count blocks are for Data-Out
+ * buffer blocks, and before gathering the Data-In buffer
+ * the Data-Out buffer blocks should be discarded.
+ */
+ count = DIV_ROUND_UP(se_cmd->data_length, DATA_BLOCK_SIZE);
+ while (count--) {
+ block = find_first_bit(bitmap, DATA_BLOCK_BITS);
+ clear_bit(block, bitmap);
+ }
+
+ data_sg = se_cmd->t_bidi_data_sg;
+ data_nents = se_cmd->t_bidi_data_nents;
+ }
for_each_sg(data_sg, sg, data_nents, i) {
int sg_remaining = sg->length;
to = kmap_atomic(sg_page(sg)) + sg->offset;
while (sg_remaining > 0) {
if (block_remaining == 0) {
- block = find_first_bit(cmd_bitmap,
+ block = find_first_bit(bitmap,
DATA_BLOCK_BITS);
block_remaining = DATA_BLOCK_SIZE;
- clear_bit(block, cmd_bitmap);
+ clear_bit(block, bitmap);
}
copy_bytes = min_t(size_t, sg_remaining,
block_remaining);
return true;
}
+static inline size_t tcmu_cmd_get_data_length(struct tcmu_cmd *tcmu_cmd)
+{
+ struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
+ size_t data_length = round_up(se_cmd->data_length, DATA_BLOCK_SIZE);
+
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
+ data_length += round_up(se_cmd->t_bidi_data_sg->length,
+ DATA_BLOCK_SIZE);
+ }
+
+ return data_length;
+}
+
+static inline uint32_t tcmu_cmd_get_block_cnt(struct tcmu_cmd *tcmu_cmd)
+{
+ size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
+
+ return data_length / DATA_BLOCK_SIZE;
+}
+
static sense_reason_t
tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
{
uint32_t cmd_head;
uint64_t cdb_off;
bool copy_to_data_area;
- size_t data_length;
+ size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS);
if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
* expensive to tell how many regions are freed in the bitmap
*/
base_command_size = max(offsetof(struct tcmu_cmd_entry,
- req.iov[se_cmd->t_bidi_data_nents +
- se_cmd->t_data_nents]),
+ req.iov[tcmu_cmd_get_block_cnt(tcmu_cmd)]),
sizeof(struct tcmu_cmd_entry));
command_size = base_command_size
+ round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE);
mb = udev->mb_addr;
cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
- data_length = se_cmd->data_length;
- if (se_cmd->se_cmd_flags & SCF_BIDI) {
- BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
- data_length += se_cmd->t_bidi_data_sg->length;
- }
if ((command_size > (udev->cmdr_size / 2)) ||
data_length > udev->data_size) {
pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
entry->req.iov_dif_cnt = 0;
/* Handle BIDI commands */
- iov_cnt = 0;
- alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
- se_cmd->t_bidi_data_nents, &iov, &iov_cnt, false);
- entry->req.iov_bidi_cnt = iov_cnt;
-
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ iov_cnt = 0;
+ iov++;
+ alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
+ se_cmd->t_bidi_data_nents, &iov, &iov_cnt,
+ false);
+ entry->req.iov_bidi_cnt = iov_cnt;
+ }
/* cmd's data_bitmap is what changed in process */
bitmap_xor(tcmu_cmd->data_bitmap, old_bitmap, udev->data_bitmap,
DATA_BLOCK_BITS);
se_cmd->scsi_sense_length);
free_data_area(udev, cmd);
} else if (se_cmd->se_cmd_flags & SCF_BIDI) {
- DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
/* Get Data-In buffer before clean up */
- bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
- gather_data_area(udev, bitmap,
- se_cmd->t_bidi_data_sg, se_cmd->t_bidi_data_nents);
+ gather_data_area(udev, cmd, true);
free_data_area(udev, cmd);
} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
- DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
- bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
- gather_data_area(udev, bitmap,
- se_cmd->t_data_sg, se_cmd->t_data_nents);
+ gather_data_area(udev, cmd, false);
free_data_area(udev, cmd);
} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
free_data_area(udev, cmd);
if (ret < 0)
return ret;
- if (!val) {
- pr_err("Illegal value for cmd_time_out\n");
- return -EINVAL;
- }
-
udev->cmd_time_out = val * MSEC_PER_SEC;
return count;
}
usb_ep_free_request(fu->ep_in, fu->bot_req_in);
usb_ep_free_request(fu->ep_out, fu->bot_req_out);
usb_ep_free_request(fu->ep_out, fu->cmd.req);
- usb_ep_free_request(fu->ep_out, fu->bot_status.req);
+ usb_ep_free_request(fu->ep_in, fu->bot_status.req);
kfree(fu->cmd.buf);
#include <linux/efi.h>
#include <linux/errno.h>
#include <linux/fb.h>
+#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/screen_info.h>
#include <video/vga.h>
};
ATTRIBUTE_GROUPS(efifb);
+static bool pci_dev_disabled; /* FB base matches BAR of a disabled device */
+
static int efifb_probe(struct platform_device *dev)
{
struct fb_info *info;
unsigned int size_total;
char *option = NULL;
- if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+ if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
return -ENODEV;
if (fb_get_options("efifb", &option))
};
builtin_platform_driver(efifb_driver);
+
+#if defined(CONFIG_PCI) && !defined(CONFIG_X86)
+
+static bool pci_bar_found; /* did we find a BAR matching the efifb base? */
+
+static void claim_efifb_bar(struct pci_dev *dev, int idx)
+{
+ u16 word;
+
+ pci_bar_found = true;
+
+ pci_read_config_word(dev, PCI_COMMAND, &word);
+ if (!(word & PCI_COMMAND_MEMORY)) {
+ pci_dev_disabled = true;
+ dev_err(&dev->dev,
+ "BAR %d: assigned to efifb but device is disabled!\n",
+ idx);
+ return;
+ }
+
+ if (pci_claim_resource(dev, idx)) {
+ pci_dev_disabled = true;
+ dev_err(&dev->dev,
+ "BAR %d: failed to claim resource for efifb!\n", idx);
+ return;
+ }
+
+ dev_info(&dev->dev, "BAR %d: assigned to efifb\n", idx);
+}
+
+static void efifb_fixup_resources(struct pci_dev *dev)
+{
+ u64 base = screen_info.lfb_base;
+ u64 size = screen_info.lfb_size;
+ int i;
+
+ if (pci_bar_found || screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+ return;
+
+ if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)screen_info.ext_lfb_base << 32;
+
+ if (!base)
+ return;
+
+ for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+ struct resource *res = &dev->resource[i];
+
+ if (!(res->flags & IORESOURCE_MEM))
+ continue;
+
+ if (res->start <= base && res->end >= base + size - 1) {
+ claim_efifb_bar(dev, i);
+ break;
+ }
+ }
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY,
+ 16, efifb_fixup_resources);
+
+#endif
return 0;
}
-static void check_required_callbacks(struct omapfb_device *fbdev)
-{
-#define _C(x) (fbdev->ctrl->x != NULL)
-#define _P(x) (fbdev->panel->x != NULL)
- BUG_ON(fbdev->ctrl == NULL || fbdev->panel == NULL);
- BUG_ON(!(_C(init) && _C(cleanup) && _C(get_caps) &&
- _C(set_update_mode) && _C(setup_plane) && _C(enable_plane) &&
- _P(init) && _P(cleanup) && _P(enable) && _P(disable) &&
- _P(get_caps)));
-#undef _P
-#undef _C
-}
-
/*
* Called by LDM binding to probe and attach a new device.
* Initialization sequence:
omapfb_ops.fb_mmap = omapfb_mmap;
init_state++;
- check_required_callbacks(fbdev);
-
r = planes_init(fbdev);
if (r)
goto cleanup;
par->vbat_reg = devm_regulator_get_optional(&client->dev, "vbat");
if (IS_ERR(par->vbat_reg)) {
- dev_err(&client->dev, "failed to get VBAT regulator: %ld\n",
- PTR_ERR(par->vbat_reg));
ret = PTR_ERR(par->vbat_reg);
- goto fb_alloc_error;
+ if (ret == -ENODEV) {
+ par->vbat_reg = NULL;
+ } else {
+ dev_err(&client->dev, "failed to get VBAT regulator: %d\n",
+ ret);
+ goto fb_alloc_error;
+ }
}
if (of_property_read_u32(node, "solomon,width", &par->width))
udelay(4);
}
- ret = regulator_enable(par->vbat_reg);
- if (ret) {
- dev_err(&client->dev, "failed to enable VBAT: %d\n", ret);
- goto reset_oled_error;
+ if (par->vbat_reg) {
+ ret = regulator_enable(par->vbat_reg);
+ if (ret) {
+ dev_err(&client->dev, "failed to enable VBAT: %d\n",
+ ret);
+ goto reset_oled_error;
+ }
}
ret = ssd1307fb_init(par);
pwm_put(par->pwm);
};
regulator_enable_error:
- regulator_disable(par->vbat_reg);
+ if (par->vbat_reg)
+ regulator_disable(par->vbat_reg);
reset_oled_error:
fb_deferred_io_cleanup(info);
fb_alloc_error:
break;
case XenbusStateInitWait:
-InitWait:
xenbus_switch_state(dev, XenbusStateConnected);
break;
* get Connected twice here.
