From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: Pierrick Bouvier <pierrick.bouvier@linaro.org>,
Helge Deller <deller@gmx.de>
Subject: [PATCH 43/60] linux-user: Split out mmap_h_gt_g
Date: Fri, 1 Mar 2024 13:06:02 -1000 [thread overview]
Message-ID: <20240301230619.661008-44-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240301230619.661008-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Acked-by: Helge Deller <deller@gmx.de>
Message-Id: <20240102015808.132373-24-richard.henderson@linaro.org>
---
linux-user/mmap.c | 288 ++++++++++++++++++++++------------------------
1 file changed, 139 insertions(+), 149 deletions(-)
diff --git a/linux-user/mmap.c b/linux-user/mmap.c
index ff8f9f7ed0..82f4026283 100644
--- a/linux-user/mmap.c
+++ b/linux-user/mmap.c
@@ -282,7 +282,16 @@ static int do_munmap(void *addr, size_t len)
return munmap(addr, len);
}
-/* map an incomplete host page */
+/*
+ * Map an incomplete host page.
+ *
+ * Here be dragons. This case will not work if there is an existing
+ * overlapping host page, which is file mapped, and for which the mapping
+ * is beyond the end of the file. In that case, we will see SIGBUS when
+ * trying to write a portion of this page.
+ *
+ * FIXME: Work around this with a temporary signal handler and longjmp.
+ */
static bool mmap_frag(abi_ulong real_start, abi_ulong start, abi_ulong last,
int prot, int flags, int fd, off_t offset)
{
@@ -719,19 +728,138 @@ static abi_long mmap_h_lt_g(abi_ulong start, abi_ulong len, int host_prot,
return mmap_end(start, last, start, pass_last, mmap_flags, page_flags);
}
+/*
+ * Special case host page size > target page size.
+ *
+ * The two special cases are address and file offsets that are valid
+ * for the guest that cannot be directly represented by the host.
+ */
+static abi_long mmap_h_gt_g(abi_ulong start, abi_ulong len,
+ int target_prot, int host_prot,
+ int flags, int page_flags, int fd,
+ off_t offset, int host_page_size)
+{
+ void *p, *want_p = g2h_untagged(start);
+ off_t host_offset = offset & -host_page_size;
+ abi_ulong last, real_start, real_last;
+ bool misaligned_offset = false;
+ size_t host_len;
+
+ if (!(flags & (MAP_FIXED | MAP_FIXED_NOREPLACE))) {
+ /*
+ * Adjust the offset to something representable on the host.
+ */
+ host_len = len + offset - host_offset;
+ p = mmap(want_p, host_len, host_prot, flags, fd, host_offset);
+ if (p == MAP_FAILED) {
+ return -1;
+ }
+
+ /* Update start to the file position at offset. */
+ p += offset - host_offset;
+
+ start = h2g(p);
+ last = start + len - 1;
+ return mmap_end(start, last, start, last, flags, page_flags);
+ }
+
+ if (!(flags & MAP_ANONYMOUS)) {
+ misaligned_offset = (start ^ offset) & (host_page_size - 1);
+
+ /*
+ * The fallback for misalignment is a private mapping + read.
+ * This carries none of semantics required of MAP_SHARED.
+ */
+ if (misaligned_offset && (flags & MAP_TYPE) != MAP_PRIVATE) {
+ errno = EINVAL;
+ return -1;
+ }
+ }
+
+ last = start + len - 1;
+ real_start = start & -host_page_size;
+ real_last = ROUND_UP(last, host_page_size) - 1;
+
+ /*
+ * Handle the start and end of the mapping.
