Merge tag 'pull-tcg-20230805' of https://gitlab.com/rth7680/qemu into…

… staging

accel/tcg: Do not issue misaligned i/o
accel/tcg: Call save_iotlb_data from io_readx
gdbstub: use 0 ("any process") on packets with no PID
linux-user: Fixes for MAP_FIXED_NOREPLACE
linux-user: Fixes for brk
linux-user: Adjust task_unmapped_base for reserved_va
linux-user: Use ELF_ET_DYN_BASE for ET_DYN with interpreter
linux-user: Remove host != guest page size workarounds in brk and image load
linux-user: Set V in ELF_HWCAP for RISC-V
*-user: Remove last_brk as unused

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmTPFQkdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV9B/ggAlYHsJAJdQaGXYTZD
# 8ycXAUAKSovIxLbI0nGDgr9qjFeoMLYB0FYlN3Xur9yY3olOcQYIdL81Cog/RAti
# RooQt1U3VaXIXwSb+fniM9yqu0vP8KrBlH5HgU3dViNa9AYkRXHypmo1j1vRKWL9
# C1GGoY9pehlvLvWweA5BuW1f8cMPX4xG1WJBX1nl3/JMRHCOerUnw0Q6cGqlmFAI
# IV32lkXnbLh9zkSeuizi2F+zZP1MuYOjR7nzqlfU/R4E6bKCdPl/FfCQNkA4VjUM
# SRHWljjKwk3/MbYi4PSs9aS1fKKv+fLdzeAzrMJhGri72CsAHXennaJ3rqk2Bu3U
# you+9g==
# =rI/G
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 05 Aug 2023 08:35:37 PM PDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* tag 'pull-tcg-20230805' of https://gitlab.com/rth7680/qemu: (24 commits)
  linux-user/elfload: Set V in ELF_HWCAP for RISC-V
  accel/tcg: Call save_iotlb_data from io_readx as well.
  linux-user: Use zero_bss for PT_LOAD with no file contents too
  linux-user: Do not adjust zero_bss for host page size
  linux-user: Do not adjust image mapping for host page size
  linux-user: Properly set image_info.brk in flatload
  linux-user: Adjust initial brk when interpreter is close to executable
  linux-user: Use elf_et_dyn_base for ET_DYN with interpreter
  linux-user: Use MAP_FIXED_NOREPLACE for initial image mmap
  linux-user: Define ELF_ET_DYN_BASE in $guest/target_mman.h
  linux-user: Define TASK_UNMAPPED_BASE in $guest/target_mman.h
  linux-user: Adjust task_unmapped_base for reserved_va
  bsd-user: Remove last_brk
  linux-user: Remove last_brk
  linux-user: Do not align brk with host page size
  linux-user: Do nothing if too small brk is specified
  linux-user: Use MAP_FIXED_NOREPLACE for do_brk()
  linux-user: Do not call get_errno() in do_brk()
  linux-user: Fix MAP_FIXED_NOREPLACE on old kernels
  linux-user: Unset MAP_FIXED_NOREPLACE for host
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

bsd-user/mmap.c

@@ -214,8 +214,6 @@ static int mmap_frag(abi_ulong real_start,
 #endif
 abi_ulong mmap_next_start = TASK_UNMAPPED_BASE;
 
-unsigned long last_brk;
-
 /*
  * Subroutine of mmap_find_vma, used when we have pre-allocated a chunk of guest
  * address space.

bsd-user/qemu.h

@@ -232,7 +232,6 @@ abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
                        abi_ulong new_size, unsigned long flags,
                        abi_ulong new_addr);
 int target_msync(abi_ulong start, abi_ulong len, int flags);
-extern unsigned long last_brk;
 extern abi_ulong mmap_next_start;
 abi_ulong mmap_find_vma(abi_ulong start, abi_ulong size);
 void TSA_NO_TSA mmap_fork_start(void);

gdbstub/gdbstub.c

@@ -537,7 +537,7 @@ static GDBThreadIdKind read_thread_id(const char *buf, const char **end_buf,
         /* Skip '.' */
         buf++;
     } else {
-        p = 1;
+        p = 0;
     }
 
     ret = qemu_strtoul(buf, &buf, 16, &t);

linux-user/aarch64/target_mman.h

@@ -4,6 +4,19 @@
 #define TARGET_PROT_BTI         0x10
 #define TARGET_PROT_MTE         0x20
 