*/
if (dev->state != XenbusStateConnected)
- goto InitWait; /* no InitWait seen yet, fudge it */
+ /* no InitWait seen yet, fudge it */
+ xenbus_switch_state(dev, XenbusStateConnected);
if (xenbus_read_unsigned(info->xbdev->otherend,
"request-update", 0))
if (device_features & (1ULL << i))
__virtio_set_bit(dev, i);
+ if (drv->validate) {
+ err = drv->validate(dev);
+ if (err)
+ goto err;
+ }
+
err = virtio_finalize_features(dev);
if (err)
goto err;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i;
- synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0));
- for (i = 1; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->intx_enabled)
+ synchronize_irq(vp_dev->pci_dev->irq);
+
+ for (i = 0; i < vp_dev->msix_vectors; ++i)
synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
}
static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
{
struct virtio_pci_device *vp_dev = opaque;
+ struct virtio_pci_vq_info *info;
irqreturn_t ret = IRQ_NONE;
- struct virtqueue *vq;
+ unsigned long flags;
- list_for_each_entry(vq, &vp_dev->vdev.vqs, list) {
- if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED)
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_for_each_entry(info, &vp_dev->virtqueues, node) {
+ if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
ret = IRQ_HANDLED;
}
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
return ret;
}
return vp_vring_interrupt(irq, opaque);
}
-static void vp_remove_vqs(struct virtio_device *vdev)
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+ bool per_vq_vectors, struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- struct virtqueue *vq, *n;
+ const char *name = dev_name(&vp_dev->vdev.dev);
+ unsigned i, v;
+ int err = -ENOMEM;
- list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
- if (vp_dev->msix_vector_map) {
- int v = vp_dev->msix_vector_map[vq->index];
+ vp_dev->msix_vectors = nvectors;
- if (v != VIRTIO_MSI_NO_VECTOR)
- free_irq(pci_irq_vector(vp_dev->pci_dev, v),
- vq);
- }
- vp_dev->del_vq(vq);
+ vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+ GFP_KERNEL);
+ if (!vp_dev->msix_names)
+ goto error;
+ vp_dev->msix_affinity_masks
+ = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+ GFP_KERNEL);
+ if (!vp_dev->msix_affinity_masks)
+ goto error;
+ for (i = 0; i < nvectors; ++i)
+ if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+ GFP_KERNEL))
+ goto error;
+
+ err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+ nvectors, PCI_IRQ_MSIX |
+ (desc ? PCI_IRQ_AFFINITY : 0),
+ desc);
+ if (err < 0)
+ goto error;
+ vp_dev->msix_enabled = 1;
+
+ /* Set the vector used for configuration */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-config", name);
+ err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+ vp_config_changed, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+
+ v = vp_dev->config_vector(vp_dev, v);
+ /* Verify we had enough resources to assign the vector */
+ if (v == VIRTIO_MSI_NO_VECTOR) {
+ err = -EBUSY;
+ goto error;
}
+
+ if (!per_vq_vectors) {
+ /* Shared vector for all VQs */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-virtqueues", name);
+ err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+ vp_vring_interrupt, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+ }
+ return 0;
+error:
+ return err;
+}
+
+static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
+ struct virtqueue *vq;
+ unsigned long flags;
+
+ /* fill out our structure that represents an active queue */
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ vq = vp_dev->setup_vq(vp_dev, info, index, callback, name,
+ msix_vec);
+ if (IS_ERR(vq))
+ goto out_info;
+
+ info->vq = vq;
+ if (callback) {
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+ } else {
+ INIT_LIST_HEAD(&info->node);
+ }
+
+ vp_dev->vqs[index] = info;
+ return vq;
+
+out_info:
+ kfree(info);
+ return vq;
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ unsigned long flags;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ vp_dev->del_vq(info);
+ kfree(info);
}
/* the config->del_vqs() implementation */
void vp_del_vqs(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtqueue *vq, *n;
int i;
- if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs)))
- return;
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+ if (vp_dev->per_vq_vectors) {
+ int v = vp_dev->vqs[vq->index]->msix_vector;
- vp_remove_vqs(vdev);
+ if (v != VIRTIO_MSI_NO_VECTOR) {
+ int irq = pci_irq_vector(vp_dev->pci_dev, v);
+
+ irq_set_affinity_hint(irq, NULL);
+ free_irq(irq, vq);
+ }
+ }
+ vp_del_vq(vq);
+ }
+ vp_dev->per_vq_vectors = false;
+
+ if (vp_dev->intx_enabled) {
+ free_irq(vp_dev->pci_dev->irq, vp_dev);
+ vp_dev->intx_enabled = 0;
+ }
- if (vp_dev->pci_dev->msix_enabled) {
- for (i = 0; i < vp_dev->msix_vectors; i++)
+ for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+ free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
+
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
- kfree(vp_dev->msix_affinity_masks);
- kfree(vp_dev->msix_names);
- kfree(vp_dev->msix_vector_map);
+ pci_free_irq_vectors(vp_dev->pci_dev);
+ vp_dev->msix_enabled = 0;
}
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
- pci_free_irq_vectors(vp_dev->pci_dev);
+ vp_dev->msix_vectors = 0;
+ vp_dev->msix_used_vectors = 0;
+ kfree(vp_dev->msix_names);
+ vp_dev->msix_names = NULL;
+ kfree(vp_dev->msix_affinity_masks);
+ vp_dev->msix_affinity_masks = NULL;
+ kfree(vp_dev->vqs);
+ vp_dev->vqs = NULL;
}
static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc)
+ const char * const names[], bool per_vq_vectors,
+ struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- const char *name = dev_name(&vp_dev->vdev.dev);
- int i, j, err = -ENOMEM, allocated_vectors, nvectors;
- unsigned flags = PCI_IRQ_MSIX;
- bool shared = false;
u16 msix_vec;
+ int i, err, nvectors, allocated_vectors;
- if (desc) {
- flags |= PCI_IRQ_AFFINITY;
- desc->pre_vectors++; /* virtio config vector */
- }
-
- nvectors = 1;
- for (i = 0; i < nvqs; i++)
- if (callbacks[i])
- nvectors++;
-
- /* Try one vector per queue first. */
- err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
- nvectors, flags, desc);
- if (err < 0) {
- /* Fallback to one vector for config, one shared for queues. */
- shared = true;
- err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
- PCI_IRQ_MSIX);
- if (err < 0)
- return err;
- }
- if (err < 0)
- return err;
-
- vp_dev->msix_vectors = nvectors;
- vp_dev->msix_names = kmalloc_array(nvectors,
- sizeof(*vp_dev->msix_names), GFP_KERNEL);
- if (!vp_dev->msix_names)
- goto out_free_irq_vectors;
-
- vp_dev->msix_affinity_masks = kcalloc(nvectors,
- sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL);
- if (!vp_dev->msix_affinity_masks)
- goto out_free_msix_names;
+ vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+ if (!vp_dev->vqs)
+ return -ENOMEM;
- for (i = 0; i < nvectors; ++i) {
- if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
- GFP_KERNEL))
- goto out_free_msix_affinity_masks;
+ if (per_vq_vectors) {
+ /* Best option: one for change interrupt, one per vq. */
+ nvectors = 1;
+ for (i = 0; i < nvqs; ++i)
+ if (callbacks[i])
+ ++nvectors;
+ } else {
+ /* Second best: one for change, shared for all vqs. */
+ nvectors = 2;
}
- /* Set the vector used for configuration */
- snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names),
- "%s-config", name);
- err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
- 0, vp_dev->msix_names[0], vp_dev);
+ err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors,
+ per_vq_vectors ? desc : NULL);
if (err)
- goto out_free_msix_affinity_masks;
+ goto error_find;
- /* Verify we had enough resources to assign the vector */
- if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
- err = -EBUSY;
- goto out_free_config_irq;
- }
-
- vp_dev->msix_vector_map = kmalloc_array(nvqs,
- sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
- if (!vp_dev->msix_vector_map)
- goto out_disable_config_irq;
-
- allocated_vectors = j = 1; /* vector 0 is the config interrupt */
+ vp_dev->per_vq_vectors = per_vq_vectors;
+ allocated_vectors = vp_dev->msix_used_vectors;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
- if (callbacks[i])
- msix_vec = allocated_vectors;
- else
+ if (!callbacks[i])
msix_vec = VIRTIO_MSI_NO_VECTOR;
-
- vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
- msix_vec);
+ else if (vp_dev->per_vq_vectors)
+ msix_vec = allocated_vectors++;
+ else
+ msix_vec = VP_MSIX_VQ_VECTOR;
+ vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ msix_vec);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
- goto out_remove_vqs;
+ goto error_find;
}
- if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
- vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
+ if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
continue;
- }
- snprintf(vp_dev->msix_names[j],
- sizeof(*vp_dev->msix_names), "%s-%s",
+ /* allocate per-vq irq if available and necessary */
+ snprintf(vp_dev->msix_names[msix_vec],
+ sizeof *vp_dev->msix_names,
+ "%s-%s",
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
- vring_interrupt, IRQF_SHARED,
- vp_dev->msix_names[j], vqs[i]);
- if (err) {
- /* don't free this irq on error */
- vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
- goto out_remove_vqs;
- }
- vp_dev->msix_vector_map[i] = msix_vec;
- j++;
-
- /*
- * Use a different vector for each queue if they are available,
- * else share the same vector for all VQs.
- */
- if (!shared)
- allocated_vectors++;
+ vring_interrupt, 0,
+ vp_dev->msix_names[msix_vec],
+ vqs[i]);
+ if (err)
+ goto error_find;
}
-
return 0;
-out_remove_vqs:
- vp_remove_vqs(vdev);
- kfree(vp_dev->msix_vector_map);
-out_disable_config_irq:
- vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
-out_free_config_irq:
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
-out_free_msix_affinity_masks:
- for (i = 0; i < nvectors; i++) {
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
- }
- kfree(vp_dev->msix_affinity_masks);
-out_free_msix_names:
- kfree(vp_dev->msix_names);
-out_free_irq_vectors:
- pci_free_irq_vectors(vp_dev->pci_dev);
+error_find:
+ vp_del_vqs(vdev);
return err;
}
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i, err;
+ vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+ if (!vp_dev->vqs)
+ return -ENOMEM;
+
err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
dev_name(&vdev->dev), vp_dev);
if (err)
- return err;
+ goto out_del_vqs;
+ vp_dev->intx_enabled = 1;
+ vp_dev->per_vq_vectors = false;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
- vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
- VIRTIO_MSI_NO_VECTOR);
+ vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ VIRTIO_MSI_NO_VECTOR);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
- goto out_remove_vqs;
+ goto out_del_vqs;
}
}
return 0;
-
-out_remove_vqs:
- vp_remove_vqs(vdev);
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+out_del_vqs:
+ vp_del_vqs(vdev);
return err;
}
{
int err;
- err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc);
+ /* Try MSI-X with one vector per queue. */
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc);
if (!err)
return 0;
+ /* Fallback: MSI-X with one vector for config, one shared for queues. */
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc);
+ if (!err)
+ return 0;
+ /* Finally fall back to regular interrupts. */
return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
}
{
struct virtio_device *vdev = vq->vdev;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ struct cpumask *mask;
+ unsigned int irq;
if (!vq->callback)
return -EINVAL;
- if (vp_dev->pci_dev->msix_enabled) {
- int vec = vp_dev->msix_vector_map[vq->index];
- struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
- unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
-
+ if (vp_dev->msix_enabled) {
+ mask = vp_dev->msix_affinity_masks[info->msix_vector];
+ irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
if (cpu == -1)
irq_set_affinity_hint(irq, NULL);
else {
const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- unsigned int *map = vp_dev->msix_vector_map;
- if (!map || map[index] == VIRTIO_MSI_NO_VECTOR)
+ if (!vp_dev->per_vq_vectors ||
+ vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR)
return NULL;
- return pci_irq_get_affinity(vp_dev->pci_dev, map[index]);
+ return pci_irq_get_affinity(vp_dev->pci_dev,
+ vp_dev->vqs[index]->msix_vector);
}
#ifdef CONFIG_PM_SLEEP
vp_dev->vdev.dev.parent = &pci_dev->dev;
vp_dev->vdev.dev.release = virtio_pci_release_dev;
vp_dev->pci_dev = pci_dev;
+ INIT_LIST_HEAD(&vp_dev->virtqueues);
+ spin_lock_init(&vp_dev->lock);
/* enable the device */
rc = pci_enable_device(pci_dev);
#include <linux/highmem.h>
#include <linux/spinlock.h>
+struct virtio_pci_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+
+ /* MSI-X vector (or none) */
+ unsigned msix_vector;
+};
+
/* Our device structure */
struct virtio_pci_device {
struct virtio_device vdev;
/* the IO mapping for the PCI config space */
void __iomem *ioaddr;
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+
+ /* array of all queues for house-keeping */
+ struct virtio_pci_vq_info **vqs;
+
+ /* MSI-X support */
+ int msix_enabled;
+ int intx_enabled;
cpumask_var_t *msix_affinity_masks;
/* Name strings for interrupts. This size should be enough,
* and I'm too lazy to allocate each name separately. */
char (*msix_names)[256];
- /* Total Number of MSI-X vectors (including per-VQ ones). */
- int msix_vectors;
- /* Map of per-VQ MSI-X vectors, may be NULL */
- unsigned *msix_vector_map;
+ /* Number of available vectors */
+ unsigned msix_vectors;
+ /* Vectors allocated, excluding per-vq vectors if any */
+ unsigned msix_used_vectors;
+
+ /* Whether we have vector per vq */
+ bool per_vq_vectors;
struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned idx,
void (*callback)(struct virtqueue *vq),
const char *name,
u16 msix_vec);
- void (*del_vq)(struct virtqueue *vq);
+ void (*del_vq)(struct virtio_pci_vq_info *info);
u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
};
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+ VP_MSIX_CONFIG_VECTOR = 0,
+ VP_MSIX_VQ_VECTOR = 1,
+};
+
/* Convert a generic virtio device to our structure */
static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
{
}
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
return ERR_PTR(-ENOENT);
+ info->msix_vector = msix_vec;
+
/* create the vring */
vq = vring_create_virtqueue(index, num,
VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
return ERR_PTR(err);
}
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
{
+ struct virtqueue *vq = info->vq;
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
- if (vp_dev->pci_dev->msix_enabled) {
+ if (vp_dev->msix_enabled) {
iowrite16(VIRTIO_MSI_NO_VECTOR,
vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
/* Flush the write out to device */
}
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
/* get offset of notification word for this vq */
off = vp_ioread16(&cfg->queue_notify_off);
+ info->msix_vector = msix_vec;
+
/* create the vring */
