[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper
From: |
Blue Swirl |
Subject: |
Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty. |
Date: |
Tue, 16 Mar 2010 22:10:44 +0200 |
On 3/16/10, Anthony Liguori <address@hidden> wrote:
> On 03/16/2010 08:57 AM, Avi Kivity wrote:
>
> > On 03/16/2010 03:51 PM, Anthony Liguori wrote:
> >
> > > On 03/16/2010 08:29 AM, Avi Kivity wrote:
> > >
> > > > On 03/16/2010 03:17 PM, Yoshiaki Tamura wrote:
> > > >
> > > > > Avi Kivity wrote:
> > > > >
> > > > > > On 03/16/2010 12:53 PM, Yoshiaki Tamura wrote:
> > > > > >
> > > > > > > Modifies wrapper functions for byte-based phys_ram_dirty bitmap
> to
> > > > > > > bit-based phys_ram_dirty bitmap, and adds more wrapper functions
> to
> > > > > > > prevent
> > > > > > > direct access to the phys_ram_dirty bitmap.
> > > > > > >
> > > > > >
> > > > > >
> > > > > > > +
> > > > > > > +static inline int
> cpu_physical_memory_get_dirty_flags(ram_addr_t addr)
> > > > > > > +{
> > > > > > > + unsigned long mask;
> > > > > > > + int index = (addr>> TARGET_PAGE_BITS) / HOST_LONG_BITS;
> > > > > > > + int offset = (addr>> TARGET_PAGE_BITS)& (HOST_LONG_BITS - 1);
> > > > > > > + int ret = 0;
> > > > > > > +
> > > > > > > + mask = 1UL<< offset;
> > > > > > > + if (phys_ram_vga_dirty[index]& mask)
> > > > > > > + ret |= VGA_DIRTY_FLAG;
> > > > > > > + if (phys_ram_code_dirty[index]& mask)
> > > > > > > + ret |= CODE_DIRTY_FLAG;
> > > > > > > + if (phys_ram_migration_dirty[index]& mask)
> > > > > > > + ret |= MIGRATION_DIRTY_FLAG;
> > > > > > > +
> > > > > > > + return ret;
> > > > > > > }
> > > > > > >
> > > > > > > static inline int
> cpu_physical_memory_get_dirty(ram_addr_t addr,
> > > > > > > int dirty_flags)
> > > > > > > {
> > > > > > > - return phys_ram_dirty[addr>> TARGET_PAGE_BITS]& dirty_flags;
> > > > > > > + return
> cpu_physical_memory_get_dirty_flags(addr)& dirty_flags;
> > > > > > > }
> > > > > > >
> > > > > >
> > > > > > This turns one cacheline access into three. If the dirty bitmaps
> were in
> > > > > > an array, you could do
> > > > > >
> > > > > > return dirty_bitmaps[dirty_index][addr >>
> (TARGET_PAGE_BITS +
> > > > > > BITS_IN_LONG)] & mask;
> > > > > >
> > > > > > with one cacheline access.
> > > > > >
> > > > >
> > > > > If I'm understanding the existing code correctly,
> > > > > int dirty_flags can be combined, like VGA + MIGRATION.
> > > > > If we only have to worry about a single dirty flag, I agree with
> your idea.
> > > > >
> > > >
> > > > From a quick grep it seems flags are not combined, except for
> something strange with CODE_DIRTY_FLAG:
> > > >
> > > >
> > > > > static void notdirty_mem_writel(void *opaque,
> target_phys_addr_t ram_addr,
> > > > > uint32_t val)
> > > > > {
> > > > > int dirty_flags;
> > > > > dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
> > > > > if (!(dirty_flags & CODE_DIRTY_FLAG)) {
> > > > > #if !defined(CONFIG_USER_ONLY)
> > > > > tb_invalidate_phys_page_fast(ram_addr, 4);
> > > > > dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
> > > > > #endif
> > > > > }
> > > > > stl_p(qemu_get_ram_ptr(ram_addr), val);
> > > > > dirty_flags |= (0xff & ~CODE_DIRTY_FLAG);
> > > > > phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS] = dirty_flags;
> > > > > /* we remove the notdirty callback only if the code has been
> > > > > flushed */
> > > > > if (dirty_flags == 0xff)
> > > > > tlb_set_dirty(cpu_single_env, cpu_single_env->mem_io_vaddr);
> > > > > }
> > > > >
> > > >
> > > > I can't say I understand what it does.
> > > >
> > >
> > > The semantics of CODE_DIRTY_FLAG are a little counter intuitive.
> CODE_DIRTY_FLAG means that we know that something isn't code so writes do
> not need checking for self modifying code.
> > >
> >
> > So the hardware equivalent is, when the Instruction TLB loads a page
> address, clear CODE_DIRTY_FLAG?
> >
>
> Yes, and is what tlb_protect_code() does and it's called from
> tb_alloc_page() which is what's code when a TB is created.
Just a tangential note: a long time ago, I tried to disable self
modifying code detection for Sparc. On most RISC architectures, SMC
needs explicit flushing so in theory we need not track code memory
writes. However, during exceptions the translator needs to access the
original unmodified code that was used to generate the TB. But maybe
there are other ways to avoid SMC tracking, on x86 it's still needed
but I suppose SMC is pretty rare.
- [Qemu-devel] [PATCH 5/6] qemu-kvm: Use cpu_physical_memory_set_dirty_range() to update phys_ram_dirty., (continued)
- [Qemu-devel] [PATCH 5/6] qemu-kvm: Use cpu_physical_memory_set_dirty_range() to update phys_ram_dirty., Yoshiaki Tamura, 2010/03/16
- [Qemu-devel] [PATCH 6/6] qemu-kvm: Use cpu_physical_memory_get_dirty_range() to check multiple dirty pages., Yoshiaki Tamura, 2010/03/16
- [Qemu-devel] [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Yoshiaki Tamura, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Avi Kivity, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Yoshiaki Tamura, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Avi Kivity, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Yoshiaki Tamura, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Anthony Liguori, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Avi Kivity, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Anthony Liguori, 2010/03/16
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty.,
Blue Swirl <=
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Richard Henderson, 2010/03/16
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Paul Brook, 2010/03/16
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Avi Kivity, 2010/03/17
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Paul Brook, 2010/03/17
- Re: [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Avi Kivity, 2010/03/17
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Anthony Liguori, 2010/03/16
- [Qemu-devel] Re: [PATCH 2/6] qemu-kvm: Modify and introduce wrapper functions to access phys_ram_dirty., Yoshiaki Tamura, 2010/03/16
[Qemu-devel] [PATCH 3/6] qemu-kvm: Replace direct phys_ram_dirty access with wrapper functions., Yoshiaki Tamura, 2010/03/16
[Qemu-devel] [PATCH 4/6] qemu-kvm: Introduce cpu_physical_memory_get_dirty_range()., Yoshiaki Tamura, 2010/03/16