+/*
+ * arch/arm64/include/asm/processor.h:
+ *
+ * TASK_UNMAPPED_BASE     DEFAULT_MAP_WINDOW / 4
+ * DEFAULT_MAP_WINDOW     DEFAULT_MAP_WINDOW_64
+ * DEFAULT_MAP_WINDOW_64  UL(1) << VA_BITS_MIN
+ * VA_BITS_MIN            48 (unless explicitly configured smaller)
+ */
+#define TASK_UNMAPPED_BASE      (1ull << (48 - 2))
+
+/* arch/arm64/include/asm/elf.h */
+#define ELF_ET_DYN_BASE         TARGET_PAGE_ALIGN((1ull << 48) / 3 * 2)
+
 #include "../generic/target_mman.h"
 
 #endif

linux-user/alpha/target_mman.h

@@ -20,6 +20,17 @@
 #define TARGET_MS_SYNC 2
 #define TARGET_MS_INVALIDATE 4
 
+/*
+ * arch/alpha/include/asm/processor.h:
+ *
+ * TASK_UNMAPPED_BASE           TASK_SIZE / 2
+ * TASK_SIZE                    0x40000000000UL
+ */
+#define TASK_UNMAPPED_BASE      0x20000000000ull
+
+/* arch/alpha/include/asm/elf.h */
+#define ELF_ET_DYN_BASE         (TASK_UNMAPPED_BASE + 0x1000000)
+
 #include "../generic/target_mman.h"
 
 #endif

linux-user/arm/target_mman.h

@@ -1 +1,12 @@
+/*
+ * arch/arm/include/asm/memory.h
+ * TASK_UNMAPPED_BASE        ALIGN(TASK_SIZE / 3, SZ_16M)
+ * TASK_SIZE                 CONFIG_PAGE_OFFSET
+ * CONFIG_PAGE_OFFSET        0xC0000000 (default in Kconfig)
+ */
+#define TASK_UNMAPPED_BASE   0x40000000
+
+/* arch/arm/include/asm/elf.h */
+#define ELF_ET_DYN_BASE      0x00400000
+
 #include "../generic/target_mman.h"

linux-user/cris/target_mman.h

@@ -1 +1,13 @@
+/*
+ * arch/cris/include/asm/processor.h:
+ * TASK_UNMAPPED_BASE      (PAGE_ALIGN(TASK_SIZE / 3))
+ *
+ * arch/cris/include/arch-v32/arch/processor.h
+ * TASK_SIZE               0xb0000000
+ */
+#define TASK_UNMAPPED_BASE TARGET_PAGE_ALIGN(0xb0000000 / 3)
+
+/* arch/cris/include/uapi/asm/elf.h */
+#define ELF_ET_DYN_BASE    (TASK_UNMAPPED_BASE * 2)
+
 #include "../generic/target_mman.h"

linux-user/elfload.c

@@ -1710,7 +1710,8 @@ static uint32_t get_elf_hwcap(void)
 #define MISA_BIT(EXT) (1 << (EXT - 'A'))
     RISCVCPU *cpu = RISCV_CPU(thread_cpu);
     uint32_t mask = MISA_BIT('I') | MISA_BIT('M') | MISA_BIT('A')
-                    | MISA_BIT('F') | MISA_BIT('D') | MISA_BIT('C');
+                    | MISA_BIT('F') | MISA_BIT('D') | MISA_BIT('C')
+                    | MISA_BIT('V');
 
     return cpu->env.misa_ext & mask;
 #undef MISA_BIT
@@ -1959,15 +1960,6 @@ struct exec
 #define ZMAGIC 0413
 #define QMAGIC 0314
 
