The patch titled
Subject: scripts/gdb: add mm introspection utils
has been added to the -mm mm-nonmm-unstable branch. Its filename is
scripts-gdb-add-mm-introspection-utils.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/scripts-gdb-add-mm-introspection-utils.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Dmitrii Bundin <dmitrii.bundin.a@xxxxxxxxx>
Subject: scripts/gdb: add mm introspection utils
Date: Fri, 30 Dec 2022 19:35:12 +0300
This command provides a way to traverse the entire page hierarchy by a
given virtual address. In addition to qemu's commands info tlb/info mem
it provides the complete information about the paging structure for an
arbitrary virtual address. It supports 4Kb/2MB/1GB and 5 level paging.
Here is an example output for 2MB success translation:
CR3:
CR3 BINARY DATA: 0x10c1d2002
NEXT ENTRY PHYSICALL ADDRESS: 0x10c1d2000
---
PAGE LEVEL WRITE THROUGH(bit 3): False
PAGE LEVEL CACHE DISABLED(bit 4): False
LEVEL 4:
ENTRY ADDRESS: 0xffff88810c1d27f0
PAGE ENTRY BINARY DATA: 0x8000000105dca067
NEXT ENTRY PHYSICALL ADDRESS: 0x105dca000
---
ENTRY PRESENT(bit 0): True
READ/WRITE ACCESS ALLOWED(bit 1): True
USER ACCESS ALLOWED(bit 2): True
PAGE LEVEL WRITE THROUGH(bit 3): False
PAGE LEVEL CACHE DISABLED(bit 4): False
ENTRY HAS BEEN ACCESSED(bit 5): True
PAGE SIZE(bit 7): False
RESTART TO ORDINARY(bit 11): False
EXECUTE DISABLE(bit 63): True
LEVEL 3:
ENTRY ADDRESS: 0xffff888105dca9d0
PAGE ENTRY BINARY DATA: 0x105c87067
NEXT ENTRY PHYSICALL ADDRESS: 0x105c87000
---
ENTRY PRESENT(bit 0): True
READ/WRITE ACCESS ALLOWED(bit 1): True
USER ACCESS ALLOWED(bit 2): True
PAGE LEVEL WRITE THROUGH(bit 3): False
PAGE LEVEL CACHE DISABLED(bit 4): False
ENTRY HAS BEEN ACCESSED(bit 5): True
PAGE SIZE(bit 7): False
RESTART TO ORDINARY(bit 11): False
EXECUTE DISABLE(bit 63): False
LEVEL 2:
ENTRY ADDRESS: 0xffff888105c87698
PAGE ENTRY BINARY DATA: 0x80000001622008e7
PAGE SIZE: 2MB
PAGE PHYSICALL ADDRESS: 0x162200000
---
ENTRY PRESENT(bit 0): True
READ/WRITE ACCESS ALLOWED(bit 1): True
USER ACCESS ALLOWED(bit 2): True
PAGE LEVEL WRITE THROUGH(bit 3): False
PAGE LEVEL CACHE DISABLED(bit 4): False
ENTRY HAS BEEN ACCESSED(bit 5): True
PAGE DIRTY(bit 6): True
PAGE SIZE(bit 7): True
GLOBAL TRANSLATION(bit 8): False
RESTART TO ORDINARY(bit 11): True
PAT(bit 12): False
PROTECTION KEY(bits (62, 59)): 0
EXECUTE DISABLE(bit 63): True
Link: https://lkml.kernel.org/r/20221230163512.23736-1-dmitrii.bundin.a@xxxxxxxxx
Signed-off-by: Dmitrii Bundin <dmitrii.bundin.a@xxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jan Kiszka <jan.kiszka@xxxxxxxxxxx>
Cc: Kieran Bingham <kbingham@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- /dev/null
+++ a/scripts/gdb/linux/mm.py
@@ -0,0 +1,220 @@
+#
+# gdb helper commands and functions for Linux kernel debugging
+#
+# routines to introspect virtual memory
+#
+# Authors:
+# Dmitrii Bundin <dmitrii.bundin.a@xxxxxxxxx>
+#
+# This work is licensed under the terms of the GNU GPL version 2.