vq = vring_create_virtqueue(index, num,
SMP_CACHE_BYTES, &vp_dev->vdev,
return 0;
}
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
{
+ struct virtqueue *vq = info->vq;
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
vp_iowrite16(vq->index, &vp_dev->common->queue_select);
- if (vp_dev->pci_dev->msix_enabled) {
+ if (vp_dev->msix_enabled) {
vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
&vp_dev->common->queue_msix_vector);
/* Flush the write out to device */
return xenbus_command_reply(u, XS_ERROR, "ENOENT");
rc = xenbus_dev_request_and_reply(&u->u.msg, u);
- if (rc)
+ if (rc && trans) {
+ list_del(&trans->list);
kfree(trans);
+ }
out:
return rc;
static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
- struct inode *inode;
struct bio_vec *bvec;
int i;
goto end;
ASSERT(bio->bi_vcnt == 1);
- inode = bio->bi_io_vec->bv_page->mapping->host;
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+ ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
done->uptodate = 1;
bio_for_each_segment_all(bvec, bio, i)
- clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0);
+ clean_io_failure(BTRFS_I(done->inode), done->start,
+ bvec->bv_page, 0);
end:
complete(&done->done);
bio_put(bio);
start += sectorsize;
- if (nr_sectors--) {
+ nr_sectors--;
+ if (nr_sectors) {
pgoff += sectorsize;
+ ASSERT(pgoff < PAGE_SIZE);
goto next_block_or_try_again;
}
}
{
struct btrfs_retry_complete *done = bio->bi_private;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- struct inode *inode;
struct bio_vec *bvec;
- u64 start;
int uptodate;
int ret;
int i;
uptodate = 1;
- start = done->start;
-
ASSERT(bio->bi_vcnt == 1);
- inode = bio->bi_io_vec->bv_page->mapping->host;
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+ ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
bio_for_each_segment_all(bvec, bio, i) {
ret = __readpage_endio_check(done->inode, io_bio, i,
ASSERT(nr_sectors);
- if (--nr_sectors) {
+ nr_sectors--;
+ if (nr_sectors) {
pgoff += sectorsize;
+ ASSERT(pgoff < PAGE_SIZE);
goto next_block;
}
}
case Opt_ssd:
btrfs_set_and_info(info, SSD,
"use ssd allocation scheme");
+ btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_ssd_spread:
btrfs_set_and_info(info, SSD_SPREAD,
"use spread ssd allocation scheme");
btrfs_set_opt(info->mount_opt, SSD);
+ btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_nossd:
btrfs_set_and_info(info, NOSSD,
"not using ssd allocation scheme");
btrfs_clear_opt(info->mount_opt, SSD);
+ btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
break;
case Opt_barrier:
btrfs_clear_and_info(info, NOBARRIER,
for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
dev = bbio->stripes[dev_nr].dev;
if (!dev || !dev->bdev ||
- (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) {
+ (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) {
bbio_error(bbio, first_bio, logical);
continue;
}
return rc;
}
+ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ struct inode *src_inode = file_inode(src_file);
+ struct inode *target_inode = file_inode(dst_file);
+ struct cifsFileInfo *smb_file_src;
+ struct cifsFileInfo *smb_file_target;
+ struct cifs_tcon *src_tcon;
+ struct cifs_tcon *target_tcon;
+ ssize_t rc;
+
+ cifs_dbg(FYI, "copychunk range\n");
+
+ if (src_inode == target_inode) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (!src_file->private_data || !dst_file->private_data) {
+ rc = -EBADF;
+ cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+ goto out;
+ }
+
+ rc = -EXDEV;
+ smb_file_target = dst_file->private_data;
+ smb_file_src = src_file->private_data;
+ src_tcon = tlink_tcon(smb_file_src->tlink);
+ target_tcon = tlink_tcon(smb_file_target->tlink);
+
+ if (src_tcon->ses != target_tcon->ses) {
+ cifs_dbg(VFS, "source and target of copy not on same server\n");
+ goto out;
+ }
+
+ /*
+ * Note: cifs case is easier than btrfs since server responsible for
+ * checks for proper open modes and file type and if it wants
+ * server could even support copy of range where source = target
+ */
+ lock_two_nondirectories(target_inode, src_inode);
+
+ cifs_dbg(FYI, "about to flush pages\n");
+ /* should we flush first and last page first */
+ truncate_inode_pages(&target_inode->i_data, 0);
+
+ if (target_tcon->ses->server->ops->copychunk_range)
+ rc = target_tcon->ses->server->ops->copychunk_range(xid,
+ smb_file_src, smb_file_target, off, len, destoff);
+ else
+ rc = -EOPNOTSUPP;
+
+ /* force revalidate of size and timestamps of target file now
+ * that target is updated on the server
+ */
+ CIFS_I(target_inode)->time = 0;
+ /* although unlocking in the reverse order from locking is not
+ * strictly necessary here it is a little cleaner to be consistent
+ */
+ unlock_two_nondirectories(src_inode, target_inode);
+
+out:
+ return rc;
+}
+
+static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ unsigned int xid = get_xid();
+ ssize_t rc;
+
+ rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
+ len, flags);
+ free_xid(xid);
+ return rc;
+}
+
const struct file_operations cifs_file_ops = {
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.release = cifs_closedir,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = generic_file_llseek,
};
# define cifs_listxattr NULL
#endif
+extern ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags);
+
extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_CIFS_NFSD_EXPORT
extern const struct export_operations cifs_export_ops;
/* verify the message */
int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+ int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
void (*downgrade_oplock)(struct TCP_Server_Info *,
struct cifsInodeInfo *, bool);
/* process transaction2 response */
char * (*create_lease_buf)(u8 *, u8);
/* parse lease context buffer and return oplock/epoch info */
__u8 (*parse_lease_buf)(void *, unsigned int *);
- int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
- struct cifsFileInfo *target_file, u64 src_off, u64 len,
- u64 dest_off);
+ ssize_t (*copychunk_range)(const unsigned int,
+ struct cifsFileInfo *src_file,
+ struct cifsFileInfo *target_file,
+ u64 src_off, u64 len, u64 dest_off);
int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src,
struct cifsFileInfo *target_file, u64 src_off, u64 len,
u64 dest_off);
bool use_persistent:1; /* use persistent instead of durable handles */
#ifdef CONFIG_CIFS_SMB2
bool print:1; /* set if connection to printer share */
- bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
__le32 capabilities;
__u32 share_flags;
__u32 maximal_access;
void *callback_data; /* general purpose pointer for callback */
void *resp_buf; /* pointer to received SMB header */
int mid_state; /* wish this were enum but can not pass to wait_event */
+ unsigned int mid_flags;
__le16 command; /* smb command code */
bool large_buf:1; /* if valid response, is pointer to large buf */
bool multiRsp:1; /* multiple trans2 responses for one request */
bool decrypted:1; /* decrypted entry */
};
+struct close_cancelled_open {
+ struct cifs_fid fid;
+ struct cifs_tcon *tcon;
+ struct work_struct work;
+};
+
/* Make code in transport.c a little cleaner by moving
update of optional stats into function below */
#ifdef CONFIG_CIFS_STATS2
#define MID_RESPONSE_MALFORMED 0x10
#define MID_SHUTDOWN 0x20
+/* Flags */
+#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */
+
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
#define CIFS_SMALL_BUFFER 1
length = cifs_discard_remaining_data(server);
dequeue_mid(mid, rdata->result);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
return cifs_readv_discard(server, mid);
dequeue_mid(mid, false);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
server->lstrp = jiffies;
if (mid_entry != NULL) {
+ if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+ mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+ server->ops->handle_cancelled_mid)
+ server->ops->handle_cancelled_mid(
+ mid_entry->resp_buf,
+ server);
+
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break ||
- !server->ops->is_oplock_break(buf, server)) {
+ } else if (server->ops->is_oplock_break &&
+ server->ops->is_oplock_break(buf, server)) {
+ cifs_dbg(FYI, "Received oplock break\n");
+ } else {
cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
if (IS_ERR(tcon)) {
rc = PTR_ERR(tcon);
tcon = NULL;
+ if (rc == -EACCES)
+ goto mount_fail_check;
+
goto remote_path_check;
}
wdata->credits = credits;
if (!wdata->cfile->invalidHandle ||
- !cifs_reopen_file(wdata->cfile, false))
+ !(rc = cifs_reopen_file(wdata->cfile, false)))
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
if (rc) {
rdata->credits = credits;
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
error:
if (rc) {
}
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
if (rc) {
add_credits_and_wake_if(server, rdata->credits, 0);
#include "cifs_ioctl.h"
#include <linux/btrfs.h>
-static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
- struct file *dst_file)
-{
- struct inode *src_inode = file_inode(src_file);
- struct inode *target_inode = file_inode(dst_file);
- struct cifsFileInfo *smb_file_src;
- struct cifsFileInfo *smb_file_target;
- struct cifs_tcon *src_tcon;
- struct cifs_tcon *target_tcon;
- int rc;
-
- cifs_dbg(FYI, "ioctl clone range\n");
-
- if (!src_file->private_data || !dst_file->private_data) {
- rc = -EBADF;
- cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
- goto out;
- }
-
- rc = -EXDEV;
- smb_file_target = dst_file->private_data;
- smb_file_src = src_file->private_data;
- src_tcon = tlink_tcon(smb_file_src->tlink);
- target_tcon = tlink_tcon(smb_file_target->tlink);
-
- if (src_tcon->ses != target_tcon->ses) {
- cifs_dbg(VFS, "source and target of copy not on same server\n");
- goto out;
- }
-
- /*
- * Note: cifs case is easier than btrfs since server responsible for
- * checks for proper open modes and file type and if it wants
- * server could even support copy of range where source = target
- */
- lock_two_nondirectories(target_inode, src_inode);
-
- cifs_dbg(FYI, "about to flush pages\n");
- /* should we flush first and last page first */
- truncate_inode_pages(&target_inode->i_data, 0);
-
- if (target_tcon->ses->server->ops->clone_range)
- rc = target_tcon->ses->server->ops->clone_range(xid,
- smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
- else
- rc = -EOPNOTSUPP;
-
- /* force revalidate of size and timestamps of target file now
- that target is updated on the server */
- CIFS_I(target_inode)->time = 0;
- /* although unlocking in the reverse order from locking is not
- strictly necessary here it is a little cleaner to be consistent */
- unlock_two_nondirectories(src_inode, target_inode);
-out:
- return rc;
-}
-
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
unsigned long srcfd)
{
int rc;
struct fd src_file;
struct inode *src_inode;
- cifs_dbg(FYI, "ioctl clone range\n");
+ cifs_dbg(FYI, "ioctl copychunk range\n");
/* the destination must be opened for writing */
if (!(dst_file->f_mode & FMODE_WRITE)) {
cifs_dbg(FYI, "file target not open for write\n");
if (S_ISDIR(src_inode->i_mode))
goto out_fput;
- rc = cifs_file_clone_range(xid, src_file.file, dst_file);
+ rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
+ src_inode->i_size, 0);
out_fput:
fdput(src_file);
}
break;
case CIFS_IOC_COPYCHUNK_FILE:
- rc = cifs_ioctl_clone(xid, filep, arg);
+ rc = cifs_ioctl_copychunk(xid, filep, arg);
break;
case CIFS_IOC_SET_INTEGRITY:
if (pSMBFile == NULL)
cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
return false;
}
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+ struct close_cancelled_open *cancelled = container_of(work,
+ struct close_cancelled_open, work);
+
+ cifs_dbg(VFS, "Close unmatched open\n");
+
+ SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+ cancelled->fid.volatile_fid);
+ cifs_put_tcon(cancelled->tcon);
+ kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+ struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+ struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+ struct cifs_tcon *tcon;
+ struct close_cancelled_open *cancelled;
+
+ if (sync_hdr->Command != SMB2_CREATE ||
+ sync_hdr->Status != STATUS_SUCCESS)
+ return 0;
+
+ cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+ if (!cancelled)
+ return -ENOMEM;
+
+ tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
+ sync_hdr->TreeId);
+ if (!tcon) {
+ kfree(cancelled);
+ return -ENOENT;
+ }
+
+ cancelled->fid.persistent_fid = rsp->PersistentFileId;
+ cancelled->fid.volatile_fid = rsp->VolatileFileId;
+ cancelled->tcon = tcon;
+ INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+ queue_work(cifsiod_wq, &cancelled->work);
+
+ return 0;
+}
#include <linux/vfs.h>
#include <linux/falloc.h>
#include <linux/scatterlist.h>
+#include <linux/uuid.h>
#include <crypto/aead.h>
#include "cifsglob.h"
#include "smb2pdu.h"
return rc;
}
-static int
-smb2_clone_range(const unsigned int xid,
+static ssize_t
+smb2_copychunk_range(const unsigned int xid,
struct cifsFileInfo *srcfile,
struct cifsFileInfo *trgtfile, u64 src_off,
u64 len, u64 dest_off)
struct cifs_tcon *tcon;
int chunks_copied = 0;
bool chunk_sizes_updated = false;
+ ssize_t bytes_written, total_bytes_written = 0;
pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
if (pcchunk == NULL)
return -ENOMEM;
- cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n");
+ cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n");
/* Request a key from the server to identify the source of the copy */
rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
srcfile->fid.persistent_fid,
}
chunks_copied++;
- src_off += le32_to_cpu(retbuf->TotalBytesWritten);
- dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
- len -= le32_to_cpu(retbuf->TotalBytesWritten);
+ bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
+ src_off += bytes_written;
+ dest_off += bytes_written;
+ len -= bytes_written;
+ total_bytes_written += bytes_written;
- cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+ cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
le32_to_cpu(retbuf->ChunksWritten),
le32_to_cpu(retbuf->ChunkBytesWritten),
- le32_to_cpu(retbuf->TotalBytesWritten));
+ bytes_written);
} else if (rc == -EINVAL) {
if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
goto cchunk_out;
cchunk_out:
kfree(pcchunk);
kfree(retbuf);
- return rc;
+ if (rc)
+ return rc;
+ else
+ return total_bytes_written;
}
static int
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb2_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.get_dfs_refer = smb2_get_dfs_refer,
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb21_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.enum_snapshots = smb3_enum_snapshots,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
.validate_negotiate = smb3_validate_negotiate,
.wp_retry_size = smb2_wp_retry_size,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
/* .validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */
.wp_retry_size = smb2_wp_retry_size,
* but for time being this is our only auth choice so doesn't matter.
* We just found a server which sets blob length to zero expecting raw.
