On Wed Sep 4, 2024 at 4:39 AM EEST, Aaron Lu wrote:
> On Tue, Sep 03, 2024 at 07:05:40PM +0300, Jarkko Sakkinen wrote:
> > On Fri Aug 30, 2024 at 9:14 AM EEST, Aaron Lu wrote:
> > > On Thu, Aug 29, 2024 at 07:44:13PM +0300, Jarkko Sakkinen wrote:
> > > > On Thu Aug 29, 2024 at 5:38 AM EEST, Aaron L
On Tue, Sep 03, 2024 at 07:05:40PM +0300, Jarkko Sakkinen wrote:
> On Fri Aug 30, 2024 at 9:14 AM EEST, Aaron Lu wrote:
> > On Thu, Aug 29, 2024 at 07:44:13PM +0300, Jarkko Sakkinen wrote:
> > > On Thu Aug 29, 2024 at 5:38 AM EEST, Aaron Lu wrote:
> > > > When current node doesn't have a EPC sectio
On Fri Aug 30, 2024 at 9:14 AM EEST, Aaron Lu wrote:
> On Thu, Aug 29, 2024 at 07:44:13PM +0300, Jarkko Sakkinen wrote:
> > On Thu Aug 29, 2024 at 5:38 AM EEST, Aaron Lu wrote:
> > > When current node doesn't have a EPC section configured by firmware and
> > > all other EPC sections memory are used
On Fri, Aug 30, 2024 at 07:03:33AM -0700, Dave Hansen wrote:
> On 8/29/24 23:02, Aaron Lu wrote:
> >> Also, I do think we should probably add some kind of sanity warning to
> >> the SGX code in another patch. If a node on an SGX system has CPUs and
> >> memory, it's very likely it will also have s
On 8/29/24 23:02, Aaron Lu wrote:
>> Also, I do think we should probably add some kind of sanity warning to
>> the SGX code in another patch. If a node on an SGX system has CPUs and
>> memory, it's very likely it will also have some EPC. It can be
>> something soft like a pr_info(), but I think i
On Thu, Aug 29, 2024 at 07:44:13PM +0300, Jarkko Sakkinen wrote:
> On Thu Aug 29, 2024 at 5:38 AM EEST, Aaron Lu wrote:
> > When current node doesn't have a EPC section configured by firmware and
> > all other EPC sections memory are used up, CPU can stuck inside the
> > while loop in __sgx_alloc_e
On Thu, Aug 29, 2024 at 08:17:53AM -0700, Dave Hansen wrote:
> Generally, I think it's a bad idea to refer to function names in
> subjects. This, for instance would be much more informative:
>
> x86/sgx: Fix deadlock in SGX NUMA node search
Indeed, will use this as subject, thanks.
> On 8
On Thu Aug 29, 2024 at 5:38 AM EEST, Aaron Lu wrote:
> When current node doesn't have a EPC section configured by firmware and
> all other EPC sections memory are used up, CPU can stuck inside the
> while loop in __sgx_alloc_epc_page() forever and soft lockup will happen.
> Note how nid_of_current
Generally, I think it's a bad idea to refer to function names in
subjects. This, for instance would be much more informative:
x86/sgx: Fix deadlock in SGX NUMA node search
On 8/28/24 19:38, Aaron Lu wrote:
> When current node doesn't have a EPC section configured by firmware and
> all ot
On Thu, Aug 29, 2024 at 03:56:39PM +0800, Huang, Kai wrote:
> Actually run spell check this time ...
>
> On Thu, 2024-08-29 at 10:38 +0800, Aaron Lu wrote:
> > When current node doesn't have a EPC section configured by firmware and
>
> "current node" -> "the current node"
>
> "a EPC section" ->
Actually run spell check this time ...
On Thu, 2024-08-29 at 10:38 +0800, Aaron Lu wrote:
> When current node doesn't have a EPC section configured by firmware and
"current node" -> "the current node"
"a EPC section" -> "an EPC section"
> all other EPC sections memory are used up, CPU can stuck
On Thu, 2024-08-29 at 10:38 +0800, Aaron Lu wrote:
> When current node doesn't have a EPC section configured by firmware and
> all other EPC sections memory are used up, CPU can stuck inside the
> while loop in __sgx_alloc_epc_page() forever and soft lockup will happen.
> Note how nid_of_current wi
When current node doesn't have a EPC section configured by firmware and
all other EPC sections memory are used up, CPU can stuck inside the
while loop in __sgx_alloc_epc_page() forever and soft lockup will happen.
Note how nid_of_current will never equal to nid in that while loop because
nid_of_cur
13 matches
Mail list logo
