Re: [PATCH] powerpc: Fix system calls on Cell entered with XER.SO=1

2008-11-30 Thread Benjamin Herrenschmidt
On Mon, 2008-12-01 at 08:49 +1100, Paul Mackerras wrote: > It turns out that on Cell, on a kernel with CONFIG_VIRT_CPU_ACCOUNTING > = y, if a program sets the SO (summary overflow) bit in the XER and > then does a system call, the SO bit in CR0 will be set on return > regardless of whether the syst

[PATCH] powerpc: Fix system calls on Cell entered with XER.SO=1

2008-11-30 Thread Paul Mackerras
It turns out that on Cell, on a kernel with CONFIG_VIRT_CPU_ACCOUNTING = y, if a program sets the SO (summary overflow) bit in the XER and then does a system call, the SO bit in CR0 will be set on return regardless of whether the system call detected an error. Since CR0.SO is used as the error ind

Re: [PATCH] powerpc: Fix system calls on Cell entered with XER.SO=1

2008-11-26 Thread Arnd Bergmann
On Wednesday 26 November 2008, Paul Mackerras wrote: > This fixes it by moving the clearing of CR0.SO to after the > ACCOUNT_CPU_USER_ENTRY call in the system call entry path. Thanks for taking care of this! > Signed-off-by: Paul Mackerras <[EMAIL PROTECTED]> Acked-by: Arnd Bergmann <[EMAIL PROT

[PATCH] powerpc: Fix system calls on Cell entered with XER.SO=1

2008-11-25 Thread Paul Mackerras
It turns out that on Cell, on a kernel with CONFIG_VIRT_CPU_ACCOUNTING = y, if a program sets the SO (summary overflow) bit in the XER and then does a system call, the SO bit in CR0 will be set on return regardless of whether the system call detected an error. Since CR0.SO is used as the error ind