*/
- if (blob_length == 0)
+ if (blob_length == 0) {
cifs_dbg(FYI, "missing security blob on negprot\n");
+ server->sec_ntlmssp = true;
+ }
rc = cifs_enable_signing(server, ses->sign);
if (rc)
else
return -EIO;
- if (tcon && tcon->bad_network_name)
- return -ENOENT;
-
unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
if (unc_path == NULL)
return -ENOMEM;
return -EINVAL;
}
+ /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+ if (tcon)
+ tcon->tid = 0;
+
rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
if (rc) {
kfree(unc_path);
tcon_error_exit:
if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
- if (tcon)
- tcon->bad_network_name = true;
}
goto tcon_exit;
}
struct cifs_tcon *tcon, *tcon2;
struct list_head tmp_list;
int tcon_exist = false;
+ int rc;
+ int resched = false;
+
/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
mutex_lock(&server->reconnect_mutex);
spin_unlock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
- if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon))
+ rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon);
+ if (!rc)
cifs_reopen_persistent_handles(tcon);
+ else
+ resched = true;
list_del_init(&tcon->rlist);
cifs_put_tcon(tcon);
}
cifs_dbg(FYI, "Reconnecting tcons finished\n");
+ if (resched)
+ queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
mutex_unlock(&server->reconnect_mutex);
/* now we can safely release srv struct */
struct smb_rqst *rqst);
extern struct mid_q_entry *smb2_setup_async_request(
struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+ __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+ __u64 ses_id, __u32 tid);
extern int smb2_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
extern int smb3_calc_signature(struct smb_rqst *rqst,
extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
const u64 persistent_fid, const u64 volatile_fid,
const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+ struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id,
struct kstatfs *FSData);
return 0;
}
-struct cifs_ses *
-smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+static struct cifs_ses *
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
struct cifs_ses *ses;
- spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
if (ses->Suid != ses_id)
continue;
- spin_unlock(&cifs_tcp_ses_lock);
return ses;
}
+
+ return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+ struct cifs_ses *ses;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
spin_unlock(&cifs_tcp_ses_lock);
+ return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid)
+{
+ struct cifs_tcon *tcon;
+
+ list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+ if (tcon->tid != tid)
+ continue;
+ ++tcon->tc_count;
+ return tcon;
+ }
+
return NULL;
}
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid)
+{
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
+ if (!ses) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ return NULL;
+ }
+ tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ return tcon;
+}
+
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
+ cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid);
send_cancel(ses->server, rqst, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+ midQ->mid_flags |= MID_WAIT_CANCELLED;
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
add_credits(ses->server, 1, optype);
}
spin_lock_irq(&mapping->tree_lock);
+ if (!entry) {
+ /*
+ * We needed to drop the page_tree lock while calling
+ * radix_tree_preload() and we didn't have an entry to
+ * lock. See if another thread inserted an entry at
+ * our index during this time.
+ */
+ entry = __radix_tree_lookup(&mapping->page_tree, index,
+ NULL, &slot);
+ if (entry) {
+ radix_tree_preload_end();
+ spin_unlock_irq(&mapping->tree_lock);
+ goto restart;
+ }
+ }
+
if (pmd_downgrade) {
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
if (err) {
spin_unlock_irq(&mapping->tree_lock);
/*
- * Someone already created the entry? This is a
- * normal failure when inserting PMDs in a range
- * that already contains PTEs. In that case we want
- * to return -EEXIST immediately.
- */
- if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
- goto restart;
- /*
- * Our insertion of a DAX PMD entry failed, most
- * likely because it collided with a PTE sized entry
- * at a different index in the PMD range. We haven't
- * inserted anything into the radix tree and have no
- * waiters to wake.
+ * Our insertion of a DAX entry failed, most likely
+ * because we were inserting a PMD entry and it
+ * collided with a PTE sized entry at a different
+ * index in the PMD range. We haven't inserted
+ * anything into the radix tree and have no waiters to
+ * wake.
*/
return ERR_PTR(err);
}
extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
+extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
- .getattr = ext4_getattr,
+ .getattr = ext4_file_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
int ext4_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct inode *inode;
- unsigned long long delalloc_blocks;
+ struct inode *inode = d_inode(path->dentry);
+ struct ext4_inode *raw_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int flags;
+
+ if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ei->i_crtime.tv_sec;
+ stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
+ }
+
+ flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+ if (flags & EXT4_APPEND_FL)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (flags & EXT4_COMPR_FL)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (flags & EXT4_ENCRYPT_FL)
+ stat->attributes |= STATX_ATTR_ENCRYPTED;
+ if (flags & EXT4_IMMUTABLE_FL)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (flags & EXT4_NODUMP_FL)
+ stat->attributes |= STATX_ATTR_NODUMP;
+
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_ENCRYPTED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
- inode = d_inode(path->dentry);
generic_fillattr(inode, stat);
+ return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int query_flags)
+{
+ struct inode *inode = d_inode(path->dentry);
+ u64 delalloc_blocks;
+
+ ext4_getattr(path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
.tmpfile = ext4_tmpfile,
.rename = ext4_rename2,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_encrypted_symlink_inode_operations = {
.get_link = ext4_encrypted_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_symlink_inode_operations = {
.get_link = page_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_fast_symlink_inode_operations = {
.get_link = simple_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
vma->vm_ops = &hugetlb_vm_ops;
+ /*
+ * Offset passed to mmap (before page shift) could have been
+ * negative when represented as a (l)off_t.
+ */
+ if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+ return -EINVAL;
+
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+ len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+ /* check for overflow */
+ if (len < vma_len)
+ return -EINVAL;
inode_lock(inode);
file_accessed(file);
ret = -ENOMEM;
- len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
if (hugetlb_reserve_pages(inode,
vma->vm_pgoff >> huge_page_order(h),
len >> huge_page_shift(h), vma,
ret = 0;
if (vma->vm_flags & VM_WRITE && inode->i_size < len)
- inode->i_size = len;
+ i_size_write(inode, len);
out:
inode_unlock(inode);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.features.features = 0;
- ret = service_operation(new_op, "orangefs_features", 0);
- orangefs_features = new_op->downcall.resp.features.features;
+ ret = service_operation(new_op, "orangefs_features",
+ ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+ if (!ret)
+ orangefs_features =
+ new_op->downcall.resp.features.features;
+ else
+ orangefs_features = 0;
op_release(new_op);
} else {
orangefs_features = 0;
if ((table->proc_handler == proc_dostring) ||
(table->proc_handler == proc_dointvec) ||
+ (table->proc_handler == proc_douintvec) ||
(table->proc_handler == proc_dointvec_minmax) ||
(table->proc_handler == proc_dointvec_jiffies) ||
(table->proc_handler == proc_dointvec_userhz_jiffies) ||
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+ pmd_t pmd = *pmdp;
+
+ /* See comment in change_huge_pmd() */
+ pmdp_invalidate(vma, addr, pmdp);
+ if (pmd_dirty(*pmdp))
+ pmd = pmd_mkdirty(pmd);
+ if (pmd_young(*pmdp))
+ pmd = pmd_mkyoung(pmd);
pmd = pmd_wrprotect(pmd);
pmd = pmd_clear_soft_dirty(pmd);
int vfs_statx_fd(unsigned int fd, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct fd f = fdget_raw(fd);
+ struct fd f;
int error = -EBADF;
+ if (query_flags & ~KSTAT_QUERY_FLAGS)
+ return -EINVAL;
+
+ f = fdget_raw(fd);
if (f.file) {
error = vfs_getattr(&f.file->f_path, stat,
request_mask, query_flags);
* Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
* at the given name from being referenced.
*
- * The caller must have preset stat->request_mask as for vfs_getattr(). The
- * flags are also used to load up stat->query_flags.
- *
* 0 will be returned on success, and a -ve error code if unsuccessful.
*/
int vfs_statx(int dfd, const char __user *filename, int flags,
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
-static inline int __put_timestamp(struct timespec *kts,
- struct statx_timestamp __user *uts)
-{
- return (__put_user(kts->tv_sec, &uts->tv_sec ) ||
- __put_user(kts->tv_nsec, &uts->tv_nsec ) ||
- __put_user(0, &uts->__reserved ));
-}
-
-/*
- * Set the statx results.
- */
-static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
+static noinline_for_stack int
+cp_statx(const struct kstat *stat, struct statx __user *buffer)
{
- uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
- gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
-
- if (__put_user(stat->result_mask, &buffer->stx_mask ) ||
- __put_user(stat->mode, &buffer->stx_mode ) ||
- __clear_user(&buffer->__spare0, sizeof(buffer->__spare0)) ||
- __put_user(stat->nlink, &buffer->stx_nlink ) ||
- __put_user(uid, &buffer->stx_uid ) ||
- __put_user(gid, &buffer->stx_gid ) ||
- __put_user(stat->attributes, &buffer->stx_attributes ) ||
- __put_user(stat->blksize, &buffer->stx_blksize ) ||
- __put_user(MAJOR(stat->rdev), &buffer->stx_rdev_major ) ||
- __put_user(MINOR(stat->rdev), &buffer->stx_rdev_minor ) ||
- __put_user(MAJOR(stat->dev), &buffer->stx_dev_major ) ||
- __put_user(MINOR(stat->dev), &buffer->stx_dev_minor ) ||
- __put_timestamp(&stat->atime, &buffer->stx_atime ) ||
- __put_timestamp(&stat->btime, &buffer->stx_btime ) ||
- __put_timestamp(&stat->ctime, &buffer->stx_ctime ) ||
- __put_timestamp(&stat->mtime, &buffer->stx_mtime ) ||
- __put_user(stat->ino, &buffer->stx_ino ) ||
- __put_user(stat->size, &buffer->stx_size ) ||
- __put_user(stat->blocks, &buffer->stx_blocks ) ||
- __clear_user(&buffer->__spare1, sizeof(buffer->__spare1)) ||
- __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
- return -EFAULT;
-
- return 0;
+ struct statx tmp;
+
+ memset(&tmp, 0, sizeof(tmp));
+
+ tmp.stx_mask = stat->result_mask;
+ tmp.stx_blksize = stat->blksize;
+ tmp.stx_attributes = stat->attributes;
+ tmp.stx_nlink = stat->nlink;
+ tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
+ tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
+ tmp.stx_mode = stat->mode;
+ tmp.stx_ino = stat->ino;
+ tmp.stx_size = stat->size;
+ tmp.stx_blocks = stat->blocks;
+ tmp.stx_attributes_mask = stat->attributes_mask;
+ tmp.stx_atime.tv_sec = stat->atime.tv_sec;
+ tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
+ tmp.stx_btime.tv_sec = stat->btime.tv_sec;
+ tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
+ tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
+ tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
+ tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
+ tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
+ tmp.stx_rdev_major = MAJOR(stat->rdev);
+ tmp.stx_rdev_minor = MINOR(stat->rdev);
+ tmp.stx_dev_major = MAJOR(stat->dev);
+ tmp.stx_dev_minor = MINOR(stat->dev);
+
+ return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
/**
struct kstat stat;
int error;
+ if (mask & STATX__RESERVED)
+ return -EINVAL;
if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
return -EINVAL;
- if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
- return -EFAULT;
if (filename)
error = vfs_statx(dfd, filename, flags, &stat, mask);
error = vfs_statx_fd(dfd, &stat, mask, flags);
if (error)
return error;
- return statx_set_result(&stat, buffer);
+
+ return cp_statx(&stat, buffer);
}
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
{
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
struct kobject *kobj = of->kn->parent->priv;
- size_t len;
+ ssize_t len;
/*
* If buf != of->prealloc_buf, we don't know how
if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (len < 0)
+ return len;
if (pos) {
if (len <= pos)
return 0;
len -= pos;
memmove(buf, buf + pos, len);
}
- return min(count, len);
+ return min_t(ssize_t, count, len);
}
/* kernfs write callback for regular sysfs files */
* protocols: aa:... bb:...
*/
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
- pending, total, UFFD_API, UFFD_API_FEATURES,
+ pending, total, UFFD_API, ctx->features,
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern int xfs_dir2_sf_verify(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp,
- int size);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
/* xfs_dir2_readdir.c */
extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
/* Verify the consistency of an inline directory. */
int
xfs_dir2_sf_verify(
- struct xfs_mount *mp,
- struct xfs_dir2_sf_hdr *sfp,
- int size)
+ struct xfs_inode *ip)
{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
char *endp;
const struct xfs_dir_ops *dops;
+ struct xfs_ifork *ifp;
xfs_ino_t ino;
int i;
int i8count;
int offset;
+ int size;
+ int error;
__uint8_t filetype;
+ ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+ /*
+ * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+ * so we can only trust the mountpoint to have the right pointer.
+ */
dops = xfs_dir_get_ops(mp, NULL);
+ ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+ size = ifp->if_bytes;
+
/*
* Give up if the directory is way too short.
*/
- XFS_WANT_CORRUPTED_RETURN(mp, size >
- offsetof(struct xfs_dir2_sf_hdr, parent));
- XFS_WANT_CORRUPTED_RETURN(mp, size >=
- xfs_dir2_sf_hdr_size(sfp->i8count));
+ if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+ size < xfs_dir2_sf_hdr_size(sfp->i8count))
+ return -EFSCORRUPTED;
endp = (char *)sfp + size;
/* Check .. entry */
ino = dops->sf_get_parent_ino(sfp);
i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
offset = dops->data_first_offset;
/* Check all reported entries */
* Check the fixed-offset parts of the structure are
* within the data buffer.
