From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: qemu-devel@nongnu.org, qemu-ppc@nongnu.org
Subject: Re: [Qemu-devel] [PATCH qemu] target-ppc: kvm: make use of KVM_CREATE_SPAPR_TCE_64
Date: Thu, 2 Mar 2017 13:40:04 +1100 [thread overview]
Message-ID: <a0251003-e14c-9a74-33e6-ec30bb868559@ozlabs.ru> (raw)
In-Reply-To: <20170109025349.GF12515@umbus.fritz.box>
[-- Attachment #1: Type: text/plain, Size: 8592 bytes --]
On 09/01/17 13:53, David Gibson wrote:
> On Mon, Jan 09, 2017 at 01:38:26PM +1100, Alexey Kardashevskiy wrote:
>> On 03/01/17 13:26, David Gibson wrote:
>>> On Thu, Dec 22, 2016 at 12:13:12PM +1100, Alexey Kardashevskiy wrote:
>>>> KVM_CAP_SPAPR_TCE capability allows creating TCE tables in KVM which
>>>> allows having in-kernel acceleration for H_PUT_TCE_xxx hypercalls.
>>>> However it only supports 32bit DMA windows at zero bus offset.
>>>>
>>>> There is a new KVM_CAP_SPAPR_TCE_64 capability which supports 64bit
>>>> window size, variable page size and bus offset.
>>>>
>>>> This makes use of the new capability. The kernel headers are already
>>>> updated as the kernel support went in to v4.6.
>>>>
>>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
>>>> ---
>>>> target-ppc/kvm_ppc.h | 12 +++++++-----
>>>> hw/ppc/spapr_iommu.c | 8 +++++---
>>>> target-ppc/kvm.c | 48 +++++++++++++++++++++++++++++++++++++-----------
>>>> 3 files changed, 49 insertions(+), 19 deletions(-)
>>>>
>>>> diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
>>>> index bd1d78bfbe..14320c2378 100644
>>>> --- a/target-ppc/kvm_ppc.h
>>>> +++ b/target-ppc/kvm_ppc.h
>>>> @@ -36,8 +36,9 @@ int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu);
>>>> #ifndef CONFIG_USER_ONLY
>>>> off_t kvmppc_alloc_rma(void **rma);
>>>> bool kvmppc_spapr_use_multitce(void);
>>>> -void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd,
>>>> - bool need_vfio);
>>>> +void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t page_shift,
>>>> + uint64_t bus_offset, uint32_t nb_table,
>>>> + int *pfd, bool need_vfio);
>>>> int kvmppc_remove_spapr_tce(void *table, int pfd, uint32_t window_size);
>>>> int kvmppc_reset_htab(int shift_hint);
>>>> uint64_t kvmppc_rma_size(uint64_t current_size, unsigned int hash_shift);
>>>> @@ -168,9 +169,10 @@ static inline bool kvmppc_spapr_use_multitce(void)
>>>> return false;
>>>> }
>>>>
>>>> -static inline void *kvmppc_create_spapr_tce(uint32_t liobn,
>>>> - uint32_t window_size, int *fd,
>>>> - bool need_vfio)
>>>> +static inline void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t page_shift,
>>>> + uint64_t bus_offset,
>>>> + uint32_t nb_table,
>>>> + int *pfd, bool need_vfio)
>>>> {
>>>> return NULL;
>>>> }
>>>> diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
>>>> index ae30bbe30f..29c80bb3c8 100644
>>>> --- a/hw/ppc/spapr_iommu.c
>>>> +++ b/hw/ppc/spapr_iommu.c
>>>> @@ -79,15 +79,16 @@ static IOMMUAccessFlags spapr_tce_iommu_access_flags(uint64_t tce)
>>>>
>>>> static uint64_t *spapr_tce_alloc_table(uint32_t liobn,
>>>> uint32_t page_shift,
>>>> + uint64_t bus_offset,
>>>> uint32_t nb_table,
>>>> int *fd,
>>>> bool need_vfio)
>>>> {
>>>> uint64_t *table = NULL;
>>>> - uint64_t window_size = (uint64_t)nb_table << page_shift;
>>>>
>>>> - if (kvm_enabled() && !(window_size >> 32)) {
>>>> - table = kvmppc_create_spapr_tce(liobn, window_size, fd, need_vfio);
>>>> + if (kvm_enabled()) {
>>>
>>> This is broken. Previously, if we had a >4GiB window, we'd fall back
>>> to managing it in userspace, which would work, albeit slowly. Now, if
>>> you have an older kernel which doesn't support KVM_CAP_SPAPR_TCE_64 it
>>> will attempt to allocate it in the kernel, and fail completely.
>>
>>
>> No, kvmppc_create_spapr_tce() would return NULL and right after that there
>> is a "if (!table)" (it can be seen at the end of this chunk) to handle the
>> failure.
>
> Oh, yes, sorry. For some reason I thought there was a return in that
> if block.