-/* Necessary parameters */
-#define TARGET_ELF_EXEC_PAGESIZE \
-        (((eppnt->p_align & ~qemu_host_page_mask) != 0) ? \
-         TARGET_PAGE_SIZE : MAX(qemu_host_page_size, TARGET_PAGE_SIZE))
-#define TARGET_ELF_PAGELENGTH(_v) ROUND_UP((_v), TARGET_ELF_EXEC_PAGESIZE)
-#define TARGET_ELF_PAGESTART(_v) ((_v) & \
-                                 ~(abi_ulong)(TARGET_ELF_EXEC_PAGESIZE-1))
-#define TARGET_ELF_PAGEOFFSET(_v) ((_v) & (TARGET_ELF_EXEC_PAGESIZE-1))
-
 #define DLINFO_ITEMS 16
 
 static inline void memcpy_fromfs(void * to, const void * from, unsigned long n)
@@ -2221,44 +2213,36 @@ static abi_ulong setup_arg_pages(struct linux_binprm *bprm,
 
 /* Map and zero the bss.  We need to explicitly zero any fractional pages
    after the data section (i.e. bss).  */
-static void zero_bss(abi_ulong elf_bss, abi_ulong last_bss, int prot)
+static void zero_bss(abi_ulong start_bss, abi_ulong end_bss, int prot)
 {
-    uintptr_t host_start, host_map_start, host_end;
-
-    last_bss = TARGET_PAGE_ALIGN(last_bss);
-
-    /* ??? There is confusion between qemu_real_host_page_size and
-       qemu_host_page_size here and elsewhere in target_mmap, which
-       may lead to the end of the data section mapping from the file
-       not being mapped.  At least there was an explicit test and
-       comment for that here, suggesting that "the file size must
-       be known".  The comment probably pre-dates the introduction
-       of the fstat system call in target_mmap which does in fact
-       find out the size.  What isn't clear is if the workaround
-       here is still actually needed.  For now, continue with it,
-       but merge it with the "normal" mmap that would allocate the bss.  */
-
-    host_start = (uintptr_t) g2h_untagged(elf_bss);
-    host_end = (uintptr_t) g2h_untagged(last_bss);
-    host_map_start = REAL_HOST_PAGE_ALIGN(host_start);
-
-    if (host_map_start < host_end) {
-        void *p = mmap((void *)host_map_start, host_end - host_map_start,
-                       prot, MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-        if (p == MAP_FAILED) {
-            perror("cannot mmap brk");
-            exit(-1);
-        }
-    }
+    abi_ulong align_bss;
+
+    align_bss = TARGET_PAGE_ALIGN(start_bss);
+    end_bss = TARGET_PAGE_ALIGN(end_bss);
 
-    /* Ensure that the bss page(s) are valid */
-    if ((page_get_flags(last_bss-1) & prot) != prot) {
-        page_set_flags(elf_bss & TARGET_PAGE_MASK, last_bss - 1,
-                       prot | PAGE_VALID);
+    if (start_bss < align_bss) {
+        int flags = page_get_flags(start_bss);
+
+        if (!(flags & PAGE_VALID)) {
+            /* Map the start of the bss. */
+            align_bss -= TARGET_PAGE_SIZE;
+        } else if (flags & PAGE_WRITE) {
+            /* The page is already mapped writable. */
+            memset(g2h_untagged(start_bss), 0, align_bss - start_bss);
+        } else {
+            /* Read-only zeros? */
+            g_assert_not_reached();
+        }
     }
 
-    if (host_start < host_map_start) {
-        memset((void *)host_start, 0, host_map_start - host_start);
+    if (align_bss < end_bss) {
+        abi_long err = target_mmap(align_bss, end_bss - align_bss, prot,
+                                   MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS,
+                                   -1, 0);
+        if (err == -1) {
+            perror("cannot mmap brk");
+            exit(-1);
+        }
     }
 }
 
@@ -3106,60 +3090,65 @@ static void load_elf_image(const char *image_name, int image_fd,
         }
     }
 
-    if (pinterp_name != NULL) {
-        /*
-         * This is the main executable.
-         *
-         * Reserve extra space for brk.
-         * We hold on to this space while placing the interpreter
-         * and the stack, lest they be placed immediately after
-         * the data segment and block allocation from the brk.
-         *
-         * 16MB is chosen as "large enough" without being so large as
-         * to allow the result to not fit with a 32-bit guest on a
-         * 32-bit host. However some 64 bit guests (e.g. s390x)
-         * attempt to place their heap further ahead and currently
-         * nothing stops them smashing into QEMUs address space.
-         */
-#if TARGET_LONG_BITS == 64
-        info->reserve_brk = 32 * MiB;
-#else
-        info->reserve_brk = 16 * MiB;
-#endif
-        hiaddr += info->reserve_brk;
+    load_addr = loaddr;
 
