Commit 5a3ae276 authored by Suresh Siddha's avatar Suresh Siddha Committed by Linus Torvalds
Browse files

x86, PAT: Remove duplicate memtype reserve in pci mmap 

pci mmap code was doing memtype reserve for a while now. Recently we
added memtype tracking in remap_pfn_range, and pci code indirectly calls
remap_pfn_range. So, we don't need seperate tracking in pci code
anymore. Which means a patch that removes ~50 lines of code :-).

Also, recently we found out that the pci tracking is not working as we expect
it to work in some cases. Specifically, userlevel X mmap of pci, with some
recent version of X, is having a problem with vm_page_prot getting reset.
The pci tracking uses vm_page_prot to pass on the protection type from parent
to child during fork.
a) Parent does a pci mmap
b) We look at PAT and get either UC_MINUS or WC mapping for parent
c) Store that mapping type in vma vm_page_prot for future use
d) This thread does a fork
e) Fork results in mmap_ops ->open for the child process
f) We get the vm_page_prot from vma and reserve that type for the child process

But, between c) and e) above, the vma vm_page_prot is getting reset to zero.
This results in PAT reserve failing at the time of fork as in here.
http://marc.info/?l=linux-kernel&m=123858163103240&w=2



This cleanup makes the above problem go away as we do not depend on
vm_page_prot in our PAT code anymore.

Signed-off-by: default avatarSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: default avatarVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 78609a81

arch/x86/pci/i386.c

+0 −46
Original line number Diff line number Diff line
@@ -258,24 +258,7 @@ void pcibios_set_master(struct pci_dev *dev) 
	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);

}



static void pci_unmap_page_range(struct vm_area_struct *vma)

{

	u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT;

	free_memtype(addr, addr + vma->vm_end - vma->vm_start);

}



static void pci_track_mmap_page_range(struct vm_area_struct *vma)

{

	u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT;

	unsigned long flags = pgprot_val(vma->vm_page_prot)

						& _PAGE_CACHE_MASK;



	reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL);

}



static struct vm_operations_struct pci_mmap_ops = {

	.open  = pci_track_mmap_page_range,

	.close = pci_unmap_page_range,

	.access = generic_access_phys,

};
@@ -283,11 +266,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, 
			enum pci_mmap_state mmap_state, int write_combine)

{

	unsigned long prot;

	u64 addr = vma->vm_pgoff << PAGE_SHIFT;

	unsigned long len = vma->vm_end - vma->vm_start;

	unsigned long flags;

	unsigned long new_flags;

	int retval;



	/* I/O space cannot be accessed via normal processor loads and

	 * stores on this platform.
@@ -308,30 +286,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, 


	vma->vm_page_prot = __pgprot(prot);



	flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK;

	retval = reserve_memtype(addr, addr + len, flags, &new_flags);

	if (retval)

		return retval;



	if (flags != new_flags) {

		if (!is_new_memtype_allowed(flags, new_flags)) {

			free_memtype(addr, addr+len);

			return -EINVAL;

		}

		flags = new_flags;

		vma->vm_page_prot = __pgprot(

			(pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK) |

			flags);

	}



	if (((vma->vm_pgoff < max_low_pfn_mapped) ||

	     (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) &&

	      vma->vm_pgoff < max_pfn_mapped)) &&

	    ioremap_change_attr((unsigned long)__va(addr), len, flags)) {

		free_memtype(addr, addr + len);

		return -EINVAL;

	}



	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,

			       vma->vm_end - vma->vm_start,

			       vma->vm_page_prot))

CRA Git | Maintained and supported by SUSTech CRA and CCSE