*/
- XFS_WANT_CORRUPTED_RETURN(mp,
- ((char *)sfep + sizeof(*sfep)) < endp);
+ if (((char *)sfep + sizeof(*sfep)) >= endp)
+ return -EFSCORRUPTED;
/* Don't allow names with known bad length. */
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0);
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN);
+ if (sfep->namelen == 0)
+ return -EFSCORRUPTED;
/*
* Check that the variable-length part of the structure is
* name component, so nextentry is an acceptable test.
*/
next_sfep = dops->sf_nextentry(sfp, sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep);
+ if (endp < (char *)next_sfep)
+ return -EFSCORRUPTED;
/* Check that the offsets always increase. */
- XFS_WANT_CORRUPTED_RETURN(mp,
- xfs_dir2_sf_get_offset(sfep) >= offset);
+ if (xfs_dir2_sf_get_offset(sfep) < offset)
+ return -EFSCORRUPTED;
/* Check the inode number. */
ino = dops->sf_get_ino(sfp, sfep);
i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
/* Check the file type. */
filetype = dops->sf_get_ftype(sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX);
+ if (filetype >= XFS_DIR3_FT_MAX)
+ return -EFSCORRUPTED;
offset = xfs_dir2_sf_get_offset(sfep) +
dops->data_entsize(sfep->namelen);
sfep = next_sfep;
}
- XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count);
- XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp);
+ if (i8count != sfp->i8count)
+ return -EFSCORRUPTED;
+ if ((void *)sfep != (void *)endp)
+ return -EFSCORRUPTED;
/* Make sure this whole thing ought to be in local format. */
- XFS_WANT_CORRUPTED_RETURN(mp, offset +
- (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
- (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize);
+ if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+ (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+ return -EFSCORRUPTED;
return 0;
}
if (error)
return error;
+ /* Check inline dir contents. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ dip->di_format == XFS_DINODE_FMT_LOCAL) {
+ error = xfs_dir2_sf_verify(ip);
+ if (error) {
+ xfs_idestroy_fork(ip, XFS_DATA_FORK);
+ return error;
+ }
+ }
+
if (xfs_is_reflink_inode(ip)) {
ASSERT(ip->i_cowfp == NULL);
xfs_ifork_init_cow(ip);
int whichfork,
int size)
{
- int error;
-
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
return -EFSCORRUPTED;
}
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(ip->i_mount,
- (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip),
- size);
- if (error)
- return error;
- }
-
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
* In these cases, the format always takes precedence, because the
* format indicates the current state of the fork.
*/
-int
+void
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
- int error;
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
if (!iip)
- return 0;
+ return;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
*/
if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
- return 0;
+ return;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
switch (XFS_IFORK_FORMAT(ip, whichfork)) {
case XFS_DINODE_FMT_LOCAL:
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(mp,
- (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data,
- ifp->if_bytes);
- if (error)
- return error;
- }
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(0);
break;
}
- return 0;
}
/*
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
-int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
+void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_inode *, int);
void xfs_idata_realloc(struct xfs_inode *, int, int);
/*
* Now that we've unmap all full blocks we'll have to zero out any
* partial block at the beginning and/or end. xfs_zero_range is
- * smart enough to skip any holes, including those we just created.
+ * smart enough to skip any holes, including those we just created,
+ * but we must take care not to zero beyond EOF and enlarge i_size.
*/
+
+ if (offset >= XFS_ISIZE(ip))
+ return 0;
+
+ if (offset + len > XFS_ISIZE(ip))
+ len = XFS_ISIZE(ip) - offset;
+
return xfs_zero_range(ip, offset, len, NULL);
}
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_inode_zone;
struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_dinode *dip;
struct xfs_mount *mp = ip->i_mount;
- int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
if (ip->i_d.di_version < 3)
ip->i_d.di_flushiter++;
+ /* Check the inline directory data. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+ xfs_dir2_sf_verify(ip))
+ goto corrupt_out;
+
/*
* Copy the dirty parts of the inode into the on-disk inode. We always
* copy out the core of the inode, because if the inode is dirty at all
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
ip->i_d.di_flushiter = 0;
- error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
- if (error)
- return error;
- if (XFS_IFORK_Q(ip)) {
- error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
- if (error)
- return error;
- }
+ xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
+ if (XFS_IFORK_Q(ip))
+ xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
xfs_inobp_check(mp, bp);
/*
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+ if (ip->i_d.di_version == 3) {
+ if (request_mask & STATX_BTIME) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
+ stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+ }
+ }
+
+ if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+ stat->attributes |= STATX_ATTR_NODUMP;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
return error;
bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
- buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+ buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
do {
struct xfs_inobt_rec_incore r;
int stat;
*/
#ifndef RO_AFTER_INIT_DATA
#define RO_AFTER_INIT_DATA \
- __start_ro_after_init = .; \
+ VMLINUX_SYMBOL(__start_ro_after_init) = .; \
*(.data..ro_after_init) \
- __end_ro_after_init = .;
+ VMLINUX_SYMBOL(__end_ro_after_init) = .;
#endif
/*
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
+void kvm_vgic_init_cpu_hardware(void);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
atomic_t nr_active;
+ struct delayed_work delayed_run_work;
struct delayed_work delay_work;
struct hlist_node cpuhp_dead;
void blk_mq_start_hw_queues(struct request_queue *q);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */
#define QUEUE_FLAG_DAX 26 /* device supports DAX */
#define QUEUE_FLAG_STATS 27 /* track rq completion times */
-#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
pr_cont_kernfs_path(cgrp->kn);
}
+static inline void cgroup_init_kthreadd(void)
+{
+ /*
+ * kthreadd is inherited by all kthreads, keep it in the root so
+ * that the new kthreads are guaranteed to stay in the root until
+ * initialization is finished.
+ */
+ current->no_cgroup_migration = 1;
+}
+
+static inline void cgroup_kthread_ready(void)
+{
+ /*
+ * This kthread finished initialization. The creator should have
+ * set PF_NO_SETAFFINITY if this kthread should stay in the root.
+ */
+ current->no_cgroup_migration = 0;
+}
+
#else /* !CONFIG_CGROUPS */
struct cgroup_subsys_state;
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
+static inline void cgroup_init_kthreadd(void) {}
+static inline void cgroup_kthread_ready(void) {}
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct elevator_queue *);
+extern void elevator_exit(struct request_queue *, struct elevator_queue *);
extern int elevator_change(struct request_queue *, const char *);
extern bool elv_bio_merge_ok(struct request *, struct bio *);
extern struct elevator_queue *elevator_alloc(struct request_queue *,
#define GICH_MISR_EOI (1 << 0)
#define GICH_MISR_U (1 << 1)
+#define GICV_PMR_PRIORITY_SHIFT 3
+#define GICV_PMR_PRIORITY_MASK (0x1f << GICV_PMR_PRIORITY_SHIFT)
+
#ifndef __ASSEMBLY__
#include <linux/irqdomain.h>
___pud; \
})
-#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \
-({ \
- unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \
- pmd_t ___pmd; \
- \
- ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \
- mmu_notifier_invalidate_range(__mm, ___haddr, \
- ___haddr + HPAGE_PMD_SIZE); \
- \
- ___pmd; \
-})
-
/*
* set_pte_at_notify() sets the pte _after_ running the notifier.
* This is safe to start by updating the secondary MMUs, because the primary MMU
#define ptep_clear_flush_notify ptep_clear_flush
#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
#define pudp_huge_clear_flush_notify pudp_huge_clear_flush
-#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear
#define set_pte_at_notify set_pte_at
#endif /* CONFIG_MMU_NOTIFIER */
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */
- NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */
+ NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */
+ NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */
};
/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */
- NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */
- NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */
- NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */
- NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */
+ NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */
+ NVMF_RDMA_PRTYPE_IB = 2, /* InfiniBand */
+ NVMF_RDMA_PRTYPE_ROCE = 3, /* InfiniBand RoCE */
+ NVMF_RDMA_PRTYPE_ROCEV2 = 4, /* InfiniBand RoCEV2 */
+ NVMF_RDMA_PRTYPE_IWARP = 5, /* IWARP */
};
/* RDMA Connection Management Service Type codes for Discovery Log Page
* entry TSAS RDMA_CMS field
*/
enum {
- NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */
+ NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */
};
#define NVMF_AQ_DEPTH 32
extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev);
+extern int pinctrl_enable(struct pinctrl_dev *pctldev);
-/* Please use pinctrl_register_and_init() instead */
+/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */
extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data);
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
+#ifdef CONFIG_CGROUPS
+ /* disallow userland-initiated cgroup migration */
+ unsigned no_cgroup_migration:1;
+#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
unsigned int nlink;
uint32_t blksize; /* Preferred I/O size */
u64 attributes;
+ u64 attributes_mask;
#define KSTAT_ATTR_FS_IOC_FLAGS \
(STATX_ATTR_COMPRESSED | \
STATX_ATTR_IMMUTABLE | \
};
union {
unsigned long nr_segs;
- int idx;
+ struct {
+ int idx;
+ int start_idx;
+ };
};
};
size_t iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
+void iov_iter_revert(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
unsigned int feature_table_size;
const unsigned int *feature_table_legacy;
unsigned int feature_table_size_legacy;
+ int (*validate)(struct virtio_device *dev);
int (*probe)(struct virtio_device *dev);
void (*scan)(struct virtio_device *dev);
void (*remove)(struct virtio_device *dev);
TRANSPORT_ISTATE_PROCESSING = 11,
TRANSPORT_COMPLETE_QF_WP = 18,
TRANSPORT_COMPLETE_QF_OK = 19,
+ TRANSPORT_COMPLETE_QF_ERR = 20,
};
/* Used for struct se_cmd->se_cmd_flags */
u16 tg_pt_gp_id;
int tg_pt_gp_valid_id;
int tg_pt_gp_alua_supported_states;
- int tg_pt_gp_alua_pending_state;
- int tg_pt_gp_alua_previous_state;
int tg_pt_gp_alua_access_status;
int tg_pt_gp_alua_access_type;
int tg_pt_gp_nonop_delay_msecs;
int tg_pt_gp_pref;
int tg_pt_gp_write_metadata;
u32 tg_pt_gp_members;
- atomic_t tg_pt_gp_alua_access_state;
+ int tg_pt_gp_alua_access_state;
atomic_t tg_pt_gp_ref_cnt;
spinlock_t tg_pt_gp_lock;
- struct mutex tg_pt_gp_md_mutex;
+ struct mutex tg_pt_gp_transition_mutex;
struct se_device *tg_pt_gp_dev;
struct config_group tg_pt_gp_group;
struct list_head tg_pt_gp_list;
struct list_head tg_pt_gp_lun_list;
struct se_lun *tg_pt_gp_alua_lun;
struct se_node_acl *tg_pt_gp_alua_nacl;
- struct work_struct tg_pt_gp_transition_work;
- struct completion *tg_pt_gp_transition_complete;
};
struct t10_vpd {
u64 unpacked_lun;
#define SE_LUN_LINK_MAGIC 0xffff7771
u32 lun_link_magic;
+ bool lun_shutdown;
bool lun_access_ro;
u32 lun_index;
header-y += unix_diag.h
header-y += usbdevice_fs.h
header-y += usbip.h
+header-y += userio.h
header-y += utime.h
header-y += utsname.h
header-y += uuid.h
__u64 stx_ino; /* Inode number */
__u64 stx_size; /* File size */
__u64 stx_blocks; /* Number of 512-byte blocks allocated */
- __u64 __spare1[1];
+ __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
/* 0x40 */
struct statx_timestamp stx_atime; /* Last access time */
struct statx_timestamp stx_btime; /* File creation time */
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
/*
- * Attributes to be found in stx_attributes
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
*
* These give information about the features or the state of a file that might
* be of use to ordinary userspace programs such as GUIs or ls rather than
* configuration space */
#define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20)
/* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled)
+#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
/* Virtio ABI version, this must match exactly */
#define VIRTIO_PCI_ABI_VERSION 0
/* queue msgs to send via kauditd_task */
static struct sk_buff_head audit_queue;
-static void kauditd_hold_skb(struct sk_buff *skb);
/* queue msgs due to temporary unicast send problems */
static struct sk_buff_head audit_retry_queue;
/* queue msgs waiting for new auditd connection */
}
/**
- * auditd_reset - Disconnect the auditd connection
- *
- * Description:
- * Break the auditd/kauditd connection and move all the queued records into the
- * hold queue in case auditd reconnects.
