linux/arch/x86/include/asm/xen/page.h

232 lines
6.5 KiB
C
Raw Normal View History

#ifndef _ASM_X86_XEN_PAGE_H
#define _ASM_X86_XEN_PAGE_H
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/pfn.h>
#include <linux/mm.h>
#include <asm/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <xen/interface/xen.h>
#include <xen/grant_table.h>
#include <xen/features.h>
/* Xen machine address */
typedef struct xmaddr {
phys_addr_t maddr;
} xmaddr_t;
/* Xen pseudo-physical address */
typedef struct xpaddr {
phys_addr_t paddr;
} xpaddr_t;
#define XMADDR(x) ((xmaddr_t) { .maddr = (x) })
#define XPADDR(x) ((xpaddr_t) { .paddr = (x) })
/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
#define INVALID_P2M_ENTRY (~0UL)
xen/mmu: Add the notion of identity (1-1) mapping. Our P2M tree structure is a three-level. On the leaf nodes we set the Machine Frame Number (MFN) of the PFN. What this means is that when one does: pfn_to_mfn(pfn), which is used when creating PTE entries, you get the real MFN of the hardware. When Xen sets up a guest it initially populates a array which has descending (or ascending) MFN values, as so: idx: 0, 1, 2 [0x290F, 0x290E, 0x290D, ..] so pfn_to_mfn(2)==0x290D. If you start, restart many guests that list starts looking quite random. We graft this structure on our P2M tree structure and stick in those MFN in the leafs. But for all other leaf entries, or for the top root, or middle one, for which there is a void entry, we assume it is "missing". So pfn_to_mfn(0xc0000)=INVALID_P2M_ENTRY. We add the possibility of setting 1-1 mappings on certain regions, so that: pfn_to_mfn(0xc0000)=0xc0000 The benefit of this is, that we can assume for non-RAM regions (think PCI BARs, or ACPI spaces), we can create mappings easily b/c we get the PFN value to match the MFN. For this to work efficiently we introduce one new page p2m_identity and allocate (via reserved_brk) any other pages we need to cover the sides (1GB or 4MB boundary violations). All entries in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, no other fancy value). On lookup we spot that the entry points to p2m_identity and return the identity value instead of dereferencing and returning INVALID_P2M_ENTRY. If the entry points to an allocated page, we just proceed as before and return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in appropriate functions (pfn_to_mfn). The reason for having the IDENTITY_FRAME_BIT instead of just returning the PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a non-identity pfn. To protect ourselves against we elect to set (and get) the IDENTITY_FRAME_BIT on all identity mapped PFNs. This simplistic diagram is used to explain the more subtle piece of code. There is also a digram of the P2M at the end that can help. Imagine your E820 looking as so: 1GB 2GB /-------------------+---------\/----\ /----------\ /---+-----\ | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | \-------------------+---------/\----/ \----------/ \---+-----/ ^- 1029MB ^- 2001MB [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), 2048MB = 524288 (0x80000)] And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB is actually not present (would have to kick the balloon driver to put it in). When we are told to set the PFNs for identity mapping (see patch: "xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start of the PFN and the end PFN (263424 and 512256 respectively). The first step is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page covers 512^2 of page estate (1GB) and in case the start or end PFN is not aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn to end pfn. We reserve_brk top leaf pages if they are missing (means they point to p2m_mid_missing). With the E820 example above, 263424 is not 1GB aligned so we allocate a reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. Each entry in the allocate page is "missing" (points to p2m_missing). Next stage is to determine if we need to do a more granular boundary check on the 4MB (or 2MB depending on architecture) off the start and end pfn's. We check if the start pfn and end pfn violate that boundary check, and if so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer granularity of setting which PFNs are missing and which ones are identity. In our example 263424 and 512256 both fail the check so we reserve_brk two pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" values) and assign them to p2m[1][2] and p2m[1][488] respectively. At this point we would at minimum reserve_brk one page, but could be up to three. Each call to set_phys_range_identity has at maximum a three page cost. If we were to query the P2M at this stage, all those entries from start PFN through end PFN (so 1029MB -> 2001MB) would return INVALID_P2M_ENTRY ("missing"). The next step is to walk from the start pfn to the end pfn setting the IDENTITY_FRAME_BIT on each PFN. This is done in 'set_phys_range_identity'. If we find that the middle leaf is pointing to p2m_missing we can swap it over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this point we do not need to worry about boundary aligment (so no need to reserve_brk a middle page, figure out which PFNs are "missing" and which ones are identity), as that has been