+ */
+ if (real_start < start) {
+ abi_ulong real_page_last = real_start + host_page_size - 1;
+ if (last <= real_page_last) {
+ /* Entire allocation a subset of one host page. */
+ if (!mmap_frag(real_start, start, last, target_prot,
+ flags, fd, offset)) {
+ return -1;
+ }
+ return mmap_end(start, last, -1, 0, flags, page_flags);
+ }
+
+ if (!mmap_frag(real_start, start, real_page_last, target_prot,
+ flags, fd, offset)) {
+ return -1;
+ }
+ real_start = real_page_last + 1;
+ }
+
+ if (last < real_last) {
+ abi_ulong real_page_start = real_last - host_page_size + 1;
+ if (!mmap_frag(real_page_start, real_page_start, last,
+ target_prot, flags, fd,
+ offset + real_page_start - start)) {
+ return -1;
+ }
+ real_last = real_page_start - 1;
+ }
+
+ if (real_start > real_last) {
+ return mmap_end(start, last, -1, 0, flags, page_flags);
+ }
+
+ /*
+ * Handle the middle of the mapping.
+ */
+
+ host_len = real_last - real_start + 1;
+ want_p += real_start - start;
+
+ if (flags & MAP_ANONYMOUS) {
+ p = mmap(want_p, host_len, host_prot, flags, -1, 0);
+ } else if (!misaligned_offset) {
+ p = mmap(want_p, host_len, host_prot, flags, fd,
+ offset + real_start - start);
+ } else {
+ p = mmap(want_p, host_len, host_prot | PROT_WRITE,
+ flags | MAP_ANONYMOUS, -1, 0);
+ }
+ if (p != want_p) {
+ if (p != MAP_FAILED) {
+ do_munmap(p, host_len);
+ errno = EEXIST;
+ }
+ return -1;
+ }
+
+ if (misaligned_offset) {
+ /* TODO: The read could be short. */
+ if (pread(fd, p, host_len, offset + real_start - start) != host_len) {
+ do_munmap(p, host_len);
+ return -1;
+ }
+ if (!(host_prot & PROT_WRITE)) {
+ mprotect(p, host_len, host_prot);
+ }
+ }
+
+ return mmap_end(start, last, -1, 0, flags, page_flags);
+}
+
static abi_long target_mmap__locked(abi_ulong start, abi_ulong len,
int target_prot, int flags, int page_flags,
int fd, off_t offset)
{
int host_page_size = qemu_real_host_page_size();
- abi_ulong ret, last, real_start, real_last, retaddr, host_len;
- abi_ulong passthrough_start = -1, passthrough_last = 0;
- off_t host_offset;
int host_prot;
- real_start = start & -host_page_size;
- host_offset = offset & -host_page_size;
-
/*
* For reserved_va, we are in full control of the allocation.
* Find a suitable hole and convert to MAP_FIXED.
@@ -745,6 +873,8 @@ static abi_long target_mmap__locked(abi_ulong start, abi_ulong len,
}
flags = (flags & ~MAP_FIXED_NOREPLACE) | MAP_FIXED;
} else if (!(flags & MAP_FIXED)) {
+ abi_ulong real_start = start & -host_page_size;
+ off_t host_offset = offset & -host_page_size;
size_t real_len = len + offset - host_offset;
abi_ulong align = MAX(host_page_size, TARGET_PAGE_SIZE);
@@ -766,150 +896,10 @@ static abi_long target_mmap__locked(abi_ulong start, abi_ulong len,
} else if (host_page_size < TARGET_PAGE_SIZE) {
return mmap_h_lt_g(start, len, host_prot, flags,
page_flags, fd, offset, host_page_size);
- }
-
- if (!(flags & (MAP_FIXED | MAP_FIXED_NOREPLACE))) {
- uintptr_t host_start;
- void *p;
-
- host_len = len + offset - host_offset;
- host_len = ROUND_UP(host_len, host_page_size);
-
- /* Note: we prefer to control the mapping address. */
- p = mmap(g2h_untagged(start), host_len, host_prot,
- flags | MAP_FIXED | MAP_ANONYMOUS, -1, 0);
- if (p == MAP_FAILED) {
- return -1;
- }
- /* update start so that it points to the file position at 'offset' */
- host_start = (uintptr_t)p;
- if (!(flags & MAP_ANONYMOUS)) {
- p = mmap(g2h_untagged(start), len, host_prot,
- flags | MAP_FIXED, fd, host_offset);
- if (p == MAP_FAILED) {
- do_munmap(g2h_untagged(start), host_len);
- return -1;
- }
- host_start += offset - host_offset;
- }
- start = h2g(host_start);
- last = start + len - 1;
- passthrough_start = start;
- passthrough_last = last;
} else {
- last = start + len - 1;
- real_last = ROUND_UP(last, host_page_size) - 1;
-
- if (flags & MAP_FIXED_NOREPLACE) {
- /* Validate that the chosen range is empty. */
- if (!page_check_range_empty(start, last)) {
- errno = EEXIST;
- return -1;
- }
-
- /*
- * With reserved_va, the entire address space is mmaped in the
- * host to ensure it isn't accidentally used for something else.