This was the only comment which turned out to be not a bug, what now? :)
>
>>>
>>>> + table = kvmppc_create_spapr_tce(liobn, page_shift, bus_offset, nb_table,
>>>> + fd, need_vfio);
>>>> }
>>>>
>>>> if (!table) {
>>>> @@ -342,6 +343,7 @@ void spapr_tce_table_enable(sPAPRTCETable *tcet,
>>>> tcet->nb_table = nb_table;
>>>> tcet->table = spapr_tce_alloc_table(tcet->liobn,
>>>> tcet->page_shift,
>>>> + tcet->bus_offset,
>>>> tcet->nb_table,
>>>> &tcet->fd,
>>>> tcet->need_vfio);
>>>> diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
>>>> index 9c4834c4fc..6e91a4d8bb 100644
>>>> --- a/target-ppc/kvm.c
>>>> +++ b/target-ppc/kvm.c
>>>> @@ -71,6 +71,7 @@ static int cap_booke_sregs;
>>>> static int cap_ppc_smt;
>>>> static int cap_ppc_rma;
>>>> static int cap_spapr_tce;
>>>> +static int cap_spapr_tce_64;
>>>> static int cap_spapr_multitce;
>>>> static int cap_spapr_vfio;
>>>> static int cap_hior;
>>>> @@ -123,6 +124,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>>>> cap_ppc_smt = kvm_check_extension(s, KVM_CAP_PPC_SMT);
>>>> cap_ppc_rma = kvm_check_extension(s, KVM_CAP_PPC_RMA);
>>>> cap_spapr_tce = kvm_check_extension(s, KVM_CAP_SPAPR_TCE);
>>>> + cap_spapr_tce_64 = kvm_check_extension(s, KVM_CAP_SPAPR_TCE_64);
>>>> cap_spapr_multitce = kvm_check_extension(s, KVM_CAP_SPAPR_MULTITCE);
>>>> cap_spapr_vfio = false;
>>>> cap_one_reg = kvm_check_extension(s, KVM_CAP_ONE_REG);
>>>> @@ -2201,13 +2203,10 @@ bool kvmppc_spapr_use_multitce(void)
>>>> return cap_spapr_multitce;
>>>> }
>>>>
>>>> -void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd,
>>>> - bool need_vfio)
>>>> +void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t page_shift,
>>>> + uint64_t bus_offset, uint32_t nb_table,
>>>> + int *pfd, bool need_vfio)
>>>> {
>>>> - struct kvm_create_spapr_tce args = {
>>>> - .liobn = liobn,
>>>> - .window_size = window_size,
>>>> - };
>>>> long len;
>>>> int fd;
>>>> void *table;
>>>> @@ -2220,14 +2219,41 @@ void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd,
>>>> return NULL;
>>>> }
>>>>
>>>> - fd = kvm_vm_ioctl(kvm_state, KVM_CREATE_SPAPR_TCE, &args);
>>>> - if (fd < 0) {
>>>> - fprintf(stderr, "KVM: Failed to create TCE table for liobn 0x%x\n",
>>>> - liobn);
>>>> + if (cap_spapr_tce_64) {
>>>> + struct kvm_create_spapr_tce_64 args = {
>>>> + .liobn = liobn,
>>>> + .page_shift = page_shift,
>>>> + .offset = bus_offset >> page_shift,
>>>> + .size = nb_table,
>>>> + .flags = 0
>>>> + };
>>>> + fd = kvm_vm_ioctl(kvm_state, KVM_CREATE_SPAPR_TCE_64, &args);
>>>> + if (fd < 0) {
>>>> + fprintf(stderr,
>>>> + "KVM: Failed to create TCE64 table for liobn 0x%x\n",
>>>> + liobn);
>>>> + return NULL;
>>>> + }
>>>> + } else if (cap_spapr_tce) {
>>>> + uint64_t window_size = (uint64_t) nb_table << page_shift;
>>>> + struct kvm_create_spapr_tce args = {
>>>> + .liobn = liobn,
>>>> + .window_size = window_size,
>>>> + };
>>>> + if ((window_size != args.window_size) || bus_offset) {
>>>> + return NULL;
>>>> + }
>>>> + fd = kvm_vm_ioctl(kvm_state, KVM_CREATE_SPAPR_TCE, &args);
>>>> + if (fd < 0) {
>>>> + fprintf(stderr, "KVM: Failed to create TCE table for liobn 0x%x\n",
>>>> + liobn);
>>>> + return NULL;
>>>> + }
>>>> + } else {
>>>> return NULL;
>>>> }
>>>>
>>>> - len = (window_size / SPAPR_TCE_PAGE_SIZE) * sizeof(uint64_t);
>>>> + len = nb_table * sizeof(uint64_t);
>>>> /* FIXME: round this up to page size */
>>>>
>>>> table = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
>>>
>>
>>
>
>
>
>
--
Alexey
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 839 bytes --]
next prev parent reply other threads:[~2017-03-02 2:40 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-22 1:13 [Qemu-devel] [PATCH qemu] target-ppc: kvm: make use of KVM_CREATE_SPAPR_TCE_64 Alexey Kardashevskiy
2017-01-03 2:26 ` David Gibson
2017-01-09 2:38 ` Alexey Kardashevskiy
2017-01-09 2:53 ` David Gibson
2017-03-02 2:40 ` Alexey Kardashevskiy [this message]
2017-03-08 4:48 ` Alexey Kardashevskiy
2017-03-10 0:32 ` David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=a0251003-e14c-9a74-33e6-ec30bb868559@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=david@gibson.dropbear.id.au \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).