done earlier. If we find that the middle leaf is not occupied by p2m_identity or p2m_missing, we dereference that page (which covers 512 PFNs) and set the appropriate PFN with IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we set from p2m[1][2][256->511] and p2m[1][488][0->256] with IDENTITY_FRAME_BIT set. All other regions that are void (or not filled) either point to p2m_missing (considered missing) or have the default value of INVALID_P2M_ENTRY (also considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] contain the INVALID_P2M_ENTRY value and are considered "missing." This is what the p2m ends up looking (for the E820 above) with this fabulous drawing: p2m /--------------\ /-----\ | &mfn_list[0],| /-----------------\ | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | |-----| \ | [p2m_identity]+\\ | .... | | 2 |--\ \-------------------->| ... | \\ \----------------/ |-----| \ \---------------/ \\ | 3 |\ \ \\ p2m_identity |-----| \ \-------------------->/---------------\ /-----------------\ | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | \-----/ / | [p2m_identity]+-->| ..., ~0 | / /---------------\ | .... | \-----------------/ / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | / | IDENTITY[@256]|<----/ \---------------/ / | ~0, ~0, .... | | \---------------/ | p2m_missing p2m_missing /------------------\ /------------\ | [p2m_mid_missing]+---->| ~0, ~0, ~0 | | [p2m_mid_missing]+---->| ..., ~0 | \------------------/ \------------/ where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) Reviewed-by: Ian Campbell <ian.campbell@citrix.com> [v5: Changed code to use ranges, added ASCII art] [v6: Rebased on top of xen->p2m code split] [v4: Squished patches in just this one] [v7: Added RESERVE_BRK for potentially allocated pages] [v8: Fixed alignment problem] [v9: Changed 1<<3X to 1<<BITS_PER_LONG-X] [v10: Copied git commit description in the p2m code + Add Review tag] [v11: Title had '2-1' - should be '1-1' mapping] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-01-19 01:15:21 +00:00
#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1))
#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2))
#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT)
xen/mmu: Add the notion of identity (1-1) mapping. Our P2M tree structure is a three-level. On the leaf nodes we set the Machine Frame Number (MFN) of the PFN. What this means is that when one does: pfn_to_mfn(pfn), which is used when creating PTE entries, you get the real MFN of the hardware. When Xen sets up a guest it initially populates a array which has descending (or ascending) MFN values, as so: idx: 0, 1, 2 [0x290F, 0x290E, 0x290D, ..] so pfn_to_mfn(2)==0x290D. If you start, restart many guests that list starts looking quite random. We graft this structure on our P2M tree structure and stick in those MFN in the leafs. But for all other leaf entries, or for the top root, or middle one, for which there is a void entry, we assume it is "missing". So pfn_to_mfn(0xc0000)=INVALID_P2M_ENTRY. We add the possibility of setting 1-1 mappings on certain regions, so that: pfn_to_mfn(0xc0000)=0xc0000 The benefit of this is, that we can assume for non-RAM regions (think PCI BARs, or ACPI spaces), we can create mappings easily b/c we get the PFN value to match the MFN. For this to work efficiently we introduce one new page p2m_identity and allocate (via reserved_brk) any other pages we need to cover the sides (1GB or 4MB boundary violations). All entries in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, no other fancy value). On lookup we spot that the entry points to p2m_identity and return the identity value instead of dereferencing and returning INVALID_P2M_ENTRY. If the entry points to an allocated page, we just proceed as before and return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in appropriate functions (pfn_to_mfn). The reason for having the IDENTITY_FRAME_BIT instead of just returning the PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a non-identity pfn. To protect ourselves against we elect to set (and get) the IDENTITY_FRAME_BIT on all identity mapped PFNs. This simplistic diagram is used to explain the more subtle piece of code. There is also a digram of the P2M at the end that can help. Imagine your E820 looking as so: 1GB 2GB /-------------------+---------\/----\ /----------\ /---+-----\ | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | \-------------------+---------/\----/ \----------/ \---+-----/ ^- 1029MB ^- 2001MB [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), 2048MB = 524288 (0x80000)] And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB is actually not present (would have to kick the balloon driver to put it in). When we are told to set the PFNs for identity mapping (see patch: "xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start of the PFN and the end PFN (263424 and 512256 respectively). The first step is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page covers 512^2 of page estate (1GB) and in case the start or end PFN is not aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn to end pfn. We reserve_brk top leaf pages if they are missing (means they point to p2m_mid_missing). With the E820 example