+#
+
+import gdb
+
+from linux import utils
+
+PHYSICAL_ADDRESS_MASK = gdb.parse_and_eval('0xfffffffffffff')
+
+
+def page_mask(level=1):
+ # 4KB
+ if level == 1:
+ return gdb.parse_and_eval('(u64) ~0xfff')
+ # 2MB
+ elif level == 2:
+ return gdb.parse_and_eval('(u64) ~0x1fffff')
+ # 1GB
+ elif level == 3:
+ return gdb.parse_and_eval('(u64) ~0x3fffffff')
+ else:
+ raise Exception(f'Unknown page level: {level}')
+
+
+def _page_offset_base():
+ pob_symbol = gdb.lookup_global_symbol('page_offset_base')
+ pob = pob_symbol.name if pob_symbol else '0xffff888000000000'
+ return gdb.parse_and_eval(pob)
+
+
+def is_bit_defined_tupled(data, offset):
+ return offset, bool(data >> offset & 1)
+
+def content_tupled(data, bit_start, bit_end):
+ return (bit_end, bit_start), data >> bit_start & ((1 << (1 + bit_end - bit_start)) - 1)
+
+def entry_va(level, phys_addr, translating_va):
+ def start_bit(level):
+ if level == 5:
+ return 48
+ elif level == 4:
+ return 39
+ elif level == 3:
+ return 30
+ elif level == 2:
+ return 21
+ elif level == 1:
+ return 12
+ else:
+ raise Exception(f'Unknown level {level}')
+
+ entry_offset = ((translating_va >> start_bit(level)) & 511) * 8
+ entry_va = _page_offset_base() + phys_addr + entry_offset
+ return entry_va
+
+class Cr3():
+ def __init__(self, cr3, page_levels):
+ self.cr3 = cr3
+ self.page_levels = page_levels
+ self.page_level_write_through = is_bit_defined_tupled(cr3, 3)
+ self.page_level_cache_disabled = is_bit_defined_tupled(cr3, 4)
+ self.next_entry_physical_address = cr3 & PHYSICAL_ADDRESS_MASK & page_mask()
+
+ def next_entry(self, va):
+ next_level = self.page_levels
+ return PageHierarchyEntry(entry_va(next_level, self.next_entry_physical_address, va), next_level)
+
+ def mk_string(self):
+ return f"""\
+CR3:
+ CR3 BINARY DATA: {hex(self.cr3)}
+ NEXT ENTRY PHYSICALL ADDRESS: {hex(self.next_entry_physical_address)}
+ ---
+ PAGE LEVEL WRITE THROUGH(bit {self.page_level_write_through[0]}): {self.page_level_write_through[1]}
+ PAGE LEVEL CACHE DISABLED(bit {self.page_level_cache_disabled[0]}): {self.page_level_cache_disabled[1]}
+"""
+
+
+class PageHierarchyEntry():
+ def __init__(self, address, level):
+ data = int.from_bytes(
+ memoryview(gdb.selected_inferior().read_memory(address, 8)),
+ "little"
+ )
+ if level == 1:
+ self.is_page = True
+ self.entry_present = is_bit_defined_tupled(data, 0)
+ self.read_write = is_bit_defined_tupled(data, 1)
+ self.user_access_allowed = is_bit_defined_tupled(data, 2)
+ self.page_level_write_through = is_bit_defined_tupled(data, 3)
+ self.page_level_cache_disabled = is_bit_defined_tupled(data, 4)
+ self.entry_was_accessed = is_bit_defined_tupled(data, 5)
+ self.dirty = is_bit_defined_tupled(data, 6)
+ self.pat = is_bit_defined_tupled(data, 7)
+ self.global_translation = is_bit_defined_tupled(data, 8)
+ self.page_physical_address = data & PHYSICAL_ADDRESS_MASK & page_mask(level)