- */
-static void auditd_reset(void)
-{
- struct sk_buff *skb;
-
- /* if it isn't already broken, break the connection */
- rcu_read_lock();
- if (auditd_conn.pid)
- auditd_set(0, 0, NULL);
- rcu_read_unlock();
-
- /* flush all of the main and retry queues to the hold queue */
- while ((skb = skb_dequeue(&audit_retry_queue)))
- kauditd_hold_skb(skb);
- while ((skb = skb_dequeue(&audit_queue)))
- kauditd_hold_skb(skb);
-}
-
-/**
* kauditd_print_skb - Print the audit record to the ring buffer
* @skb: audit record
*
{
/* put the record back in the queue at the same place */
skb_queue_head(&audit_hold_queue, skb);
-
- /* fail the auditd connection */
- auditd_reset();
}
/**
/* we have no other options - drop the message */
audit_log_lost("kauditd hold queue overflow");
kfree_skb(skb);
-
- /* fail the auditd connection */
- auditd_reset();
}
/**
}
/**
+ * auditd_reset - Disconnect the auditd connection
+ *
+ * Description:
+ * Break the auditd/kauditd connection and move all the queued records into the
+ * hold queue in case auditd reconnects.
+ */
+static void auditd_reset(void)
+{
+ struct sk_buff *skb;
+
+ /* if it isn't already broken, break the connection */
+ rcu_read_lock();
+ if (auditd_conn.pid)
+ auditd_set(0, 0, NULL);
+ rcu_read_unlock();
+
+ /* flush all of the main and retry queues to the hold queue */
+ while ((skb = skb_dequeue(&audit_retry_queue)))
+ kauditd_hold_skb(skb);
+ while ((skb = skb_dequeue(&audit_queue)))
+ kauditd_hold_skb(skb);
+}
+
+/**
* auditd_send_unicast_skb - Send a record via unicast to auditd
* @skb: audit record
*
NULL, kauditd_rehold_skb);
if (rc < 0) {
sk = NULL;
+ auditd_reset();
goto main_queue;
}
NULL, kauditd_hold_skb);
if (rc < 0) {
sk = NULL;
+ auditd_reset();
goto main_queue;
}
* unicast, dump failed record sends to the retry queue; if
* sk == NULL due to previous failures we will just do the
* multicast send and move the record to the retry queue */
- kauditd_send_queue(sk, portid, &audit_queue, 1,
- kauditd_send_multicast_skb,
- kauditd_retry_skb);
+ rc = kauditd_send_queue(sk, portid, &audit_queue, 1,
+ kauditd_send_multicast_skb,
+ kauditd_retry_skb);
+ if (sk == NULL || rc < 0)
+ auditd_reset();
+ sk = NULL;
/* drop our netns reference, no auditd sends past this line */
if (net) {
put_net(net);
net = NULL;
}
- sk = NULL;
/* we have processed all the queues so wake everyone */
wake_up(&audit_backlog_wait);
extern int audit_filter(int msgtype, unsigned int listtype);
#ifdef CONFIG_AUDITSYSCALL
-extern int __audit_signal_info(int sig, struct task_struct *t);
-static inline int audit_signal_info(int sig, struct task_struct *t)
-{
- if (auditd_test_task(t) || (audit_signals && !audit_dummy_context()))
- return __audit_signal_info(sig, t);
- return 0;
-}
+extern int audit_signal_info(int sig, struct task_struct *t);
extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
extern struct list_head *audit_killed_trees(void);
#else
* If the audit subsystem is being terminated, record the task (pid)
* and uid that is doing that.
*/
-int __audit_signal_info(int sig, struct task_struct *t)
+int audit_signal_info(int sig, struct task_struct *t)
{
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
kuid_t uid = current_uid(), t_uid = task_uid(t);
- if (auditd_test_task(t)) {
- if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
- audit_sig_pid = task_tgid_nr(tsk);
- if (uid_valid(tsk->loginuid))
- audit_sig_uid = tsk->loginuid;
- else
- audit_sig_uid = uid;
- security_task_getsecid(tsk, &audit_sig_sid);
- }
- if (!audit_signals || audit_dummy_context())
- return 0;
+ if (auditd_test_task(t) &&
+ (sig == SIGTERM || sig == SIGHUP ||
+ sig == SIGUSR1 || sig == SIGUSR2)) {
+ audit_sig_pid = task_tgid_nr(tsk);
+ if (uid_valid(tsk->loginuid))
+ audit_sig_uid = tsk->loginuid;
+ else
+ audit_sig_uid = uid;
+ security_task_getsecid(tsk, &audit_sig_sid);
}
+ if (!audit_signals || audit_dummy_context())
+ return 0;
+
/* optimize the common case by putting first signal recipient directly
* in audit_context */
if (!ctx->target_pid) {
LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
off = IMM;
load_word:
- /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
- * only appearing in the programs where ctx ==
- * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
- * == BPF_R6, bpf_convert_filter() saves it in BPF_R6,
- * internal BPF verifier will check that BPF_R6 ==
- * ctx.
+ /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+ * appearing in the programs where ctx == skb
+ * (see may_access_skb() in the verifier). All programs
+ * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
+ * bpf_convert_filter() saves it in BPF_R6, internal BPF
+ * verifier will check that BPF_R6 == ctx.
*
* BPF_ABS and BPF_IND are wrappers of function calls,
* so they scratch BPF_R1-BPF_R5 registers, preserve
* path is super cold. Let's just sleep a bit and retry.
*/
pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
- if (IS_ERR(pinned_sb) ||
+ if (IS_ERR_OR_NULL(pinned_sb) ||
!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
mutex_unlock(&cgroup_mutex);
if (!IS_ERR_OR_NULL(pinned_sb))
tsk = tsk->group_leader;
/*
- * Workqueue threads may acquire PF_NO_SETAFFINITY and become
- * trapped in a cpuset, or RT worker may be born in a cgroup
- * with no rt_runtime allocated. Just say no.
+ * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+ * If userland migrates such a kthread to a non-root cgroup, it can
+ * become trapped in a cpuset, or RT kthread may be born in a
+ * cgroup with no rt_runtime allocated. Just say no.
*/
- if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out_unlock_rcu;
}
struct cpumask *
irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
{
- int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec;
+ int n, nodes, cpus_per_vec, extra_vecs, curvec;
int affv = nvecs - affd->pre_vectors - affd->post_vectors;
int last_affv = affv + affd->pre_vectors;
nodemask_t nodemsk = NODE_MASK_NONE;
goto done;
}
- /* Spread the vectors per node */
- vecs_per_node = affv / nodes;
- /* Account for rounding errors */
- extra_vecs = affv - (nodes * vecs_per_node);
-
for_each_node_mask(n, nodemsk) {
- int ncpus, v, vecs_to_assign = vecs_per_node;
+ int ncpus, v, vecs_to_assign, vecs_per_node;
+
+ /* Spread the vectors per node */
+ vecs_per_node = (affv - curvec) / nodes;
/* Get the cpus on this node which are in the mask */
cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n));
/* Calculate the number of cpus per vector */
ncpus = cpumask_weight(nmsk);
+ vecs_to_assign = min(vecs_per_node, ncpus);
+
+ /* Account for rounding errors */
+ extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);
for (v = 0; curvec < last_affv && v < vecs_to_assign;
curvec++, v++) {
/* Account for extra vectors to compensate rounding errors */
if (extra_vecs) {
cpus_per_vec++;
- if (!--extra_vecs)
- vecs_per_node++;
+ --extra_vecs;
}
irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
}
if (curvec >= last_affv)
break;
+ --nodes;
}
done:
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
+#include <linux/cgroup.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
+ cgroup_kthread_ready();
__kthread_parkme(self);
ret = threadfn(data);
}
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
+ cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
WARN_ON(!task->ptrace || task->parent != current);
+ /*
+ * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+ * Recheck state under the lock to close this race.
+ */
spin_lock_irq(&task->sighand->siglock);
- if (__fatal_signal_pending(task))
- wake_up_state(task, __TASK_TRACED);
- else
- task->state = TASK_TRACED;
+ if (task->state == __TASK_TRACED) {
+ if (__fatal_signal_pending(task))
+ wake_up_state(task, __TASK_TRACED);
+ else
+ task->state = TASK_TRACED;
+ }
spin_unlock_irq(&task->sighand->siglock);
}
if (write) {
if (*negp)
return -EINVAL;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
+ *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
rb_data[cpu].cnt = cpu;
rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
"rbtester/%d", cpu);
- if (WARN_ON(!rb_threads[cpu])) {
+ if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_threads[cpu]);
goto out_free;
}
/* Now create the rb hammer! */
rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
- if (WARN_ON(!rb_hammer)) {
+ if (WARN_ON(IS_ERR(rb_hammer))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_hammer);
goto out_free;
}
}
EXPORT_SYMBOL(iov_iter_advance);
+void iov_iter_revert(struct iov_iter *i, size_t unroll)
+{
+ if (!unroll)
+ return;
+ i->count += unroll;
+ if (unlikely(i->type & ITER_PIPE)) {
+ struct pipe_inode_info *pipe = i->pipe;
+ int idx = i->idx;
+ size_t off = i->iov_offset;
+ while (1) {
+ size_t n = off - pipe->bufs[idx].offset;
+ if (unroll < n) {
+ off -= (n - unroll);
+ break;
+ }
+ unroll -= n;
+ if (!unroll && idx == i->start_idx) {
+ off = 0;
+ break;
+ }
+ if (!idx--)
+ idx = pipe->buffers - 1;
+ off = pipe->bufs[idx].offset + pipe->bufs[idx].len;
+ }
+ i->iov_offset = off;
+ i->idx = idx;
+ pipe_truncate(i);
+ return;
+ }
+ if (unroll <= i->iov_offset) {
+ i->iov_offset -= unroll;
+ return;
+ }
+ unroll -= i->iov_offset;
+ if (i->type & ITER_BVEC) {
+ const struct bio_vec *bvec = i->bvec;
+ while (1) {
+ size_t n = (--bvec)->bv_len;
+ i->nr_segs++;
+ if (unroll <= n) {
+ i->bvec = bvec;
+ i->iov_offset = n - unroll;
+ return;
+ }
+ unroll -= n;
+ }
+ } else { /* same logics for iovec and kvec */
+ const struct iovec *iov = i->iov;
+ while (1) {
+ size_t n = (--iov)->iov_len;
+ i->nr_segs++;
+ if (unroll <= n) {
+ i->iov = iov;
+ i->iov_offset = n - unroll;
+ return;
+ }
+ unroll -= n;
+ }
+ }
+}
+EXPORT_SYMBOL(iov_iter_revert);
+
/*
* Return the count of just the current iov_iter segment.
*/
i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
i->iov_offset = 0;
i->count = count;
+ i->start_idx = i->idx;
}
EXPORT_SYMBOL(iov_iter_pipe);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer", buf,
- min(sizeof("defer")-1, count))) {
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
- set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("defer+madvise", buf,
min(sizeof("defer+madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ } else if (!memcmp("defer", buf,
+ min(sizeof("defer")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("madvise", buf,
min(sizeof("madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
deactivate_page(page);
if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
- orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
- tlb->fullmm);
+ pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
orig_pmd = pmd_mkclean(orig_pmd);
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
- int ret = 0;
+ pmd_t entry;
+ bool preserve_write;
+ int ret;
ptl = __pmd_trans_huge_lock(pmd, vma);
- if (ptl) {
- pmd_t entry;
- bool preserve_write = prot_numa && pmd_write(*pmd);
- ret = 1;
+ if (!ptl)
+ return 0;
- /*
- * Avoid trapping faults against the zero page. The read-only
- * data is likely to be read-cached on the local CPU and
- * local/remote hits to the zero page are not interesting.
- */
- if (prot_numa && is_huge_zero_pmd(*pmd)) {
- spin_unlock(ptl);
- return ret;
- }
+ preserve_write = prot_numa && pmd_write(*pmd);
+ ret = 1;
- if (!prot_numa || !pmd_protnone(*pmd)) {
- entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
- entry = pmd_modify(entry, newprot);
- if (preserve_write)
- entry = pmd_mk_savedwrite(entry);
- ret = HPAGE_PMD_NR;
- set_pmd_at(mm, addr, pmd, entry);
- BUG_ON(vma_is_anonymous(vma) && !preserve_write &&
- pmd_write(entry));
- }
- spin_unlock(ptl);
- }
+ /*
+ * Avoid trapping faults against the zero page. The read-only
+ * data is likely to be read-cached on the local CPU and
+ * local/remote hits to the zero page are not interesting.
+ */
+ if (prot_numa && is_huge_zero_pmd(*pmd))
+ goto unlock;
+
+ if (prot_numa && pmd_protnone(*pmd))
+ goto unlock;
+
+ /*
+ * In case prot_numa, we are under down_read(mmap_sem). It's critical
+ * to not clear pmd intermittently to avoid race with MADV_DONTNEED
+ * which is also under down_read(mmap_sem):
+ *
+ * CPU0: CPU1:
+ * change_huge_pmd(prot_numa=1)
+ * pmdp_huge_get_and_clear_notify()
+ * madvise_dontneed()
+ * zap_pmd_range()
+ * pmd_trans_huge(*pmd) == 0 (without ptl)
+ * // skip the pmd
+ * set_pmd_at();
+ * // pmd is re-established
+ *
+ * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
+ * which may break userspace.
+ *
+ * pmdp_invalidate() is required to make sure we don't miss
+ * dirty/young flags set by hardware.