above, 263424 is not 1GB aligned so we allocate a reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. Each entry in the allocate page is "missing" (points to p2m_missing). Next stage is to determine if we need to do a more granular boundary check on the 4MB (or 2MB depending on architecture) off the start and end pfn's. We check if the start pfn and end pfn violate that boundary check, and if so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer granularity of setting which PFNs are missing and which ones are identity. In our example 263424 and 512256 both fail the check so we reserve_brk two pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" values) and assign them to p2m[1][2] and p2m[1][488] respectively. At this point we would at minimum reserve_brk one page, but could be up to three. Each call to set_phys_range_identity has at maximum a three page cost. If we were to query the P2M at this stage, all those entries from start PFN through end PFN (so 1029MB -> 2001MB) would return INVALID_P2M_ENTRY ("missing"). The next step is to walk from the start pfn to the end pfn setting the IDENTITY_FRAME_BIT on each PFN. This is done in 'set_phys_range_identity'. If we find that the middle leaf is pointing to p2m_missing we can swap it over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this point we do not need to worry about boundary aligment (so no need to reserve_brk a middle page, figure out which PFNs are "missing" and which ones are identity), as that has been done earlier. If we find that the middle leaf is not occupied by p2m_identity or p2m_missing, we dereference that page (which covers 512 PFNs) and set the appropriate PFN with IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we set from p2m[1][2][256->511] and p2m[1][488][0->256] with IDENTITY_FRAME_BIT set. All other regions that are void (or not filled) either point to p2m_missing (considered missing) or have the default value of INVALID_P2M_ENTRY (also considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] contain the INVALID_P2M_ENTRY value and are considered "missing." This is what the p2m ends up looking (for the E820 above) with this fabulous drawing: p2m /--------------\ /-----\ | &mfn_list[0],| /-----------------\ | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | |-----| \ | [p2m_identity]+\\ | .... | | 2 |--\ \-------------------->| ... | \\ \----------------/ |-----| \ \---------------/ \\ | 3 |\ \ \\ p2m_identity |-----| \ \-------------------->/---------------\ /-----------------\ | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | \-----/ / | [p2m_identity]+-->| ..., ~0 | / /---------------\ | .... | \-----------------/ / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | / | IDENTITY[@256]|<----/ \---------------/ / | ~0, ~0, .... | | \---------------/ | p2m_missing p2m_missing /------------------\ /------------\ | [p2m_mid_missing]+---->| ~0, ~0, ~0 | | [p2m_mid_missing]+---->| ..., ~0 | \------------------/ \------------/ where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) Reviewed-by: Ian Campbell <ian.campbell@citrix.com> [v5: Changed code to use ranges, added ASCII art] [v6: Rebased on top of xen->p2m code split] [v4: Squished patches in just this one] [v7: Added RESERVE_BRK for potentially allocated pages] [v8: Fixed alignment problem] [v9: Changed 1<<3X to 1<<BITS_PER_LONG-X] [v10: Copied git commit description in the p2m code + Add Review tag] [v11: Title had '2-1' - should be '1-1' mapping] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-01-19 01:15:21 +00:00
#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT)
/* Maximum amount of memory we can handle in a domain in pages */
#define MAX_DOMAIN_PAGES \
((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
extern unsigned long *machine_to_phys_mapping;
extern unsigned long machine_to_phys_nr;
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
xen/mmu: Add the notion of identity (1-1) mapping. Our P2M tree structure is a three-level. On the leaf nodes we set the Machine Frame Number (MFN) of the PFN. What this means is that when one does: pfn_to_mfn(pfn), which is used when creating PTE entries, you get the real MFN of the hardware. When Xen sets up a guest it initially populates a array which has descending (or ascending) MFN values, as so: idx: 0, 1, 2 [0x290F, 0x290E, 0x290D, ..] so pfn_to_mfn(2)==0x290D. If you start, restart many guests that list starts looking quite random. We graft this structure on our P2M tree structure and stick in those MFN in the leafs. But for all other leaf entries, or for the top root, or middle one, for which there is a void entry, we assume it is "missing". So pfn_to_mfn(0xc0000)=INVALID_P2M_ENTRY. We add the possibility of setting 1-1 mappings on certain regions, so that: pfn_to_mfn(0xc0000)=0xc0000 The benefit of this is, that we can assume for non-RAM regions (think PCI BARs, or ACPI spaces), we can create mappings easily b/c we get the PFN value to match the MFN. For this to work efficiently we introduce one new page p2m_identity and allocate (via reserved_brk) any other pages we need to cover the sides (1GB or 4MB boundary violations). All entries in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, no other fancy