+    if (pinterp_name != NULL) {
         if (ehdr->e_type == ET_EXEC) {
             /*
              * Make sure that the low address does not conflict with
              * MMAP_MIN_ADDR or the QEMU application itself.
              */
             probe_guest_base(image_name, loaddr, hiaddr);
         } else {
+            abi_ulong align;
+
             /*
              * The binary is dynamic, but we still need to
              * select guest_base.  In this case we pass a size.
              */
             probe_guest_base(image_name, 0, hiaddr - loaddr);
+
+            /*
+             * Avoid collision with the loader by providing a different
+             * default load address.
+             */
+            load_addr += elf_et_dyn_base;
+
+            /*
+             * TODO: Better support for mmap alignment is desirable.
+             * Since we do not have complete control over the guest
+             * address space, we prefer the kernel to choose some address
+             * rather than force the use of LOAD_ADDR via MAP_FIXED.
+             * But without MAP_FIXED we cannot guarantee alignment,
+             * only suggest it.
+             */
+            align = pow2ceil(info->alignment);
+            if (align) {
+                load_addr &= -align;
+            }
         }
     }
 
     /*
      * Reserve address space for all of this.
      *
-     * In the case of ET_EXEC, we supply MAP_FIXED so that we get
-     * exactly the address range that is required.
+     * In the case of ET_EXEC, we supply MAP_FIXED_NOREPLACE so that we get
+     * exactly the address range that is required.  Without reserved_va,
+     * the guest address space is not isolated.  We have attempted to avoid
+     * conflict with the host program itself via probe_guest_base, but using
+     * MAP_FIXED_NOREPLACE instead of MAP_FIXED provides an extra check.
      *
      * Otherwise this is ET_DYN, and we are searching for a location
      * that can hold the memory space required.  If the image is
-     * pre-linked, LOADDR will be non-zero, and the kernel should
+     * pre-linked, LOAD_ADDR will be non-zero, and the kernel should
      * honor that address if it happens to be free.
      *
      * In both cases, we will overwrite pages in this range with mappings
      * from the executable.
      */
-    load_addr = target_mmap(loaddr, (size_t)hiaddr - loaddr + 1, PROT_NONE,
+    load_addr = target_mmap(load_addr, (size_t)hiaddr - loaddr + 1, PROT_NONE,
                             MAP_PRIVATE | MAP_ANON | MAP_NORESERVE |
-                            (ehdr->e_type == ET_EXEC ? MAP_FIXED : 0),
+                            (ehdr->e_type == ET_EXEC ? MAP_FIXED_NOREPLACE : 0),
                             -1, 0);
     if (load_addr == -1) {
         goto exit_mmap;
@@ -3194,7 +3183,8 @@ static void load_elf_image(const char *image_name, int image_fd,
     info->end_code = 0;
     info->start_data = -1;
     info->end_data = 0;
-    info->brk = 0;
+    /* Usual start for brk is after all sections of the main executable. */
+    info->brk = TARGET_PAGE_ALIGN(hiaddr);
     info->elf_flags = ehdr->e_flags;
 
     prot_exec = PROT_EXEC;
@@ -3220,7 +3210,7 @@ static void load_elf_image(const char *image_name, int image_fd,
     for (i = 0; i < ehdr->e_phnum; i++) {
         struct elf_phdr *eppnt = phdr + i;
         if (eppnt->p_type == PT_LOAD) {
-            abi_ulong vaddr, vaddr_po, vaddr_ps, vaddr_ef, vaddr_em, vaddr_len;
+            abi_ulong vaddr, vaddr_po, vaddr_ps, vaddr_ef, vaddr_em;
             int elf_prot = 0;
 
             if (eppnt->p_flags & PF_R) {
@@ -3234,8 +3224,8 @@ static void load_elf_image(const char *image_name, int image_fd,
             }
 