+ */
+ entry = *pmd;
+ pmdp_invalidate(vma, addr, pmd);
+ /*
+ * Recover dirty/young flags. It relies on pmdp_invalidate to not
+ * corrupt them.
+ */
+ if (pmd_dirty(*pmd))
+ entry = pmd_mkdirty(entry);
+ if (pmd_young(*pmd))
+ entry = pmd_mkyoung(entry);
+
+ entry = pmd_modify(entry, newprot);
+ if (preserve_write)
+ entry = pmd_mk_savedwrite(entry);
+ ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
+ BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
+unlock:
+ spin_unlock(ptl);
return ret;
}
enum ttu_flags;
struct tlbflush_unmap_batch;
+
+/*
+ * only for MM internal work items which do not depend on
+ * any allocations or locks which might depend on allocations
+ */
+extern struct workqueue_struct *mm_percpu_wq;
+
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(bm, nmask, nr_bits);
+ if (compat_get_bitmap(bm, nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, bm, alloc_size);
+ if (copy_to_user(nm, bm, alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_set_mempolicy(mode, nm, nr_bits+1);
}
compat_ulong_t, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode, compat_ulong_t, flags)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
nodemask_t bm;
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+ if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+ if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}
*/
static cpumask_t cpus_with_pcps;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON_ONCE(!mm_percpu_wq))
+ return;
+
/* Workqueues cannot recurse */
if (current->flags & PF_WQ_WORKER)
return;
for_each_cpu(cpu, &cpus_with_pcps) {
struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
INIT_WORK(work, drain_local_pages_wq);
- schedule_work_on(cpu, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
}
for_each_cpu(cpu, &cpus_with_pcps)
flush_work(per_cpu_ptr(&pcpu_drain, cpu));
K(node_page_state(pgdat, NR_FILE_MAPPED)),
K(node_page_state(pgdat, NR_FILE_DIRTY)),
K(node_page_state(pgdat, NR_WRITEBACK)),
+ K(node_page_state(pgdat, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
* HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
- K(node_page_state(pgdat, NR_SHMEM)),
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
node_page_state(pgdat, NR_PAGES_SCANNED),
if (pvmw->pmd && !pvmw->pte)
return not_found(pvmw);
- /* Only for THP, seek to next pte entry makes sense */
- if (pvmw->pte) {
- if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
- return not_found(pvmw);
+ if (pvmw->pte)
goto next_pte;
- }
if (unlikely(PageHuge(pvmw->page))) {
/* when pud is not present, pte will be NULL */
while (1) {
if (check_pte(pvmw))
return true;
-next_pte: do {
+next_pte:
+ /* Seek to next pte only makes sense for THP */
+ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+ return not_found(pvmw);
+ do {
pvmw->address += PAGE_SIZE;
- if (pvmw->address >=
+ if (pvmw->address >= pvmw->vma->vm_end ||
+ pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
hpage_nr_pages(pvmw->page) * PAGE_SIZE)
return not_found(pvmw);
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
-/*
- * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
- * workqueue, aiding in getting memory freed.
- */
-static struct workqueue_struct *lru_add_drain_wq;
-
-static int __init lru_init(void)
-{
- lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
-
- if (WARN(!lru_add_drain_wq,
- "Failed to create workqueue lru_add_drain_wq"))
- return -ENOMEM;
-
- return 0;
-}
-early_initcall(lru_init);
-
void lru_add_drain_all(void)
{
static DEFINE_MUTEX(lock);
static struct cpumask has_work;
int cpu;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON(!mm_percpu_wq))
+ return;
+
mutex_lock(&lock);
get_online_cpus();
cpumask_clear(&has_work);
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
- queue_work_on(cpu, lru_add_drain_wq, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
cpumask_set_cpu(cpu, &has_work);
}
}
struct page *page = map[i];
if (page)
__free_page(page);
+ if (!(i % SWAP_CLUSTER_MAX))
+ cond_resched();
}
vfree(map);
}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
-static struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
* to occur in the future. Keep on running the
* update worker thread.
*/
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+ queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
}
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
if (!delayed_work_pending(dw) && need_update(cpu))
- queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+ queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
}
put_online_cpus();
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
vmstat_update);
- vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
}
#endif
+struct workqueue_struct *mm_percpu_wq;
+
void __init init_mm_internals(void)
{
-#ifdef CONFIG_SMP
- int ret;
+ int ret __maybe_unused;
+ mm_percpu_wq = alloc_workqueue("mm_percpu_wq",
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+
+#ifdef CONFIG_SMP
ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
NULL, vmstat_cpu_dead);
if (ret < 0)
spin_lock(&zhdr->page_lock);
}
+/* Try to lock a z3fold page */
+static inline int z3fold_page_trylock(struct z3fold_header *zhdr)
+{
+ return spin_trylock(&zhdr->page_lock);
+}
+
/* Unlock a z3fold page */
static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
{
spin_lock(&pool->lock);
zhdr = list_first_entry_or_null(&pool->unbuddied[i],
struct z3fold_header, buddy);
- if (!zhdr) {
+ if (!zhdr || !z3fold_page_trylock(zhdr)) {
spin_unlock(&pool->lock);
continue;
}
spin_unlock(&pool->lock);
page = virt_to_page(zhdr);
- z3fold_page_lock(zhdr);
if (zhdr->first_chunks == 0) {
if (zhdr->middle_chunks != 0 &&
chunks >= zhdr->start_middle)
struct zspage {
struct {
unsigned int fullness:FULLNESS_BITS;
- unsigned int class:CLASS_BITS;
+ unsigned int class:CLASS_BITS + 1;
unsigned int isolated:ISOLATED_BITS;
unsigned int magic:MAGIC_VAL_BITS;
};
return err;
}
+static void br_dev_uninit(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ br_multicast_uninit_stats(br);
+ br_vlan_flush(br);
+ free_percpu(br->stats);
+}
+
static int br_dev_open(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_init = br_dev_init,
+ .ndo_uninit = br_dev_uninit,
.ndo_start_xmit = br_dev_xmit,
.ndo_get_stats64 = br_get_stats64,
.ndo_set_mac_address = br_set_mac_address,
.ndo_features_check = passthru_features_check,
};
-static void br_dev_free(struct net_device *dev)
-{
- struct net_bridge *br = netdev_priv(dev);
-
- free_percpu(br->stats);
- free_netdev(dev);
-}
-
static struct device_type br_type = {
.name = "bridge",
};
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
- dev->destructor = br_dev_free;
+ dev->destructor = free_netdev;
dev->ethtool_ops = &br_ethtool_ops;
SET_NETDEV_DEVTYPE(dev, &br_type);
dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
br_fdb_delete_by_port(br, NULL, 0, 1);
- br_vlan_flush(br);
br_multicast_dev_del(br);
cancel_delayed_work_sync(&br->gc_work);
out:
spin_unlock_bh(&br->multicast_lock);
-
- free_percpu(br->mcast_stats);
}
int br_multicast_set_router(struct net_bridge *br, unsigned long val)
return 0;
}
+void br_multicast_uninit_stats(struct net_bridge *br)
+{
+ free_percpu(br->mcast_stats);
+}
+
static void mcast_stats_add_dir(u64 *dst, u64 *src)
{
dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
spin_unlock_bh(&br->lock);
}
- err = br_changelink(dev, tb, data);
+ err = register_netdevice(dev);
if (err)
return err;
- return register_netdevice(dev);
+ err = br_changelink(dev, tb, data);
+ if (err)
+ unregister_netdevice(dev);
+ return err;
}
static size_t br_get_size(const struct net_device *brdev)
void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
const struct sk_buff *skb, u8 type, u8 dir);
int br_multicast_init_stats(struct net_bridge *br);
+void br_multicast_uninit_stats(struct net_bridge *br);
void br_multicast_get_stats(const struct net_bridge *br,
const struct net_bridge_port *p,
struct br_mcast_stats *dest);
return 0;
}
+static inline void br_multicast_uninit_stats(struct net_bridge *br)
+{
+}
+
static inline int br_multicast_igmp_type(const struct sk_buff *skb)
{
return 0;
struct iov_iter *to, int len)
{
int start = skb_headlen(skb);
- int i, copy = start - offset;
+ int i, copy = start - offset, start_off = offset, n;
struct sk_buff *frag_iter;
trace_skb_copy_datagram_iovec(skb, len);
if (copy > 0) {
if (copy > len)
copy = len;
- if (copy_to_iter(skb->data + offset, copy, to) != copy)
+ n = copy_to_iter(skb->data + offset, copy, to);
+ offset += n;
+ if (n != copy)
goto short_copy;
if ((len -= copy) == 0)
return 0;
- offset += copy;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
- if (copy_page_to_iter(skb_frag_page(frag),
+ n = copy_page_to_iter(skb_frag_page(frag),
frag->page_offset + offset -
- start, copy, to) != copy)
+ start, copy, to);
+ offset += n;
+ if (n != copy)
goto short_copy;
if (!(len -= copy))
return 0;
- offset += copy;
}
start = end;
}
*/
fault:
+ iov_iter_revert(to, offset - start_off);
return -EFAULT;
short_copy:
__wsum *csump)
{
int start = skb_headlen(skb);
- int i, copy = start - offset;
+ int i, copy = start - offset, start_off = offset;
struct sk_buff *frag_iter;
int pos = 0;
int n;
if (copy > len)
copy = len;
n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+ offset += n;
if (n != copy)
goto fault;
if ((len -= copy) == 0)
return 0;
- offset += copy;
pos = copy;
}
offset - start, copy,
&csum2, to);
kunmap(page);
+ offset += n;
if (n != copy)
goto fault;
*csump = csum_block_add(*csump, csum2, pos);
if (!(len -= copy))
return 0;
- offset += copy;
pos += copy;
}
start = end;
return 0;
fault:
+ iov_iter_revert(to, offset - start_off);
return -EFAULT;
}
}
return 0;
csum_error:
+ iov_iter_revert(&msg->msg_iter, chunk);
return -EINVAL;
fault:
return -EFAULT;
return err;
}
-EXPORT_SYMBOL(dev_change_xdp_fd);
/**
* dev_new_index - allocate an ifindex
clusterip_config_put(cipinfo->config);
- nf_ct_netns_get(par->net, par->family);
+ nf_ct_netns_put(par->net, par->family);
}
#ifdef CONFIG_COMPAT
tcp_init_send_head(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
+ tcp_saved_syn_free(tp);
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct sk_buff *skb;
+ bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
bool is_reneg; /* is receiver reneging on SACKs? */
bool mark_lost;
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
- /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
- * if a previous recovery is underway, otherwise it may incorrectly
- * call a timeout spurious if some previously retransmitted packets
- * are s/acked (sec 3.2). We do not apply that retriction since
- * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
- * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
- * on PTMU discovery to avoid sending new data.
+ /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+ * loss recovery is underway except recurring timeout(s) on
+ * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
+ *
+ * In theory F-RTO can be used repeatedly during loss recovery.
+ * In practice this interacts badly with broken middle-boxes that
+ * falsely raise the receive window, which results in repeated
+ * timeouts and stop-and-go behavior.
*/
- tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size;
+ tp->frto = sysctl_tcp_frto &&
+ (new_recovery || icsk->icsk_retransmits) &&
+ !inet_csk(sk)->icsk_mtup.probe_size;
}
/* If ACK arrived pointing to a remembered SACK, it means that our
{
struct sk_buff *skb;
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
+
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
/* Send a crossed SYN-ACK during socket establishment.
INIT_LIST_HEAD(&del_list);
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
struct rt6_info *rt = NULL;
+ bool keep;
addrconf_del_dad_work(ifa);
+ keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+ !addr_is_local(&ifa->addr);
+ if (!keep)
+ list_move(&ifa->if_list, &del_list);
+
write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
- if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
- !addr_is_local(&ifa->addr)) {
+ if (keep) {
/* set state to skip the notifier below */
state = INET6_IFADDR_STATE_DEAD;
ifa->state = 0;
} else {
state = ifa->state;
ifa->state = INET6_IFADDR_STATE_DEAD;
-
- list_move(&ifa->if_list, &del_list);
}
spin_unlock_bh(&ifa->lock);
} else
err = pppol2tp_session_setsockopt(sk, session, optname, val);
- err = 0;
-
end_put_sess:
sock_put(sk);
end:
err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
sock_put(ps->tunnel_sock);
- } else
+ if (err)
+ goto end_put_sess;
+ } else {
err = pppol2tp_session_getsockopt(sk, session, optname, &val);
+ if (err)
+ goto end_put_sess;
+ }
err = -EFAULT;
if (put_user(len, optlen))
hlist_del_rcu(&exp->hnode);
net->ct.expect_count--;
- hlist_del(&exp->lnode);
+ hlist_del_rcu(&exp->lnode);
master_help->expecting[exp->class]--;
nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
/* two references : one for hash insert, one for the timer */
refcount_add(2, &exp->use);
- hlist_add_head(&exp->lnode, &master_help->expectations);
+ hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
master_help->expecting[exp->class]++;
hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
{
struct nf_conntrack_helper *h;
+ rcu_read_lock();
+
h = __nf_conntrack_helper_find(name, l3num, protonum);
#ifdef CONFIG_MODULES
if (h == NULL) {
- if (request_module("nfct-helper-%s", name) == 0)
+ rcu_read_unlock();
+ if (request_module("nfct-helper-%s", name) == 0) {
+ rcu_read_lock();
h = __nf_conntrack_helper_find(name, l3num, protonum);
+ } else {
+ return h;
+ }
}
#endif
if (h != NULL && !try_module_get(h->me))
h = NULL;
+ rcu_read_unlock();
+
return h;
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
+/* Caller should hold the rcu lock */
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_name(const char *name)
{
struct nf_ct_helper_expectfn *cur;
bool found = false;
- rcu_read_lock();
list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
if (!strcmp(cur->name, name)) {
found = true;
break;
}
}
- rcu_read_unlock();
return found ? cur : NULL;
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name);
+/* Caller should hold the rcu lock */
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_symbol(const void *symbol)
{
struct nf_ct_helper_expectfn *cur;
bool found = false;
- rcu_read_lock();
list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
if (cur->expectfn == symbol) {
found = true;
break;
}
}
- rcu_read_unlock();
return found ? cur : NULL;
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol);
* treat the second attempt as a no-op instead of returning
* an error.