value). On lookup we spot that the entry points to p2m_identity and return the identity value instead of dereferencing and returning INVALID_P2M_ENTRY. If the entry points to an allocated page, we just proceed as before and return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in appropriate functions (pfn_to_mfn). The reason for having the IDENTITY_FRAME_BIT instead of just returning the PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a non-identity pfn. To protect ourselves against we elect to set (and get) the IDENTITY_FRAME_BIT on all identity mapped PFNs. This simplistic diagram is used to explain the more subtle piece of code. There is also a digram of the P2M at the end that can help. Imagine your E820 looking as so: 1GB 2GB /-------------------+---------\/----\ /----------\ /---+-----\ | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | \-------------------+---------/\----/ \----------/ \---+-----/ ^- 1029MB ^- 2001MB [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), 2048MB = 524288 (0x80000)] And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB is actually not present (would have to kick the balloon driver to put it in). When we are told to set the PFNs for identity mapping (see patch: "xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start of the PFN and the end PFN (263424 and 512256 respectively). The first step is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page covers 512^2 of page estate (1GB) and in case the start or end PFN is not aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn to end pfn. We reserve_brk top leaf pages if they are missing (means they point to p2m_mid_missing). With the E820 example above, 263424 is not 1GB aligned so we allocate a reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. Each entry in the allocate page is "missing" (points to p2m_missing). Next stage is to determine if we need to do a more granular boundary check on the 4MB (or 2MB depending on architecture) off the start and end pfn's. We check if the start pfn and end pfn violate that boundary check, and if so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer granularity of setting which PFNs are missing and which ones are identity. In our example 263424 and 512256 both fail the check so we reserve_brk two pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" values) and assign them to p2m[1][2] and p2m[1][488] respectively. At this point we would at minimum reserve_brk one page, but could be up to three. Each call to set_phys_range_identity has at maximum a three page cost. If we were to query the P2M at this stage, all those entries from start PFN through end PFN (so 1029MB -> 2001MB) would return INVALID_P2M_ENTRY ("missing"). The next step is to walk from the start pfn to the end pfn setting the IDENTITY_FRAME_BIT on each PFN. This is done in 'set_phys_range_identity'. If we find that the middle leaf is pointing to p2m_missing we can swap it over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this point we do not need to worry about boundary aligment (so no need to reserve_brk a middle page, figure out which PFNs are "missing" and which ones are identity), as that has been done earlier. If we find that the middle leaf is not occupied by p2m_identity or p2m_missing, we dereference that page (which covers 512 PFNs) and set the appropriate PFN with IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we set from p2m[1][2][256->511] and p2m[1][488][0->256] with IDENTITY_FRAME_BIT set. All other regions that are void (or not filled) either point to p2m_missing (considered missing) or have the default value of INVALID_P2M_ENTRY (also considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] contain the INVALID_P2M_ENTRY value and are considered "missing." This is what the p2m ends up looking (for the E820 above) with this fabulous drawing: p2m /--------------\ /-----\ | &mfn_list[0],| /-----------------\ | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | |-----| \ | [p2m_identity]+\\ | .... | | 2 |--\ \-------------------->| ... | \\ \----------------/ |-----| \ \---------------/ \\ | 3 |\ \ \\ p2m_identity |-----| \ \-------------------->/---------------\ /-----------------\ | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | \-----/ / | [p2m_identity]+-->| ..., ~0 | / /---------------\ | .... | \-----------------/ / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | / | IDENTITY[@256]|<----/ \---------------/ / | ~0, ~0, .... | | \---------------/ | p2m_missing p2m_missing /------------------\ /------------\ | [p2m_mid_missing]+---->| ~0, ~0, ~0 | | [p2m_mid_missing]+---->| ..., ~0 | \------------------/ \------------/ where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) Reviewed-by: Ian Campbell <ian.campbell@citrix.com> [v5: Changed code to use ranges, added ASCII art] [v6: Rebased on top of xen->p2m code split] [v4: Squished patches in just this one] [v7: Added RESERVE_BRK for potentially allocated pages] [v8: Fixed alignment problem] [v9: Changed 1<<3X to 1<<BITS_PER_LONG-X] [v10: Copied git commit description in the p2m code + Add Review tag] [v11: Title had '2-1' - should be '1-1' mapping] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-01-19 01:15:21 +00:00