- * We have just checked that the guest address is not mapped
- * within the guest, but need to replace the host reservation.
- *
- * Without reserved_va, despite the guest address check above,
- * keep MAP_FIXED_NOREPLACE so that the guest does not overwrite
- * any host address mappings.
- */
- if (reserved_va) {
- flags = (flags & ~MAP_FIXED_NOREPLACE) | MAP_FIXED;
- }
- }
-
- /*
- * worst case: we cannot map the file because the offset is not
- * aligned, so we read it
- */
- if (!(flags & MAP_ANONYMOUS) &&
- (offset & (host_page_size - 1)) != (start & (host_page_size - 1))) {
- /*
- * msync() won't work here, so we return an error if write is
- * possible while it is a shared mapping
- */
- if ((flags & MAP_TYPE) == MAP_SHARED
- && (target_prot & PROT_WRITE)) {
- errno = EINVAL;
- return -1;
- }
- retaddr = target_mmap(start, len, target_prot | PROT_WRITE,
- (flags & (MAP_FIXED | MAP_FIXED_NOREPLACE))
- | MAP_PRIVATE | MAP_ANONYMOUS,
- -1, 0);
- if (retaddr == -1) {
- return -1;
- }
- if (pread(fd, g2h_untagged(start), len, offset) == -1) {
- return -1;
- }
- if (!(target_prot & PROT_WRITE)) {
- ret = target_mprotect(start, len, target_prot);
- assert(ret == 0);
- }
- return mmap_end(start, last, -1, 0, flags, page_flags);
- }
-
- /* handle the start of the mapping */
- if (start > real_start) {
- if (real_last == real_start + host_page_size - 1) {
- /* one single host page */
- if (!mmap_frag(real_start, start, last,
- target_prot, flags, fd, offset)) {
- return -1;
- }
- return mmap_end(start, last, -1, 0, flags, page_flags);
- }
- if (!mmap_frag(real_start, start,
- real_start + host_page_size - 1,
- target_prot, flags, fd, offset)) {
- return -1;
- }
- real_start += host_page_size;
- }
- /* handle the end of the mapping */
- if (last < real_last) {
- abi_ulong real_page = real_last - host_page_size + 1;
- if (!mmap_frag(real_page, real_page, last,
- target_prot, flags, fd,
- offset + real_page - start)) {
- return -1;
- }
- real_last -= host_page_size;
- }
-
- /* map the middle (easier) */
- if (real_start < real_last) {
- void *p, *want_p;
- off_t offset1;
- size_t len1;
-
- if (flags & MAP_ANONYMOUS) {
- offset1 = 0;
- } else {
- offset1 = offset + real_start - start;
- }
- len1 = real_last - real_start + 1;
- want_p = g2h_untagged(real_start);
-
- p = mmap(want_p, len1, host_prot, flags, fd, offset1);
- if (p != want_p) {
- if (p != MAP_FAILED) {
- do_munmap(p, len1);
- errno = EEXIST;
- }
- return -1;
- }
- passthrough_start = real_start;
- passthrough_last = real_last;
- }
+ return mmap_h_gt_g(start, len, target_prot, host_prot, flags,
+ page_flags, fd, offset, host_page_size);
}
- return mmap_end(start, last, passthrough_start, passthrough_last,
- flags, page_flags);
}
/* NOTE: all the constants are the HOST ones */
--
2.34.1
next prev parent reply other threads:[~2024-03-02 4:13 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-01 23:05 [PATCH 00/60] linux-user and tcg patch queue Richard Henderson
2024-03-01 23:05 ` [PATCH 01/60] linux-user/elfload: Disable core dump if getrlimit fails Richard Henderson