             vaddr = load_bias + eppnt->p_vaddr;
-            vaddr_po = TARGET_ELF_PAGEOFFSET(vaddr);
-            vaddr_ps = TARGET_ELF_PAGESTART(vaddr);
+            vaddr_po = vaddr & ~TARGET_PAGE_MASK;
+            vaddr_ps = vaddr & TARGET_PAGE_MASK;
 
             vaddr_ef = vaddr + eppnt->p_filesz;
             vaddr_em = vaddr + eppnt->p_memsz;
@@ -3245,30 +3235,17 @@ static void load_elf_image(const char *image_name, int image_fd,
              * but no backing file segment.
              */
             if (eppnt->p_filesz != 0) {
-                vaddr_len = TARGET_ELF_PAGELENGTH(eppnt->p_filesz + vaddr_po);
-                error = target_mmap(vaddr_ps, vaddr_len, elf_prot,
-                                    MAP_PRIVATE | MAP_FIXED,
+                error = target_mmap(vaddr_ps, eppnt->p_filesz + vaddr_po,
+                                    elf_prot, MAP_PRIVATE | MAP_FIXED,
                                     image_fd, eppnt->p_offset - vaddr_po);
-
                 if (error == -1) {
                     goto exit_mmap;
                 }
+            }
 
-                /*
-                 * If the load segment requests extra zeros (e.g. bss), map it.
-                 */
-                if (eppnt->p_filesz < eppnt->p_memsz) {
-                    zero_bss(vaddr_ef, vaddr_em, elf_prot);
-                }
-            } else if (eppnt->p_memsz != 0) {
-                vaddr_len = TARGET_ELF_PAGELENGTH(eppnt->p_memsz + vaddr_po);
-                error = target_mmap(vaddr_ps, vaddr_len, elf_prot,
-                                    MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS,
-                                    -1, 0);
-
-                if (error == -1) {
-                    goto exit_mmap;
-                }
+            /* If the load segment requests extra zeros (e.g. bss), map it. */
+            if (vaddr_ef < vaddr_em) {
+                zero_bss(vaddr_ef, vaddr_em, elf_prot);
             }
 
             /* Find the full program boundaries.  */
@@ -3288,9 +3265,6 @@ static void load_elf_image(const char *image_name, int image_fd,
                     info->end_data = vaddr_ef;
                 }
             }
-            if (vaddr_em > info->brk) {
-                info->brk = vaddr_em;
-            }
 #ifdef TARGET_MIPS
         } else if (eppnt->p_type == PT_MIPS_ABIFLAGS) {
             Mips_elf_abiflags_v0 abiflags;
@@ -3619,6 +3593,19 @@ int load_elf_binary(struct linux_binprm *bprm, struct image_info *info)
     if (elf_interpreter) {
         load_elf_interp(elf_interpreter, &interp_info, bprm->buf);
 
+        /*
+         * While unusual because of ELF_ET_DYN_BASE, if we are unlucky
+         * with the mappings the interpreter can be loaded above but
+         * near the main executable, which can leave very little room
+         * for the heap.
+         * If the current brk has less than 16MB, use the end of the
+         * interpreter.
+         */
+        if (interp_info.brk > info->brk &&
+            interp_info.load_bias - info->brk < 16 * MiB)  {
+            info->brk = interp_info.brk;
+        }
+
         /* If the program interpreter is one of these two, then assume
            an iBCS2 image.  Otherwise assume a native linux image.  */
 
@@ -3672,17 +3659,6 @@ int load_elf_binary(struct linux_binprm *bprm, struct image_info *info)
     bprm->core_dump = &elf_core_dump;
 #endif
 
-    /*
-     * If we reserved extra space for brk, release it now.
-     * The implementation of do_brk in syscalls.c expects to be able
-     * to mmap pages in this space.
-     */
-    if (info->reserve_brk) {
-        abi_ulong start_brk = HOST_PAGE_ALIGN(info->brk);
-        abi_ulong end_brk = HOST_PAGE_ALIGN(info->brk + info->reserve_brk);
-        target_munmap(start_brk, end_brk - start_brk);
-    }
-
     return 0;
 }