extern unsigned long set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e);
xen/p2m/m2p/gnttab: Support GNTMAP_host_map in the M2P override. We only supported the M2P (and P2M) override only for the GNTMAP_contains_pte type mappings. Meaning that we grants operations would "contain the machine address of the PTE to update" If the flag is unset, then the grant operation is "contains a host virtual address". The latter case means that the Hypervisor takes care of updating our page table (specifically the PTE entry) with the guest's MFN. As such we should not try to do anything with the PTE. Previous to this patch we would try to clear the PTE which resulted in Xen hypervisor being upset with us: (XEN) mm.c:1066:d0 Attempt to implicitly unmap a granted PTE c0100000ccc59067 (XEN) domain_crash called from mm.c:1067 (XEN) Domain 0 (vcpu#0) crashed on cpu#3: (XEN) ----[ Xen-4.0-110228 x86_64 debug=y Not tainted ]---- and crashing us. This patch allows us to inhibit the PTE clearing in the PV guest if the GNTMAP_contains_pte is not set. On the m2p_remove_override path we provide the same parameter. Sadly in the grant-table driver we do not have a mechanism to tell m2p_remove_override whether to clear the PTE or not. Since the grant-table driver is used by user-space, we can safely assume that it operates only on PTE's. Hence the implementation for it to work on !GNTMAP_contains_pte returns -EOPNOTSUPP. In the future we can implement the support for this. It will require some extra accounting structure to keep track of the page[i], and the flag. [v1: Added documentation details, made it return -EOPNOTSUPP instead of trying to do a half-way implementation] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-02-28 22:58:48 +00:00
extern int m2p_add_override(unsigned long mfn, struct page *page,
struct gnttab_map_grant_ref *kmap_op);
extern int m2p_remove_override(struct page *page,
struct gnttab_map_grant_ref *kmap_op);
extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
if (xen_feature(XENFEAT_auto_translated_physmap))
return pfn;
mfn = get_phys_to_machine(pfn);
if (mfn != INVALID_P2M_ENTRY)
xen/mmu: Add the notion of identity (1-1) mapping. Our P2M tree structure is a three-level. On the leaf nodes we set the Machine Frame Number (MFN) of the PFN. What this means is that when one does: pfn_to_mfn(pfn), which is used when creating PTE entries, you get the real MFN of the hardware. When Xen sets up a guest it initially populates a array which has descending (or ascending) MFN values, as so: idx: 0, 1, 2 [0x290F, 0x290E, 0x290D, ..] so pfn_to_mfn(2)==0x290D. If you start, restart many guests that list starts looking quite random. We graft this structure on our P2M tree structure and stick in those MFN in the leafs. But for all other leaf entries, or for the top root, or middle one, for which there is a void entry, we assume it is "missing". So pfn_to_mfn(0xc0000)=INVALID_P2M_ENTRY. We add the possibility of setting 1-1 mappings on certain regions, so that: pfn_to_mfn(0xc0000)=0xc0000 The benefit of this is, that we can assume for non-RAM regions (think PCI BARs, or ACPI spaces), we can create mappings easily b/c we get the PFN value to match the MFN. For this to work efficiently we introduce one new page p2m_identity and allocate (via reserved_brk) any other pages we need to cover the sides (1GB or 4MB boundary violations). All entries in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, no other fancy value). On lookup we spot that the entry points to p2m_identity and return the identity value instead of dereferencing and returning INVALID_P2M_ENTRY. If the entry points to an allocated page, we just proceed as before and return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in appropriate functions (pfn_to_mfn). The reason for having the IDENTITY_FRAME_BIT instead of just returning the PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a non-identity pfn. To protect ourselves against we elect to set (and get) the IDENTITY_FRAME_BIT on all identity mapped PFNs. This simplistic diagram is used to explain the more subtle piece of code. There is also a digram of the P2M at the end that can help. Imagine your E820 looking as so: 1GB 2GB /-------------------+---------\/----\ /----------\ /---+-----\ | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | \-------------------+---------/\----/ \----------/ \---+-----/ ^- 1029MB ^- 2001MB [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), 2048MB = 524288 (0x80000)] And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB is actually not present (would have to kick the balloon driver to put it in). When we are told to set the PFNs for identity mapping (see patch: "xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start of the PFN and the end PFN (263424 and 512256 respectively). The first step is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page covers 512^2 of page estate (1GB) and in case the start or end PFN is not aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn to end pfn. We reserve_brk top leaf pages if they are missing (means they point to p2m_mid_missing). With the E820 example above, 263424 is not 1GB aligned so we allocate a reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. Each