*/
- if (help && help->helper &&
- !strcmp(help->helper->name, helpname))
- return 0;
- else
- return -EBUSY;
+ err = -EBUSY;
+ if (help) {
+ rcu_read_lock();
+ helper = rcu_dereference(help->helper);
+ if (helper && !strcmp(helper->name, helpname))
+ err = 0;
+ rcu_read_unlock();
+ }
+
+ return err;
}
if (!strcmp(helpname, "")) {
err = 0;
if (test_bit(IPS_EXPECTED_BIT, &ct->status))
- events = IPCT_RELATED;
+ events = 1 << IPCT_RELATED;
else
- events = IPCT_NEW;
+ events = 1 << IPCT_NEW;
if (cda[CTA_LABELS] &&
ctnetlink_attach_labels(ct, cda) == 0)
last = (struct nf_conntrack_expect *)cb->args[1];
for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
restart:
- hlist_for_each_entry(exp, &nf_ct_expect_hash[cb->args[0]],
- hnode) {
+ hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
+ hnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
rcu_read_lock();
last = (struct nf_conntrack_expect *)cb->args[1];
restart:
- hlist_for_each_entry(exp, &help->expectations, lnode) {
+ hlist_for_each_entry_rcu(exp, &help->expectations, lnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
if (cb->args[1]) {
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
+ /* No expectation linked to this connection tracking. */
+ if (!nfct_help(ct)) {
+ nf_ct_put(ct);
+ return 0;
+ }
+
c.data = ct;
err = netlink_dump_start(ctnl, skb, nlh, &c);
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
+ rcu_read_lock();
if (cda[CTA_EXPECT_HELP_NAME]) {
const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
helper = __nf_conntrack_helper_find(helpname, u3,
nf_ct_protonum(ct));
if (helper == NULL) {
+ rcu_read_unlock();
#ifdef CONFIG_MODULES
if (request_module("nfct-helper-%s", helpname) < 0) {
err = -EOPNOTSUPP;
goto err_ct;
}
+ rcu_read_lock();
helper = __nf_conntrack_helper_find(helpname, u3,
nf_ct_protonum(ct));
if (helper) {
err = -EAGAIN;
- goto err_ct;
+ goto err_rcu;
}
+ rcu_read_unlock();
#endif
err = -EOPNOTSUPP;
goto err_ct;
exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
if (IS_ERR(exp)) {
err = PTR_ERR(exp);
- goto err_ct;
+ goto err_rcu;
}
err = nf_ct_expect_related_report(exp, portid, report);
nf_ct_expect_put(exp);
+err_rcu:
+ rcu_read_unlock();
err_ct:
nf_ct_put(ct);
return err;
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
if (idev != NULL) {
+ read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
newdst = ifa->addr;
addr = true;
break;
}
+ read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
enum nft_registers sreg:8;
enum nft_registers dreg:8;
u8 len;
+ bool autogen_seed:1;
u32 modulus;
u32 seed;
u32 offset;
if (priv->offset + priv->modulus - 1 < priv->offset)
return -EOVERFLOW;
- if (tb[NFTA_HASH_SEED])
+ if (tb[NFTA_HASH_SEED]) {
priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
- else
+ } else {
+ priv->autogen_seed = true;
get_random_bytes(&priv->seed, sizeof(priv->seed));
+ }
return nft_validate_register_load(priv->sreg, len) &&
nft_validate_register_store(ctx, priv->dreg, NULL,
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
+ if (!priv->autogen_seed &&
+ nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
goto nla_put_failure;
if (priv->offset != 0)
if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
tcp_hdrlen = tcph->doff * 4;
- if (len < tcp_hdrlen)
+ if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr))
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
if (len > tcp_hdrlen)
return 0;
+ /* tcph->doff has 4 bits, do not wrap it to 0 */
+ if (tcp_hdrlen >= 15 * 4)
+ return 0;
+
/*
* MSS Option not found ?! add it..
*/
rcu_read_lock();
indev = __in6_dev_get(skb->dev);
- if (indev)
+ if (indev) {
+ read_lock_bh(&indev->lock);
list_for_each_entry(ifa, &indev->addr_list, if_list) {
if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
continue;
laddr = &ifa->addr;
break;
}
+ read_unlock_bh(&indev->lock);
+ }
rcu_read_unlock();
return laddr ? laddr : daddr;
}
}
#ifdef CONFIG_NET_SCHED
- if (dev->qdisc)
+ if (dev->qdisc != &noop_qdisc)
qdisc_hash_add(dev->qdisc, false);
#endif
}
if (sock->state != SS_UNCONNECTED)
goto out;
+ if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+ goto out;
+
/* If backlog is zero, disable listening. */
if (!backlog) {
if (sctp_sstate(sk, CLOSED))
if (stx->stx_mask & STATX_BTIME)
print_time(" Birth: ", &stx->stx_btime);
- if (stx->stx_attributes) {
- unsigned char bits;
+ if (stx->stx_attributes_mask) {
+ unsigned char bits, mbits;
int loop, byte;
static char attr_representation[64 + 1] =
printf("Attributes: %016llx (", stx->stx_attributes);
for (byte = 64 - 8; byte >= 0; byte -= 8) {
bits = stx->stx_attributes >> byte;
+ mbits = stx->stx_attributes_mask >> byte;
for (loop = 7; loop >= 0; loop--) {
int bit = byte + loop;
- if (bits & 0x80)
+ if (!(mbits & 0x80))
+ putchar('.'); /* Not supported */
+ else if (bits & 0x80)
putchar(attr_representation[63 - bit]);
else
- putchar('-');
+ putchar('-'); /* Not set */
bits <<= 1;
+ mbits <<= 1;
}
if (byte)
putchar(' ');
.name = "powerpc",
.init = powerpc__annotate_init,
},
+ {
+ .name = "s390",
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
};
static void ins__delete(struct ins_operands *ops)
*/
case 0x2C: /* Westmere EP - Gulftown */
cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
+ break;
case 0x2A: /* SNB */
case 0x2D: /* SNB Xeon */
case 0x3A: /* IVB */
\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters.
\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
\fBPkgWatt\fP Watts consumed by the whole package.
\fBCorWatt\fP Watts consumed by the core part of the package.
* it is possible for mperf's non-halted cycles + idle states
* to exceed TSC's all cycles: show c1 = 0% in that case.
*/
- if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc)
+ if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak))
old->c1 = 0;
else {
/* normal case, derive c1 */
if (fp == NULL)
fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
- else
+ else {
rewind(fp);
+ fflush(fp);
+ }
retval = fscanf(fp, "%d", &gfx_cur_mhz);
if (retval != 1)
return 0;
fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
- "(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+ "(high %d guar %d eff %d low %d)\n",
cpu, msr,
(unsigned int)HWP_HIGHEST_PERF(msr),
(unsigned int)HWP_GUARANTEED_PERF(msr),
return 0;
fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
- "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+ "(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n",
cpu, msr,
(unsigned int)(((msr) >> 0) & 0xff),
(unsigned int)(((msr) >> 8) & 0xff),
return 0;
fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
- "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+ "(min %d max %d des %d epp 0x%x window 0x%x)\n",
cpu, msr,
(unsigned int)(((msr) >> 0) & 0xff),
(unsigned int)(((msr) >> 8) & 0xff),
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
- do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
BIC_PRESENT(BIC_PKG__);
BIC_PRESENT(BIC_RAM__);
if (rapl_joules) {
BIC_PRESENT(BIC_Pkg_J);
BIC_PRESENT(BIC_Cor_J);
BIC_PRESENT(BIC_RAM_J);
+ BIC_PRESENT(BIC_GFX_J);
} else {
BIC_PRESENT(BIC_PkgWatt);
BIC_PRESENT(BIC_CorWatt);
BIC_PRESENT(BIC_RAMWatt);
+ BIC_PRESENT(BIC_GFXWatt);
}
break;
case INTEL_FAM6_HASWELL_X: /* HSX */
int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
unsigned long long msr;
- unsigned int dts;
+ unsigned int dts, dts2;
int cpu;
if (!(do_dts || do_ptm))
fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
cpu, msr, tcc_activation_temp - dts);
-#ifdef THERM_DEBUG
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
return 0;
dts2 = (msr >> 8) & 0x7F;
fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
}
- if (do_dts) {
+ if (do_dts && debug) {
unsigned int resolution;
if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
cpu, msr, tcc_activation_temp - dts, resolution);
-#ifdef THERM_DEBUG
if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
return 0;
dts2 = (msr >> 8) & 0x7F;
fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
}
return 0;
}
void print_version() {
- fprintf(outf, "turbostat version 17.02.24"
+ fprintf(outf, "turbostat version 17.04.12"
" - Len Brown <lenb@kernel.org>\n");
}
all: $(SUB_DIRS)
$(SUB_DIRS):
- BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
+ BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
include ../lib.mk
override define RUN_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
done;
endef
override define INSTALL_RULE
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
done;
endef
override define EMIT_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
done;
endef
clean:
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
done;
rm -f tags
}
/**
+ * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
+ *
+ * For a specific CPU, initialize the GIC VE hardware.
+ */
+void kvm_vgic_init_cpu_hardware(void)
+{
+ BUG_ON(preemptible());
+
+ /*
+ * We want to make sure the list registers start out clear so that we
+ * only have the program the used registers.
+ */
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_init_lrs();
+ else
+ kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
+/**
* kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
* according to the host GIC model. Accordingly calls either
* vgic_v2/v3_probe which registers the KVM_DEVICE that can be
val = vmcr.ctlr;
break;
case GIC_CPU_PRIMASK:
- val = vmcr.pmr;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >>
+ GICV_PMR_PRIORITY_SHIFT;
break;
case GIC_CPU_BINPOINT:
val = vmcr.bpr;
vmcr.ctlr = val;
break;
case GIC_CPU_PRIMASK:
- vmcr.pmr = val;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) &
+ GICV_PMR_PRIORITY_MASK;
break;
case GIC_CPU_BINPOINT:
vmcr.bpr = val;
return (unsigned long *)val;
}
+static inline void vgic_v2_write_lr(int lr, u32 val)
+{
+ void __iomem *base = kvm_vgic_global_state.vctrl_base;
+
+ writel_relaxed(val, base + GICH_LR0 + (lr * 4));
+}
+
+void vgic_v2_init_lrs(void)
+{
+ int i;
+
+ for (i = 0; i < kvm_vgic_global_state.nr_lr; i++)
+ vgic_v2_write_lr(i, 0);
+}
+
void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
GICH_VMCR_ALIAS_BINPOINT_MASK;
vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
GICH_VMCR_BINPOINT_MASK;
- vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
- GICH_VMCR_PRIMASK_MASK;
+ vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) <<
+ GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
}
GICH_VMCR_ALIAS_BINPOINT_SHIFT;
vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
GICH_VMCR_BINPOINT_SHIFT;
- vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >>
- GICH_VMCR_PRIMASK_SHIFT;
+ vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >>
+ GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT;
}
void vgic_v2_enable(struct kvm_vcpu *vcpu)
return irq->pending_latch || irq->line_level;
}
+/*
+ * This struct provides an intermediate representation of the fields contained
+ * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
+ * state to userspace can generate either GICv2 or GICv3 CPU interface
+ * registers regardless of the hardware backed GIC used.
+ */
struct vgic_vmcr {
u32 ctlr;
u32 abpr;
u32 bpr;
- u32 pmr;
+ u32 pmr; /* Priority mask field in the GICC_PMR and
+ * ICC_PMR_EL1 priority field format */
/* Below member variable are valid only for GICv3 */
u32 grpen0;
u32 grpen1;
int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
enum vgic_type);
+void vgic_v2_init_lrs(void);
+
static inline void vgic_get_irq_kref(struct vgic_irq *irq)
{
if (irq->intid < VGIC_MIN_LPI)