search for: kmem_cach

...bject) +{ + struct extent_buffer *eb = object; + + printk(KERN_ERR "btrfs buffer leak start %llu len %lu " + "refs %d\n", (unsigned long long)eb->start, + eb->len, atomic_read(&eb->refs)); +} + int __init extent_io_init(void) { extent_state_cache = kmem_cache_create("btrfs_extent_state", @@ -115,9 +135,11 @@ void extent_io_exit(void) */ rcu_barrier(); if (extent_state_cache) - kmem_cache_destroy(extent_state_cache); + kmem_cache_destroy_decoder(extent_state_cache, + extent_state_leak_decoder); if (extent_buffer_cache) - kme...

Just use kmem_cache instead of rolling our own, limited implementation. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 4 +-- drivers/gpu/drm/virtio/virtgpu_vq.c | 57 +++++++----------------------------- 2 files changed, 11 insertions(+), 50 deletions(-) dif...

Just use kmem_cache instead of rolling our own, limited implementation. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 4 +-- drivers/gpu/drm/virtio/virtgpu_vq.c | 57 +++++++----------------------------- 2 files changed, 11 insertions(+), 50 deletions(-) dif...

On Sun, 12 May 2019, Halil Pasic wrote: > I've also got code that deals with AIRQ_IV_CACHELINE by turning the > kmem_cache into a dma_pool. > > Cornelia, Sebastian which approach do you prefer: > 1) get rid of cio_dma_pool and AIRQ_IV_CACHELINE, and waste a page per > vector, or > 2) go with the approach taken by the patch below? We only have a couple of users for airq_iv: virtio_ccw.c: 2K bits pci...

On Sun, 12 May 2019, Halil Pasic wrote: > I've also got code that deals with AIRQ_IV_CACHELINE by turning the > kmem_cache into a dma_pool. > > Cornelia, Sebastian which approach do you prefer: > 1) get rid of cio_dma_pool and AIRQ_IV_CACHELINE, and waste a page per > vector, or > 2) go with the approach taken by the patch below? We only have a couple of users for airq_iv: virtio_ccw.c: 2K bits pci...

This adds a leak decoder callback so that kmem_cache_destroy() can use to generate debugging output for the allocated objects. Callers like btrfs are using their own leak tracking which will manage allocated objects in a list(or something else), this does indeed the same thing as what slab does. So adding a callback for leak tracking can avoid thi...

On Thu, 16 May 2019 15:59:22 +0200 (CEST) Sebastian Ott <sebott at linux.ibm.com> wrote: > On Sun, 12 May 2019, Halil Pasic wrote: > > I've also got code that deals with AIRQ_IV_CACHELINE by turning the > > kmem_cache into a dma_pool. > > > > Cornelia, Sebastian which approach do you prefer: > > 1) get rid of cio_dma_pool and AIRQ_IV_CACHELINE, and waste a page per > > vector, or > > 2) go with the approach taken by the patch below? > > We only have a couple of users for ai...

...00 Halil Pasic <pasic at linux.ibm.com> wrote: > Protected virtualization guests have to use shared pages for airq > notifier bit vectors, because hypervisor needs to write these bits. > > Let us make sure we allocate DMA memory for the notifier bit vectors by > replacing the kmem_cache with a dma_cache and kalloc() with > cio_dma_zalloc(). > > Signed-off-by: Halil Pasic <pasic at linux.ibm.com> > Reviewed-by: Sebastian Ott <sebott at linux.ibm.com> > --- > arch/s390/include/asm/airq.h | 2 ++ > drivers/s390/cio/airq.c | 32 +++++++++++++++...

...00 Halil Pasic <pasic at linux.ibm.com> wrote: > Protected virtualization guests have to use shared pages for airq > notifier bit vectors, because hypervisor needs to write these bits. > > Let us make sure we allocate DMA memory for the notifier bit vectors by > replacing the kmem_cache with a dma_cache and kalloc() with > cio_dma_zalloc(). > > Signed-off-by: Halil Pasic <pasic at linux.ibm.com> > Reviewed-by: Sebastian Ott <sebott at linux.ibm.com> > --- > arch/s390/include/asm/airq.h | 2 ++ > drivers/s390/cio/airq.c | 32 +++++++++++++++...

...change on top of the current implementation. I'm good with doing that and looking for further simplification/unification later. > Commit 414cbd1e3d14 "s390/airq: provide cacheline aligned > ivs" (Sebastian Ott, 2019-02-27) could have been smaller had you implemented > 'kmem_cache for everything' (and I would have had just to replace kmem_cache with > dma_cache to achieve option 3). For some reason you decided to keep the > iv->vector = kzalloc(size, GFP_KERNEL) code-path and make the client code request > iv->vector = kmem_cache_zalloc(airq_iv_cache, GFP...

...o_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -13,6 +13,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/mempool.h> @@ -771,8 +773,7 @@ static int __init init(void) virtscsi_cmd_cache = KMEM_CACHE(virtio_scsi_cmd, 0); if (!virtscsi_cmd_cache) { - printk(KERN_ERR "kmem_cache_create() for " - "virtscsi_cmd_cache failed\n"); + pr_err("kmem_cache_create() for virtscsi_cmd_cache failed\n"); goto error; } @@ -781,8 +782,7 @@ static int __init init(void)...