2024-03-01 23:05 ` [PATCH 02/60] linux-user/elfload: Merge init_note_info and fill_note_info Richard Henderson
2024-03-01 23:05 ` [PATCH 03/60] linux-user/elfload: Tidy fill_note_info and struct elf_note_info Richard Henderson
2024-03-01 23:05 ` [PATCH 04/60] linux-user/elfload: Stack allocate struct mm_struct Richard Henderson
2024-03-01 23:05 ` [PATCH 05/60] linux-user/elfload: Latch errno before cleanup in elf_core_dump Richard Henderson
2024-03-01 23:05 ` [PATCH 06/60] linux-user/elfload: Open core file after vma_init Richard Henderson
2024-03-01 23:05 ` [PATCH 07/60] linux-user/elfload: Truncate core file on open Richard Henderson
2024-03-01 23:05 ` [PATCH 08/60] linux-user/elfload: Lock cpu list and mmap during elf_core_dump Richard Henderson
2024-03-01 23:05 ` [PATCH 09/60] linux-user/elfload: Size corefile before opening Richard Henderson
2024-03-01 23:05 ` [PATCH 10/60] linux-user/elfload: Write corefile elf header in one block Richard Henderson
2024-03-01 23:05 ` [PATCH 11/60] linux-user/elfload: Write process memory to core file in larger chunks Richard Henderson
2024-03-01 23:05 ` [PATCH 12/60] linux-user/elfload: Simplify vma_dump_size Richard Henderson
2024-03-01 23:05 ` [PATCH 13/60] linux-user/elfload: Rely on walk_memory_regions for vmas Richard Henderson
2024-03-01 23:05 ` [PATCH 14/60] linux-user/elfload: Unprotect regions before core dump Richard Henderson
2024-03-01 23:05 ` [PATCH 15/60] tcg/aarch64: Apple does not align __int128_t in even registers Richard Henderson
2024-03-01 23:05 ` [PATCH 16/60] accel/tcg: Set can_do_io at at start of lookup_tb_ptr helper Richard Henderson
2024-03-01 23:05 ` [PATCH 17/60] tcg: Avoid double lock if page tables happen to be in mmio memory Richard Henderson
2024-03-01 23:05 ` [PATCH 18/60] accel/tcg: Remove qemu_host_page_size from page_protect/page_unprotect Richard Henderson
2024-03-01 23:05 ` [PATCH 19/60] linux-user: Adjust SVr4 NULL page mapping Richard Henderson
2024-03-01 23:05 ` [PATCH 20/60] linux-user: Remove qemu_host_page_{size, mask} in probe_guest_base Richard Henderson
2024-03-01 23:05 ` [PATCH 21/60] linux-user: Remove qemu_host_page_size from create_elf_tables Richard Henderson
2024-03-01 23:05 ` [PATCH 22/60] linux-user/hppa: Simplify init_guest_commpage Richard Henderson
2024-03-01 23:05 ` [PATCH 23/60] linux-user/nios2: Remove qemu_host_page_size from init_guest_commpage Richard Henderson
2024-03-01 23:05 ` [PATCH 24/60] linux-user/arm: " Richard Henderson
2024-03-01 23:05 ` [PATCH 25/60] linux-user: Remove qemu_host_page_size from elf_core_dump Richard Henderson
2024-03-01 23:05 ` [PATCH 26/60] linux-user: Remove qemu_host_page_{size, mask} from mmap.c Richard Henderson
2024-03-01 23:05 ` [PATCH 27/60] linux-user: Remove REAL_HOST_PAGE_ALIGN " Richard Henderson
2024-03-01 23:05 ` [PATCH 28/60] linux-user: Remove HOST_PAGE_ALIGN " Richard Henderson
2024-03-01 23:05 ` [PATCH 29/60] migration: Remove qemu_host_page_size Richard Henderson
2024-03-01 23:05 ` [PATCH 30/60] hw/tpm: Remove HOST_PAGE_ALIGN from tpm_ppi_init Richard Henderson
2024-03-01 23:05 ` [PATCH 31/60] softmmu/physmem: Remove qemu_host_page_size Richard Henderson