entry in the allocate page is "missing" (points to p2m_missing). Next stage is to determine if we need to do a more granular boundary check on the 4MB (or 2MB depending on architecture) off the start and end pfn's. We check if the start pfn and end pfn violate that boundary check, and if so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer granularity of setting which PFNs are missing and which ones are identity. In our example 263424 and 512256 both fail the check so we reserve_brk two pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" values) and assign them to p2m[1][2] and p2m[1][488] respectively. At this point we would at minimum reserve_brk one page, but could be up to three. Each call to set_phys_range_identity has at maximum a three page cost. If we were to query the P2M at this stage, all those entries from start PFN through end PFN (so 1029MB -> 2001MB) would return INVALID_P2M_ENTRY ("missing"). The next step is to walk from the start pfn to the end pfn setting the IDENTITY_FRAME_BIT on each PFN. This is done in 'set_phys_range_identity'. If we find that the middle leaf is pointing to p2m_missing we can swap it over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this point we do not need to worry about boundary aligment (so no need to reserve_brk a middle page, figure out which PFNs are "missing" and which ones are identity), as that has been done earlier. If we find that the middle leaf is not occupied by p2m_identity or p2m_missing, we dereference that page (which covers 512 PFNs) and set the appropriate PFN with IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we set from p2m[1][2][256->511] and p2m[1][488][0->256] with IDENTITY_FRAME_BIT set. All other regions that are void (or not filled) either point to p2m_missing (considered missing) or have the default value of INVALID_P2M_ENTRY (also considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] contain the INVALID_P2M_ENTRY value and are considered "missing." This is what the p2m ends up looking (for the E820 above) with this fabulous drawing: p2m /--------------\ /-----\ | &mfn_list[0],| /-----------------\ | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | |-----| \ | [p2m_identity]+\\ | .... | | 2 |--\ \-------------------->| ... | \\ \----------------/ |-----| \ \---------------/ \\ | 3 |\ \ \\ p2m_identity |-----| \ \-------------------->/---------------\ /-----------------\ | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | \-----/ / | [p2m_identity]+-->| ..., ~0 | / /---------------\ | .... | \-----------------/ / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | / | IDENTITY[@256]|<----/ \---------------/ / | ~0, ~0, .... | | \---------------/ | p2m_missing p2m_missing /------------------\ /------------\ | [p2m_mid_missing]+---->| ~0, ~0, ~0 | | [p2m_mid_missing]+---->| ..., ~0 | \------------------/ \------------/ where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) Reviewed-by: Ian Campbell <ian.campbell@citrix.com> [v5: Changed code to use ranges, added ASCII art] [v6: Rebased on top of xen->p2m code split] [v4: Squished patches in just this one] [v7: Added RESERVE_BRK for potentially allocated pages] [v8: Fixed alignment problem] [v9: Changed 1<<3X to 1<<BITS_PER_LONG-X] [v10: Copied git commit description in the p2m code + Add Review tag] [v11: Title had '2-1' - should be '1-1' mapping] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-01-19 01:15:21 +00:00
mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
return mfn;
}
static inline int phys_to_machine_mapping_valid(unsigned long pfn)
{
if (xen_feature(XENFEAT_auto_translated_physmap))
return 1;
return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
}
xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel <david.vrabel@citrix.com> Cc: Stefano Stabellini <stefano.stabellini@citrix.com> Cc: Jan Beulich <JBeulich@suse.com> -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-09-13 14:13:30 +00:00
static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
{
unsigned long pfn;
xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel <david.vrabel@citrix.com> Cc: Stefano Stabellini <stefano.stabellini@citrix.com> Cc: Jan Beulich <JBeulich@suse.com> -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-09-13 14:13:30 +00:00
int ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel <david.vrabel@citrix.com> Cc: Stefano Stabellini <stefano.stabellini@citrix.com> Cc: Jan Beulich <JBeulich@suse.com> -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-09-13 14:13:30 +00:00
if (unlikely(mfn >= machine_to_phys_nr))
return ~0;
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
if (ret < 0)
xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel <david.vrabel@citrix.com> Cc: Stefano Stabellini <stefano.stabellini@citrix.com> Cc: Jan Beulich <JBeulich@suse.com> -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-09-13 14:13:30 +00:00
return ~0;
return pfn;
}
static inline unsigned long mfn_to_pfn(unsigned long mfn)
{
unsigned long pfn;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
pfn = mfn_to_pfn_no_overrides(mfn);
if (get_phys_to_machine(pfn) != mfn) {
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
* table to see if there's a better pfn to use.