...o_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -13,6 +13,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/mempool.h> @@ -771,8 +773,7 @@ static int __init init(void) virtscsi_cmd_cache = KMEM_CACHE(virtio_scsi_cmd, 0); if (!virtscsi_cmd_cache) { - printk(KERN_ERR "kmem_cache_create() for " - "virtscsi_cmd_cache failed\n"); + pr_err("kmem_cache_create() for virtscsi_cmd_cache failed\n"); goto error; } @@ -781,8 +782,7 @@ static int __init init(void)...

On Wed, 2014-01-08 at 21:18 +0200, Michael S. Tsirkin wrote: > On Wed, Jan 08, 2014 at 10:26:03AM -0800, Eric Dumazet wrote: > > On Wed, 2014-01-08 at 20:08 +0200, Michael S. Tsirkin wrote: > > > > > Eric said we also need a patch to add __GFP_NORETRY, right? > > > Probably before this one in series. > > > > Nope, this __GFP_NORETRY has nothing to do

On Wed, 2014-01-08 at 21:18 +0200, Michael S. Tsirkin wrote: > On Wed, Jan 08, 2014 at 10:26:03AM -0800, Eric Dumazet wrote: > > On Wed, 2014-01-08 at 20:08 +0200, Michael S. Tsirkin wrote: > > > > > Eric said we also need a patch to add __GFP_NORETRY, right? > > > Probably before this one in series. > > > > Nope, this __GFP_NORETRY has nothing to do

...nux.ibm.com> wrote: > > > Protected virtualization guests have to use shared pages for airq > > notifier bit vectors, because hypervisor needs to write these bits. > > > > Let us make sure we allocate DMA memory for the notifier bit vectors by > > replacing the kmem_cache with a dma_cache and kalloc() with > > cio_dma_zalloc(). > > > > Signed-off-by: Halil Pasic <pasic at linux.ibm.com> > > Reviewed-by: Sebastian Ott <sebott at linux.ibm.com> > > --- > > arch/s390/include/asm/airq.h | 2 ++ > > drivers/s390/c...

> Bug ID: 6398177 > Synopsis: zfs: poor nightly build performance in 32-bit mode (high disk activity) Part of the problem appear to be these kmem_caches: # mdb -k ... > ::kmastat cache buf buf buf memory alloc alloc name size in use total in use succeed fail ------------------------- ------ ------ ------ --------- --------- ----- ... dmu_buf_impl_t 192 2029 1043...

...job_lock; }; struct kvm_introspection { diff --git a/virt/kvm/introspection/kvmi.c b/virt/kvm/introspection/kvmi.c index 655170ffb574..5149f8e06131 100644 --- a/virt/kvm/introspection/kvmi.c +++ b/virt/kvm/introspection/kvmi.c @@ -10,6 +10,7 @@ #include <linux/kthread.h> static struct kmem_cache *msg_cache; +static struct kmem_cache *job_cache; void *kvmi_msg_alloc(void) { @@ -33,14 +34,19 @@ static void kvmi_cache_destroy(void) { kmem_cache_destroy(msg_cache); msg_cache = NULL; + kmem_cache_destroy(job_cache); + job_cache = NULL; } static int kvmi_cache_create(void) { msg...

...> > > Protected virtualization guests have to use shared pages for airq > > > notifier bit vectors, because hypervisor needs to write these bits. > > > > > > Let us make sure we allocate DMA memory for the notifier bit vectors by > > > replacing the kmem_cache with a dma_cache and kalloc() with > > > cio_dma_zalloc(). > > > > > > Signed-off-by: Halil Pasic <pasic at linux.ibm.com> > > > Reviewed-by: Sebastian Ott <sebott at linux.ibm.com> > > > --- > > > arch/s390/include/asm/airq.h |...

...> > > Protected virtualization guests have to use shared pages for airq > > > notifier bit vectors, because hypervisor needs to write these bits. > > > > > > Let us make sure we allocate DMA memory for the notifier bit vectors by > > > replacing the kmem_cache with a dma_cache and kalloc() with > > > cio_dma_zalloc(). > > > > > > Signed-off-by: Halil Pasic <pasic at linux.ibm.com> > > > Reviewed-by: Sebastian Ott <sebott at linux.ibm.com> > > > --- > > > arch/s390/include/asm/airq.h |...

From: Halil Pasic <pasic at linux.ibm.com> Protected virtualization guests have to use shared pages for airq notifier bit vectors, because hypervisor needs to write these bits. Let us make sure we allocate DMA memory for the notifier bit vectors by replacing the kmem_cache with a dma_cache and kalloc() with cio_dma_zalloc(). Signed-off-by: Halil Pasic <pasic at linux.ibm.com> --- arch/s390/include/asm/airq.h | 2 ++ drivers/s390/cio/airq.c | 32 ++++++++++++++++++++------------ drivers/s390/cio/cio.h | 2 ++ drivers/s390/cio/css.c | 1 +...