2024-03-01 23:05 ` [PATCH 32/60] softmmu/physmem: Remove HOST_PAGE_ALIGN Richard Henderson
2024-03-01 23:05 ` [PATCH 33/60] linux-user: Remove qemu_host_page_size from main Richard Henderson
2024-03-01 23:05 ` [PATCH 34/60] linux-user: Split out target_mmap__locked Richard Henderson
2024-03-01 23:05 ` [PATCH 35/60] linux-user: Move some mmap checks outside the lock Richard Henderson
2024-03-01 23:05 ` [PATCH 36/60] linux-user: Fix sub-host-page mmap Richard Henderson
2024-03-01 23:05 ` [PATCH 37/60] linux-user: Split out mmap_end Richard Henderson
2024-03-01 23:05 ` [PATCH 38/60] linux-user: Do early mmap placement only for reserved_va Richard Henderson
2024-03-01 23:05 ` [PATCH 39/60] linux-user: Split out do_munmap Richard Henderson
2024-03-01 23:05 ` [PATCH 40/60] linux-user: Use do_munmap for target_mmap failure Richard Henderson
2024-03-01 23:06 ` [PATCH 41/60] linux-user: Split out mmap_h_eq_g Richard Henderson
2024-03-01 23:06 ` [PATCH 42/60] linux-user: Split out mmap_h_lt_g Richard Henderson
2024-03-01 23:06 ` Richard Henderson [this message]
2024-03-01 23:06 ` [PATCH 44/60] tests/tcg: Remove run-test-mmap-* Richard Henderson
2024-03-01 23:06 ` [PATCH 45/60] tests/tcg: Extend file in linux-madvise.c Richard Henderson
2024-03-01 23:06 ` [PATCH 46/60] *-user: Deprecate and disable -p pagesize Richard Henderson
2024-03-01 23:06 ` [PATCH 47/60] cpu: Remove page_size_init Richard Henderson
2024-03-01 23:06 ` [PATCH 48/60] accel/tcg: Disconnect TargetPageDataNode from page size Richard Henderson
2024-03-01 23:06 ` [PATCH 49/60] linux-user: Allow TARGET_PAGE_BITS_VARY Richard Henderson
2024-03-01 23:06 ` [PATCH 50/60] target/arm: Enable TARGET_PAGE_BITS_VARY for AArch64 user-only Richard Henderson
2024-03-01 23:06 ` [PATCH 51/60] linux-user: Bound mmap_min_addr by host page size Richard Henderson
2024-03-01 23:06 ` [PATCH 52/60] target/ppc: Enable TARGET_PAGE_BITS_VARY for user-only Richard Henderson
2024-03-01 23:06 ` [PATCH 53/60] target/alpha: " Richard Henderson
2024-03-01 23:06 ` [PATCH 54/60] linux-user: Remove pgb_dynamic alignment assertion Richard Henderson
2024-03-01 23:06 ` [PATCH 55/60] tcg/optimize: fix uninitialized variable Richard Henderson
2024-03-01 23:06 ` [PATCH 56/60] linux-user/x86_64: Handle the vsyscall page in open_self_maps_{2, 4} Richard Henderson
2024-04-11 22:09 ` Michael Tokarev
2024-03-01 23:06 ` [PATCH 57/60] linux-user/loongarch64: Remove TARGET_FORCE_SHMLBA Richard Henderson
2024-03-01 23:06 ` [PATCH 58/60] linux-user: Add strace for shmat Richard Henderson
2024-03-01 23:06 ` [PATCH 59/60] linux-user: Rewrite target_shmat Richard Henderson
2024-03-01 23:06 ` [PATCH 60/60] tests/tcg: Check that shmat() does not break /proc/self/maps Richard Henderson
2024-03-01 23:13 ` [PULL 00/60] linux-user and tcg patch queue Richard Henderson
2024-03-05 11:17 ` [PATCH " Peter Maydell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240301230619.661008-44-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=deller@gmx.de \
--cc=pierrick.bouvier@linaro.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).