+ self.next_entry_physical_address = None
+ self.hlat_restart_with_ordinary = is_bit_defined_tupled(data, 11)
+ self.protection_key = content_tupled(data, 59, 62)
+ self.executed_disable = is_bit_defined_tupled(data, 63)
+ else:
+ page_size = is_bit_defined_tupled(data, 7)
+ page_size_bit = page_size[1]
+ self.is_page = page_size_bit
+ self.entry_present = is_bit_defined_tupled(data, 0)
+ self.read_write = is_bit_defined_tupled(data, 1)
+ self.user_access_allowed = is_bit_defined_tupled(data, 2)
+ self.page_level_write_through = is_bit_defined_tupled(data, 3)
+ self.page_level_cache_disabled = is_bit_defined_tupled(data, 4)
+ self.entry_was_accessed = is_bit_defined_tupled(data, 5)
+ self.page_size = page_size
+ self.dirty = is_bit_defined_tupled(
+ data, 6) if page_size_bit else None
+ self.global_translation = is_bit_defined_tupled(
+ data, 8) if page_size_bit else None
+ self.pat = is_bit_defined_tupled(
+ data, 12) if page_size_bit else None
+ self.page_physical_address = data & PHYSICAL_ADDRESS_MASK & page_mask(level) if page_size_bit else None
+ self.next_entry_physical_address = None if page_size_bit else data & PHYSICAL_ADDRESS_MASK & page_mask()
+ self.hlat_restart_with_ordinary = is_bit_defined_tupled(data, 11)
+ self.protection_key = content_tupled(data, 59, 62) if page_size_bit else None
+ self.executed_disable = is_bit_defined_tupled(data, 63)
+ self.address = address
+ self.page_entry_binary_data = data
+ self.page_hierarchy_level = level
+
+ def next_entry(self, va):
+ if self.is_page or not self.entry_present[1]:
+ return None
+
+ next_level = self.page_hierarchy_level - 1
+ return PageHierarchyEntry(entry_va(next_level, self.next_entry_physical_address, va), next_level)
+
+
+ def mk_string(self):
+ if not self.entry_present[1]:
+ return f"""\
+LEVEL {self.page_hierarchy_level}:
+ ENTRY ADDRESS: {hex(self.address)}
+ PAGE ENTRY BINARY DATA: {hex(self.page_entry_binary_data)}
+ ---
+ PAGE ENTRY IS NOT PRESENT!
+"""
+ elif self.is_page:
+ return f"""\
+LEVEL {self.page_hierarchy_level}:
+ ENTRY ADDRESS: {hex(self.address)}
+ PAGE ENTRY BINARY DATA: {hex(self.page_entry_binary_data)}
+ PAGE SIZE: {'1GB' if self.page_hierarchy_level == 3 else '2MB' if self.page_hierarchy_level == 2 else '4KB' if self.page_hierarchy_level == 1 else 'Unknown page size for level:' + self.page_hierarchy_level}
+ PAGE PHYSICALL ADDRESS: {hex(self.page_physical_address)}
+ ---
+ ENTRY PRESENT(bit {self.entry_present[0]}): {self.entry_present[1]}
+ READ/WRITE ACCESS ALLOWED(bit {self.read_write[0]}): {self.read_write[1]}
+ USER ACCESS ALLOWED(bit {self.user_access_allowed[0]}): {self.user_access_allowed[1]}
+ PAGE LEVEL WRITE THROUGH(bit {self.page_level_write_through[0]}): {self.page_level_write_through[1]}
+ PAGE LEVEL CACHE DISABLED(bit {self.page_level_cache_disabled[0]}): {self.page_level_cache_disabled[1]}