*
* m2p_find_override_pfn returns ~0 if it doesn't find anything.
*/
pfn = m2p_find_override_pfn(mfn, ~0);
xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel <david.vrabel@citrix.com> Cc: Stefano Stabellini <stefano.stabellini@citrix.com> Cc: Jan Beulich <JBeulich@suse.com> -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-09-13 14:13:30 +00:00
}
/*
* pfn is ~0 if there are no entries in the m2p for mfn or if the
* entry doesn't map back to the mfn and m2p_override doesn't have a
* valid entry for it.
*/
if (pfn == ~0 &&
get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
pfn = mfn;
return pfn;
}
static inline xmaddr_t phys_to_machine(xpaddr_t phys)
{
unsigned offset = phys.paddr & ~PAGE_MASK;
return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
}
static inline xpaddr_t machine_to_phys(xmaddr_t machine)
{
unsigned offset = machine.maddr & ~PAGE_MASK;
return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
}
/*
* We detect special mappings in one of two ways:
* 1. If the MFN is an I/O page then Xen will set the m2p entry
* to be outside our maximum possible pseudophys range.
* 2. If the MFN belongs to a different domain then we will certainly
* not have MFN in our p2m table. Conversely, if the page is ours,
* then we'll have p2m(m2p(MFN))==MFN.
* If we detect a special mapping then it doesn't have a 'struct page'.
* We force !pfn_valid() by returning an out-of-range pointer.
*
* NB. These checks require that, for any MFN that is not in our reservation,
* there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
* we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
* Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
*
* NB2. When deliberately mapping foreign pages into the p2m table, you *must*
* use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
* require. In all the cases we care about, the FOREIGN_FRAME bit is
* masked (e.g., pfn_to_mfn()) so behaviour there is correct.
*/
static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
{
unsigned long pfn;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
pfn = mfn_to_pfn(mfn);
if (get_phys_to_machine(pfn) != mfn)
return -1; /* force !pfn_valid() */
return pfn;
}
/* VIRT <-> MACHINE conversion */
#define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v))))
#define virt_to_pfn(v) (PFN_DOWN(__pa(v)))
#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v)))
#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT))
static inline unsigned long pte_mfn(pte_t pte)
{
return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
}
static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
pte_t pte;
pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
massage_pgprot(pgprot);
return pte;
}
static inline pteval_t pte_val_ma(pte_t pte)
{
return pte.pte;
}
static inline pte_t __pte_ma(pteval_t x)
{
return (pte_t) { .pte = x };
}
#define pmd_val_ma(v) ((v).pmd)
#ifdef __PAGETABLE_PUD_FOLDED
#define pud_val_ma(v) ((v).pgd.pgd)
#else
#define pud_val_ma(v) ((v).pud)
#endif
#define __pmd_ma(x) ((pmd_t) { (x) } )
#define pgd_val_ma(x) ((x).pgd)
void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
xmaddr_t arbitrary_virt_to_machine(void *address);
unsigned long arbitrary_virt_to_mfn(void *vaddr);
void make_lowmem_page_readonly(void *vaddr);
void make_lowmem_page_readwrite(void *vaddr);
#define xen_remap(cookie, size) ioremap((cookie), (size));
#endif /* _ASM_X86_XEN_PAGE_H */