+ ENTRY HAS BEEN ACCESSED(bit {self.entry_was_accessed[0]}): {self.entry_was_accessed[1]}
+ PAGE DIRTY(bit {self.dirty[0]}): {self.dirty[1]}
+ """ + \
+ ("" if self.page_hierarchy_level == 1 else f"""PAGE SIZE(bit {self.page_size[0]}): {self.page_size[1]}
+ """) + \
+ f"""GLOBAL TRANSLATION(bit {self.global_translation[0]}): {self.global_translation[1]}
+ RESTART TO ORDINARY(bit {self.hlat_restart_with_ordinary[0]}): {self.hlat_restart_with_ordinary[1]}
+ PAT(bit {self.pat[0]}): {self.pat[1]}
+ PROTECTION KEY(bits {self.protection_key[0]}): {self.protection_key[1]}
+ EXECUTE DISABLE(bit {self.executed_disable[0]}): {self.executed_disable[1]}
+"""
+ else:
+ return f"""\
+LEVEL {self.page_hierarchy_level}:
+ ENTRY ADDRESS: {hex(self.address)}
+ PAGE ENTRY BINARY DATA: {hex(self.page_entry_binary_data)}
+ NEXT ENTRY PHYSICALL ADDRESS: {hex(self.next_entry_physical_address)}
+ ---
+ ENTRY PRESENT(bit {self.entry_present[0]}): {self.entry_present[1]}
+ READ/WRITE ACCESS ALLOWED(bit {self.read_write[0]}): {self.read_write[1]}
+ USER ACCESS ALLOWED(bit {self.user_access_allowed[0]}): {self.user_access_allowed[1]}
+ PAGE LEVEL WRITE THROUGH(bit {self.page_level_write_through[0]}): {self.page_level_write_through[1]}
+ PAGE LEVEL CACHE DISABLED(bit {self.page_level_cache_disabled[0]}): {self.page_level_cache_disabled[1]}
+ ENTRY HAS BEEN ACCESSED(bit {self.entry_was_accessed[0]}): {self.entry_was_accessed[1]}
+ PAGE SIZE(bit {self.page_size[0]}): {self.page_size[1]}
+ RESTART TO ORDINARY(bit {self.hlat_restart_with_ordinary[0]}): {self.hlat_restart_with_ordinary[1]}
+ EXECUTE DISABLE(bit {self.executed_disable[0]}): {self.executed_disable[1]}
+"""
+
+
+class TranslateVM(gdb.Command):
+ """Prints the entire paging structure used to translate a given virtual address.
+
+Having an address space of the currently executed process translates the virtual address
+and prints detailed information of all paging structure levels used for the transaltion."""
+
+ def __init__(self):
+ super(TranslateVM, self).__init__('translate-vm', gdb.COMMAND_USER)
+
+ def invoke(self, arg, from_tty):
+ if utils.is_target_arch("x86"):
+ vm_address = gdb.parse_and_eval(f'{arg}')
+ cr3_data = gdb.parse_and_eval('$cr3')
+ cr4 = gdb.parse_and_eval('$cr4')
+ page_levels = 5 if cr4 & (1 << 12) else 4
+ page_entry = Cr3(cr3_data, page_levels)
+ while page_entry:
+ gdb.write(page_entry.mk_string())
+ page_entry = page_entry.next_entry(vm_address)
+ else:
+ gdb.GdbError("Virtual address translation is not"
+ "supported for this arch")
+
+
+
+TranslateVM()
--- a/scripts/gdb/vmlinux-gdb.py~scripts-gdb-add-mm-introspection-utils
+++ a/scripts/gdb/vmlinux-gdb.py
@@ -37,3 +37,4 @@ else:
import linux.clk
import linux.genpd
import linux.device
+ import linux.mm
_
Patches currently in -mm which might be from dmitrii.bundin.a@xxxxxxxxx are
scripts-gdb-add-mm-introspection-utils.patch
